This is a table of type bigram and their frequencies. Use it to search & browse the list to learn more about your study carrel.
bigram | frequency |
---|---|
public health | 803 |
machine learning | 738 |
social media | 518 |
big data | 506 |
health care | 454 |
mental health | 363 |
deep learning | 353 |
data sets | 322 |
data sharing | 314 |
infectious disease | 308 |
data collection | 294 |
time series | 288 |
data set | 278 |
artificial intelligence | 276 |
infectious diseases | 269 |
data sources | 264 |
risk factors | 245 |
personal data | 236 |
data protection | 233 |
emergency department | 206 |
data analysis | 197 |
united states | 196 |
contact tracing | 193 |
mobile phone | 191 |
health services | 185 |
abstract background | 184 |
missing data | 183 |
clinical trials | 179 |
doc id | 179 |
cord uid | 179 |
supply chain | 171 |
neural networks | 167 |
logistic regression | 160 |
systematic review | 157 |
data collected | 153 |
data analytics | 153 |
breast cancer | 153 |
altmetric data | 152 |
blood pressure | 146 |
data streams | 143 |
federated learning | 138 |
location data | 135 |
data mining | 130 |
data storage | 128 |
neural network | 125 |
phone data | 125 |
social distancing | 122 |
confirmed cases | 121 |
data processing | 120 |
raw data | 117 |
decision making | 117 |
open source | 117 |
new york | 114 |
cardiac arrest | 112 |
cohort study | 110 |
training data | 109 |
blockchain technology | 109 |
gene expression | 107 |
remote sensing | 106 |
digital health | 106 |
total number | 105 |
social networks | 101 |
research topics | 100 |
information systems | 100 |
ed patients | 99 |
data integration | 99 |
real time | 99 |
made available | 98 |
clinical data | 97 |
health information | 97 |
novel coronavirus | 96 |
learning algorithms | 96 |
large number | 95 |
health data | 94 |
case study | 92 |
collected data | 91 |
series data | 90 |
surveillance systems | 90 |
electronic health | 90 |
statistically significant | 89 |
sequence data | 88 |
ed visits | 87 |
heart rate | 87 |
data will | 87 |
data quality | 87 |
publicly available | 86 |
mobility data | 86 |
protein interactions | 84 |
epidemiological data | 84 |
new data | 83 |
coronavirus disease | 83 |
different types | 83 |
world health | 82 |
increased risk | 82 |
available data | 82 |
ai systems | 82 |
will also | 82 |
genomic data | 82 |
data stream | 81 |
input data | 81 |
access control | 81 |
open data | 80 |
syndromic surveillance | 80 |
human mobility | 79 |
surveillance data | 79 |
disease outbreaks | 78 |
emergency medicine | 78 |
acute respiratory | 78 |
patients presenting | 77 |
respiratory syndrome | 77 |
disease control | 77 |
media platforms | 77 |
data may | 76 |
protein interaction | 76 |
primary care | 76 |
heart failure | 75 |
mean age | 75 |
time data | 74 |
data types | 74 |
iot devices | 73 |
health organization | 73 |
data management | 73 |
least one | 72 |
ebola virus | 72 |
data science | 72 |
disease transmission | 72 |
pandemic influenza | 72 |
high risk | 72 |
determine whether | 71 |
surveillance system | 71 |
natural language | 71 |
may also | 70 |
using data | 70 |
data points | 70 |
even though | 70 |
gs standards | 69 |
precision medicine | 69 |
real world | 68 |
health status | 67 |
statistical methods | 67 |
genetic information | 66 |
copyright holder | 66 |
health records | 66 |
medical data | 65 |
control group | 65 |
physical activity | 65 |
disease surveillance | 65 |
statistical analysis | 65 |
health surveillance | 64 |
cancer risk | 64 |
widely used | 64 |
hiv aids | 64 |
wide range | 64 |
linear regression | 63 |
risk assessment | 63 |
genetic data | 63 |
risk factor | 63 |
early detection | 63 |
service providers | 63 |
global health | 62 |
two groups | 62 |
data acquisition | 62 |
years old | 62 |
social network | 62 |
model parameters | 62 |
health system | 62 |
intensive care | 62 |
ed data | 61 |
data source | 61 |
data access | 61 |
media data | 61 |
data available | 60 |
general population | 60 |
granted medrxiv | 60 |
learning methods | 60 |
first step | 60 |
clinical practice | 60 |
health authorities | 60 |
ml based | 60 |
developing countries | 60 |
predictive models | 60 |
author funder | 60 |
atrial fibrillation | 60 |
data using | 59 |
recent years | 59 |
literature review | 59 |
regression analysis | 59 |
influenza pandemic | 59 |
phylogenetic trees | 58 |
rare diseases | 58 |
reproduction number | 57 |
patient data | 56 |
drug sales | 56 |
version posted | 56 |
sharing data | 55 |
language processing | 55 |
descriptive statistics | 55 |
will provide | 55 |
sample size | 55 |
ed visit | 55 |
vital signs | 54 |
outbreak detection | 54 |
supply chains | 54 |
different sources | 53 |
source data | 53 |
commonly used | 53 |
chief complaint | 53 |
health problems | 53 |
study period | 53 |
inclusion criteria | 53 |
may lead | 53 |
incubation period | 52 |
systems biology | 52 |
deep neural | 52 |
peer review | 52 |
severe acute | 52 |
confidence intervals | 51 |
disease outbreak | 51 |
posterior predictive | 51 |
long term | 51 |
omics data | 51 |
urban areas | 50 |
smart manufacturing | 50 |
across different | 50 |
future research | 50 |
policy makers | 50 |
randomized controlled | 50 |
different countries | 50 |
data scientists | 50 |
privacy concerns | 50 |
money laundering | 50 |
among patients | 50 |
important role | 49 |
analyzed using | 49 |
observational study | 49 |
medical records | 49 |
patient care | 49 |
based models | 49 |
mobile devices | 49 |
health outcomes | 49 |
informed consent | 48 |
west african | 48 |
hot research | 48 |
sentiment analysis | 48 |
based data | 48 |
lung cancer | 48 |
will need | 48 |
different data | 48 |
clinical trial | 48 |
significant differences | 48 |
factors associated | 48 |
medical record | 47 |
research community | 47 |
transfer learning | 47 |
will require | 47 |
related data | 47 |
calculated using | 47 |
best practices | 47 |
interaction data | 47 |
urban health | 47 |
national health | 47 |
data across | 47 |
privacy protection | 47 |
ebola epidemic | 47 |
smart cities | 46 |
computer science | 46 |
results show | 46 |
chest pain | 46 |
myocardial infarction | 46 |
data obtained | 46 |
rfid reader | 46 |
better understand | 46 |
healthcare data | 46 |
human rights | 46 |
healthcare system | 46 |
data provided | 46 |
reinforcement learning | 46 |
confidence interval | 46 |
standard deviation | 46 |
disease spread | 45 |
empirical data | 45 |
nc detect | 45 |
wearable devices | 45 |
electronic medical | 45 |
decision support | 45 |
two different | 45 |
nan doi | 45 |
per day | 45 |
super cell | 45 |
dna data | 45 |
mathematical models | 45 |
kde bioscience | 45 |
news articles | 44 |
controlled trial | 44 |
network models | 44 |
significant difference | 44 |
missing values | 44 |
control measures | 44 |
infection rate | 44 |
african ebola | 44 |
among others | 44 |
infected individuals | 44 |
collect data | 44 |
emergency departments | 44 |
prospective cohort | 43 |
travel restrictions | 43 |
data used | 43 |
across multiple | 43 |
will help | 43 |
international license | 43 |
tertiary care | 43 |
performed using | 43 |
information technology | 43 |
see table | 43 |
data entry | 43 |
metabolic syndrome | 43 |
health policy | 43 |
drug use | 43 |
gold standard | 43 |
transmission dynamics | 43 |
data visualization | 43 |
health systems | 43 |
cloud computing | 42 |
york city | 42 |
different kinds | 42 |
convolutional neural | 42 |
mitigation strategies | 42 |
new technologies | 42 |
age group | 42 |
loss function | 42 |
health professionals | 42 |
virus disease | 42 |
learning models | 42 |
data must | 42 |
smart contracts | 42 |
real data | 41 |
adverse events | 41 |
zika virus | 41 |
systems medicine | 41 |
user interface | 41 |
public interest | 41 |
data generated | 41 |
medical research | 41 |
fake news | 41 |
care providers | 41 |
original data | 41 |
large amounts | 40 |
data type | 40 |
less likely | 40 |
primary health | 40 |
care system | 40 |
medical care | 40 |
analytics package | 40 |
bayesian inference | 40 |
pregnant women | 40 |
birth weight | 40 |
small number | 40 |
next step | 40 |
proposed system | 40 |
climate change | 40 |
new cases | 40 |
use cases | 40 |
medical center | 39 |
one year | 39 |
providable data | 39 |
relative risk | 39 |
relevant data | 39 |
general public | 39 |
median age | 39 |
human behavior | 39 |
based approach | 39 |
substitution model | 39 |
disease dynamics | 39 |
open access | 39 |
age groups | 39 |
expression data | 39 |
member states | 39 |
mf prevalence | 39 |
scientific community | 39 |
open science | 39 |
ai ethics | 39 |
time period | 39 |
high level | 39 |
primary outcome | 39 |
share data | 39 |
schema changes | 39 |
demographic data | 38 |
poster sessions | 38 |
data exchange | 38 |
clock models | 38 |
case data | 38 |
safety data | 38 |
large scale | 38 |
influenza virus | 38 |
food traceability | 38 |
smart city | 38 |
data needs | 38 |
health insurance | 38 |
consumer protection | 38 |
previous studies | 38 |
clock model | 38 |
time intervals | 37 |
historical data | 37 |
use case | 37 |
predictive value | 37 |
third parties | 37 |
based methods | 37 |
three different | 37 |
data requests | 37 |
experimental data | 37 |
significantly higher | 37 |
sensor data | 37 |
significantly associated | 37 |
monte carlo | 37 |
sensitive data | 37 |
contact patterns | 37 |
heart disease | 36 |
heterogeneous data | 36 |
sectional study | 36 |
reported cases | 36 |
modeling approaches | 36 |
genome sequencing | 36 |
nan sha | 36 |
clinical research | 36 |
data availability | 36 |
digital data | 36 |
european countries | 36 |
adult patients | 36 |
temporal data | 36 |
high quality | 36 |
per year | 36 |
mortality rates | 36 |
also provide | 36 |
odds ratios | 36 |
interaction networks | 36 |
medical students | 36 |
controlled trials | 36 |
health officials | 36 |
model predictions | 36 |
million people | 36 |
health record | 35 |
time points | 35 |
hospital admission | 35 |
learning techniques | 35 |
population density | 35 |
multiple sources | 35 |
medrxiv preprint | 35 |
information system | 35 |
recurrent neural | 35 |
better understanding | 35 |
serial interval | 35 |
different levels | 35 |
learning model | 35 |
sales data | 35 |
data privacy | 35 |
smart nodes | 35 |
health research | 35 |
object detection | 34 |
many countries | 34 |
text mining | 34 |
public good | 34 |
health centre | 34 |
healthcare systems | 34 |
time spent | 34 |
early stages | 34 |
digital contact | 34 |
ct scans | 34 |
parameter values | 34 |
health promotion | 34 |
clinical decision | 34 |
demographic characteristics | 34 |
ebola outbreak | 34 |
chart review | 34 |
west africa | 34 |
latent space | 34 |
future work | 34 |
supervised learning | 34 |
will allow | 34 |
regression models | 34 |
respiratory rate | 33 |
two main | 33 |
intervention group | 33 |
care unit | 33 |
special issue | 33 |
substance use | 33 |
many different | 33 |
metabolic engineering | 33 |
regression model | 33 |
control study | 33 |
based systems | 33 |
business models | 33 |
mass index | 33 |
quality control | 33 |
research purposes | 33 |
higher risk | 33 |
case counts | 33 |
large amount | 33 |
data repository | 32 |
odds ratio | 32 |
ambient intelligence | 32 |
additional file | 32 |
proposed approach | 32 |
sustainable development | 32 |
differential privacy | 32 |
support vector | 32 |
systematic reviews | 32 |
digital content | 32 |
quality assurance | 32 |
mobility patterns | 32 |
systematic literature | 32 |
also used | 32 |
mobile health | 32 |
cervical cancer | 32 |
prospective observational | 32 |
ray images | 32 |
creative commons | 32 |
ed physicians | 32 |
moving average | 32 |
aggregate data | 31 |
table shows | 31 |
large data | 31 |
survey data | 31 |
using different | 31 |
hospital mortality | 31 |
financial services | 31 |
domain interactions | 31 |
contact network | 31 |
target data | 31 |
body mass | 31 |
additional data | 31 |
food supply | 31 |
data controller | 31 |
allows users | 31 |
will continue | 31 |
medical services | 31 |
also provides | 31 |
authors declare | 31 |
side effects | 31 |
substance abuse | 31 |
seasonal influenza | 31 |
disease epidemiology | 31 |
exit strategies | 31 |
level i | 31 |
among women | 31 |
cardiovascular disease | 31 |
outcome measures | 31 |
health behavior | 31 |
may need | 31 |
specific data | 31 |
smart contract | 31 |
sensor devices | 31 |
spatial distribution | 31 |
growth rate | 31 |
emergency physicians | 31 |
health needs | 30 |
chain management | 30 |
food safety | 30 |
data model | 30 |
third party | 30 |
ct scan | 30 |
ai methods | 30 |
results indicate | 30 |
simulated data | 30 |
health interventions | 30 |
inner city | 30 |
network inference | 30 |
epidemiological parameters | 30 |
information security | 30 |
drug administration | 30 |
service delivery | 30 |
case studies | 30 |
level data | 30 |
johns hopkins | 30 |
randomly selected | 30 |
erasure coding | 30 |
response rate | 30 |
air pollution | 30 |
ethical issues | 30 |
wireless sensor | 30 |
intellectual property | 30 |
observational studies | 30 |
may help | 30 |
personal information | 30 |
using mobile | 30 |
year period | 30 |
using deep | 30 |
convenience sample | 30 |
mental illness | 30 |
amino acid | 30 |
among different | 30 |
media post | 30 |
socioeconomic status | 30 |
daily life | 30 |
additional information | 29 |
services research | 29 |
trauma center | 29 |
results suggest | 29 |
health service | 29 |
pilot study | 29 |
human genome | 29 |
decision makers | 29 |
data presence | 29 |
aged years | 29 |
ai ml | 29 |
treatment effect | 29 |
provide information | 29 |
community transmission | 29 |
network model | 29 |
social support | 29 |
month period | 29 |
law enforcement | 29 |
european union | 29 |
chemical descriptors | 29 |
case numbers | 29 |
protein sequences | 29 |
medical imaging | 29 |
type diabetes | 29 |
one hand | 29 |
disease prevention | 29 |
augmented reality | 29 |
influenza surveillance | 29 |
mobile phones | 29 |
recent advances | 29 |
may include | 29 |
nucleic acid | 29 |
drug users | 29 |
many cases | 28 |
wide variety | 28 |
molecular modeling | 28 |
medical devices | 28 |
health monitoring | 28 |
testing data | 28 |
useful information | 28 |
next section | 28 |
future studies | 28 |
another example | 28 |
data generation | 28 |
smart health | 28 |
may provide | 28 |
patient monitoring | 28 |
network analysis | 28 |
data subject | 28 |
older adults | 28 |
preventive measures | 28 |
ml models | 28 |
patients receiving | 28 |
healthcare providers | 28 |
significantly lower | 28 |
relationships among | 28 |
study design | 28 |
data security | 28 |
administrative data | 28 |
scientific data | 28 |
severe sepsis | 28 |
significantly different | 28 |
demographic information | 28 |
digital epidemiology | 28 |
analysis using | 28 |
legacy equipment | 28 |
mechanistic models | 28 |
within days | 28 |
march th | 28 |
random sample | 28 |
data annotation | 27 |
industrial revolution | 27 |
predictive maintenance | 27 |
model based | 27 |
imaging data | 27 |
i trauma | 27 |
federated cloud | 27 |
based research | 27 |
study population | 27 |
using ai | 27 |
correlation coefficient | 27 |
prospective study | 27 |
chronic diseases | 27 |
dna sequencing | 27 |
heavy hitters | 27 |
prediction models | 27 |
generative adversarial | 27 |
two weeks | 27 |
population size | 27 |
two types | 27 |
learning algorithm | 26 |
clinical information | 26 |
sensitivity analysis | 26 |
street youth | 26 |
learning approach | 26 |
large numbers | 26 |
healthcare professionals | 26 |
research data | 26 |
pharmaceutical interventions | 26 |
phylogenetic tree | 26 |
epidemic models | 26 |
crystal structure | 26 |
based model | 26 |
rare disease | 26 |
mc model | 26 |
predictive analytics | 26 |
data subjects | 26 |
care utilization | 26 |
twitter mentions | 26 |
based approaches | 26 |
time periods | 26 |
protection law | 26 |
clinical outcomes | 26 |
ct images | 26 |
herd immunity | 26 |
septic shock | 26 |
system based | 26 |
freely available | 26 |
prescriptive analytics | 26 |
population health | 26 |
information related | 26 |
pain management | 26 |
reality mining | 26 |
transmission trees | 26 |
artificial neural | 26 |
subject fields | 26 |
critical care | 26 |
south korea | 26 |
social learning | 26 |
north carolina | 26 |
will become | 26 |
broad range | 26 |
multiple data | 25 |
test results | 25 |
social services | 25 |
present study | 25 |
traffic flow | 25 |
infected patients | 25 |
management system | 25 |
data formats | 25 |
privacy preserving | 25 |
near future | 25 |
drug discovery | 25 |
multivariate analysis | 25 |
allows us | 25 |
coronary heart | 25 |
reproductive number | 25 |
health conditions | 25 |
data repositories | 25 |
section presents | 25 |
global pandemic | 25 |
universal health | 25 |
significant increase | 25 |
census data | 25 |
paradigm shift | 25 |
ffi ffi | 25 |
observed data | 25 |
high levels | 25 |
food products | 25 |
within hours | 25 |
various types | 25 |
social sciences | 25 |
competing interests | 25 |
also known | 25 |
one health | 25 |
sensitivity analyses | 25 |
false positive | 25 |
model selection | 25 |
monitoring data | 25 |
shivom platform | 25 |
data assimilation | 25 |
sequence information | 25 |
exponential growth | 25 |
epidemiological studies | 25 |
software packages | 25 |
longitudinal data | 25 |
event detection | 25 |
findings suggest | 25 |
based system | 25 |
focal firm | 25 |
selection bias | 25 |
policy making | 25 |
statistical data | 25 |
women aged | 25 |
world data | 25 |
public policy | 25 |
early stage | 25 |
reproduction numbers | 25 |
randomised controlled | 25 |
metapopulation models | 25 |
symptom onset | 25 |
visualization tools | 25 |
current pandemic | 25 |
study using | 25 |
academic ed | 25 |
synthetic data | 24 |
might also | 24 |
data items | 24 |
future directions | 24 |
hopkins university | 24 |
epidemiological surveillance | 24 |
income countries | 24 |
fatality rate | 24 |
molecular interaction | 24 |
gps data | 24 |
often used | 24 |
pediatric patients | 24 |
focus groups | 24 |
trauma patients | 24 |
higher levels | 24 |
satellite imagery | 24 |
alcohol consumption | 24 |
ehr systems | 24 |
syndrome coronavirus | 24 |
social justice | 24 |
first time | 24 |
took place | 24 |
markov chain | 24 |
social big | 24 |
predictive model | 24 |
antimicrobial resistance | 24 |
infected persons | 24 |
issues related | 24 |
overdose deaths | 24 |
research project | 24 |
data related | 24 |
data providers | 24 |
structured data | 24 |
protein structure | 24 |
relevant information | 24 |
molecular clock | 24 |
scientific research | 24 |
data determined | 24 |
existing data | 24 |
molecular biology | 24 |
community health | 24 |
may occur | 24 |
posted september | 24 |
pediatric emergency | 24 |
influenza epidemics | 24 |
random forest | 24 |
monitoring system | 24 |
collecting data | 24 |
training process | 24 |
information exchange | 24 |
emerging infectious | 24 |
geographic information | 24 |
supplementary material | 24 |
health effects | 24 |
black box | 23 |
determined using | 23 |
long time | 23 |
data driven | 23 |
may vary | 23 |
also help | 23 |
health survey | 23 |
may affect | 23 |
individual patient | 23 |
data governance | 23 |
sierra leone | 23 |
care services | 23 |
virtual reality | 23 |
digital technologies | 23 |
patient satisfaction | 23 |
interaction network | 23 |
hate speech | 23 |
research projects | 23 |
biological networks | 23 |
opioid overdose | 23 |
will likely | 23 |
virus transmission | 23 |
epidemiological research | 23 |
virus outbreak | 23 |
united kingdom | 23 |
computed tomography | 23 |
traffic data | 23 |
may result | 23 |
statistical models | 23 |
private data | 23 |
deep convolutional | 23 |
domain experts | 23 |
better results | 23 |
exclusion criteria | 23 |
ground truth | 23 |
social capital | 23 |
spectral clustering | 23 |
study conducted | 23 |
contact networks | 23 |
must also | 23 |
baseline data | 23 |
individual level | 23 |
chronic disease | 23 |
data use | 23 |
colorectal cancer | 22 |
data without | 22 |
cardiovascular risk | 22 |
test statistic | 22 |
low income | 22 |
care workers | 22 |
infected cases | 22 |
protein sequence | 22 |
transmission models | 22 |
using machine | 22 |
data point | 22 |
biomedical research | 22 |
medical image | 22 |
google flu | 22 |
san francisco | 22 |
private sector | 22 |
fourth amendment | 22 |
early warning | 22 |
hospital discharge | 22 |
computer vision | 22 |
operating system | 22 |
new approach | 22 |
laboratory tests | 22 |
one another | 22 |
cardiovascular diseases | 22 |
image analysis | 22 |
medical images | 22 |
health impact | 22 |
mg dl | 22 |
free text | 22 |
network data | 22 |
human health | 22 |
genome sequences | 22 |
will lead | 22 |
patient records | 22 |
natural history | 22 |
knowledge base | 22 |
three main | 22 |
contact information | 22 |
total population | 22 |
learning method | 22 |
respiratory infections | 22 |
public key | 22 |
cancer patients | 22 |
quality data | 22 |
situational awareness | 22 |
international conference | 22 |
take place | 22 |
actual data | 22 |
remote monitoring | 22 |
population data | 22 |
term memory | 22 |
information diffusion | 22 |
information management | 22 |
use data | 22 |
based services | 22 |
suspected cases | 22 |
impact assessment | 21 |
per hour | 21 |
oxygen saturation | 21 |
learning systems | 21 |
family members | 21 |
experimental results | 21 |
related information | 21 |
immune system | 21 |
likert scale | 21 |
estimated using | 21 |
information flow | 21 |
based analysis | 21 |
related research | 21 |
african american | 21 |
data need | 21 |
usual care | 21 |
proposed framework | 21 |
different methods | 21 |
retrospective cohort | 21 |
patient outcomes | 21 |
patient privacy | 21 |
national level | 21 |
common data | 21 |
aggregated data | 21 |
shape model | 21 |
will take | 21 |
many people | 21 |
data records | 21 |
led trials | 21 |
case reports | 21 |
built using | 21 |
given area | 21 |
three models | 21 |
different time | 21 |
smoking cessation | 21 |
models using | 21 |
i will | 21 |
clustering algorithm | 21 |
median time | 21 |
various sources | 21 |
hong kong | 21 |
false positives | 21 |
feature extraction | 21 |
working group | 21 |
ai system | 21 |
epidemic control | 21 |
recent studies | 21 |
become available | 21 |
ml kg | 21 |
modelling study | 21 |
secondary analysis | 21 |
patients diagnosed | 21 |
evaluated using | 21 |
lymphatic filariasis | 21 |
patients without | 21 |
read access | 21 |
clinical care | 21 |
also need | 21 |
patients admitted | 21 |
regression analyses | 21 |
high school | 21 |
population level | 21 |
retrospective study | 21 |
investigation system | 21 |
diagnosis data | 21 |
wait time | 21 |
derivative estimate | 21 |
model adequacy | 21 |
patients treated | 21 |
gene ontology | 21 |
dgsaugust dataset | 21 |
teaching hospital | 21 |
twitter users | 21 |
limited data | 21 |
potential risk | 21 |
transmission risk | 21 |
epidemiological models | 21 |
complete data | 21 |
smart devices | 21 |
help us | 21 |
biological material | 21 |
electronic communications | 21 |
bacillus anthracis | 21 |
near real | 21 |
cluster analysis | 20 |
authors also | 20 |
statistical analyses | 20 |
next generation | 20 |
smart home | 20 |
infected people | 20 |
sensor networks | 20 |
abdominal pain | 20 |
compared using | 20 |
native dutch | 20 |
hypothesis testing | 20 |
chest ct | 20 |
related confusion | 20 |
communicable diseases | 20 |
detailed information | 20 |
based access | 20 |
european commission | 20 |
health agencies | 20 |
years ago | 20 |
future outbreaks | 20 |
branch lengths | 20 |
rfid tag | 20 |
reference model | 20 |
five years | 20 |
different groups | 20 |
observational data | 20 |
image data | 20 |
data including | 20 |
different social | 20 |
food chain | 20 |
trend analysis | 20 |
second wave | 20 |
transmission events | 20 |
large datasets | 20 |
drug safety | 20 |
success rate | 20 |
results showed | 20 |
urgent need | 20 |
highly significant | 20 |
models may | 20 |
user experience | 20 |
clinically relevant | 20 |
open commons | 20 |
correlation coefficients | 20 |
age years | 20 |
mg kg | 20 |
information sharing | 20 |
collaborative research | 20 |
people living | 20 |
multimodal data | 20 |
time consuming | 20 |
epidemic dynamics | 20 |
presentation will | 20 |
data imputation | 20 |
used data | 20 |
incidence rates | 20 |
business model | 20 |
data regarding | 20 |
potential benefits | 20 |
data needed | 20 |
unsupervised learning | 20 |
clinical characteristics | 20 |
information regarding | 20 |
average number | 20 |
randomized trials | 20 |
provide feedback | 20 |
adult ed | 20 |
clinically significant | 20 |
differentially expressed | 20 |
anonymized data | 20 |
like illness | 20 |
low risk | 20 |
social networking | 20 |
protection directive | 20 |
data integrity | 20 |
medical resources | 20 |
two decades | 20 |
research questions | 20 |
natural disasters | 20 |
privacy issues | 20 |
scale data | 20 |
data extraction | 20 |
health coverage | 20 |
ai applications | 20 |
data elements | 20 |
analysis tools | 20 |
urban poor | 20 |
task force | 20 |
emergency medical | 20 |
contact interactions | 20 |
inference methods | 20 |
model using | 19 |
data flow | 19 |
complex data | 19 |
spreadsheet program | 19 |
input variables | 19 |
also use | 19 |
making process | 19 |
educational level | 19 |
mixed reality | 19 |
data might | 19 |
distancing measures | 19 |
across countries | 19 |
rural areas | 19 |
using blockchain | 19 |
principal component | 19 |
smart node | 19 |
census tracts | 19 |
data store | 19 |
training set | 19 |
many years | 19 |
make sense | 19 |
different stages | 19 |
uncertainty quantification | 19 |
parameter estimates | 19 |
virtual robot | 19 |
media platform | 19 |
south africa | 19 |
pi models | 19 |
trial data | 19 |
six months | 19 |
predictive performance | 19 |
research interests | 19 |
mass spectrometry | 19 |
cohort studies | 19 |
data curation | 19 |
detection using | 19 |
every day | 19 |
health informatics | 19 |
urban academic | 19 |
blood samples | 19 |
information available | 19 |
group contact | 19 |
intervention strategies | 19 |
airway management | 19 |
response efforts | 19 |
provide data | 19 |
time interval | 19 |
simulation models | 19 |
will discuss | 19 |
source code | 19 |
care delivery | 19 |
various data | 19 |
mobile data | 19 |
social contact | 19 |
based algorithms | 19 |
data capture | 19 |
food security | 19 |
diagnostic tests | 19 |
compartmental models | 19 |
large urban | 19 |
energy consumption | 19 |
relatively small | 19 |
therapeutic hypothermia | 19 |
data gathered | 19 |
central server | 19 |
children aged | 19 |
emergency care | 19 |
health emergencies | 19 |
attack rate | 19 |
best practice | 19 |
nucleic acids | 19 |
coronary artery | 19 |
citizen science | 19 |
expert knowledge | 19 |
infected person | 19 |
also provided | 19 |
data bank | 19 |
data structure | 19 |
scientific knowledge | 19 |
human disease | 19 |
increasing number | 19 |
take advantage | 19 |
sensitive information | 19 |
national center | 19 |
drug overdose | 19 |
patients may | 19 |
one week | 19 |
assessed using | 19 |
based medicine | 19 |
april th | 19 |
mathematical modeling | 19 |
derivative estimates | 19 |
infection rates | 19 |
daily new | 19 |
ml systems | 19 |
bottle type | 19 |
research areas | 19 |
one study | 19 |
sampling rate | 19 |
daily counts | 19 |
different ways | 19 |
see also | 19 |
clinical studies | 18 |
psychological distress | 18 |
positive predictive | 18 |
child health | 18 |
functional annotation | 18 |
respiratory data | 18 |
phylogenetic analysis | 18 |
detection performance | 18 |
higher rates | 18 |
behavior change | 18 |
analysis methods | 18 |
file system | 18 |
global model | 18 |
noisy data | 18 |
new opportunities | 18 |
dynamic contact | 18 |
study showed | 18 |
privacy policies | 18 |
active cases | 18 |
harm reduction | 18 |
significantly reduced | 18 |
artery disease | 18 |
prediction model | 18 |
may require | 18 |
systolic blood | 18 |
outbreak response | 18 |
ed utilization | 18 |
temporal resolution | 18 |
regulatory requirements | 18 |
death rate | 18 |
using artificial | 18 |
cases reported | 18 |
core competencies | 18 |
family history | 18 |
results obtained | 18 |
significant impact | 18 |
lessons learned | 18 |
molecular epidemiology | 18 |
breathing data | 18 |
disease burden | 18 |
mortality risk | 18 |
health centres | 18 |
data show | 18 |
data fusion | 18 |
medical device | 18 |
will increase | 18 |
genomics data | 18 |
vector machine | 18 |
first two | 18 |
research findings | 18 |
analysis techniques | 18 |
least squares | 18 |
consecutive patients | 18 |
predictive data | 18 |
great deal | 18 |
current state | 18 |
short term | 18 |
emergency situations | 18 |
limited number | 18 |
data provider | 18 |
medical staff | 18 |
biological data | 18 |
nuclear power | 18 |
health problem | 18 |
bacterial pneumonia | 18 |
global fscs | 18 |
population based | 18 |
united nations | 18 |
major public | 18 |
opioid use | 18 |
disease parameters | 18 |
learning system | 18 |
fault tolerance | 18 |
relaxed clock | 18 |
true number | 18 |
local health | 18 |
middle east | 18 |
system will | 18 |
image segmentation | 18 |
digital phenotyping | 18 |
data stored | 18 |
mobile device | 18 |
another important | 18 |
cancer registry | 18 |
hospital cardiac | 18 |
search engine | 18 |
data gathering | 18 |
two years | 18 |
lf models | 18 |
emergency management | 18 |
venture capital | 18 |
mathematical model | 18 |
protein data | 18 |
obtained using | 18 |
heart rhythm | 18 |
one example | 18 |
make use | 18 |
sexually transmitted | 18 |
information provided | 18 |
resource allocation | 18 |
mortality rate | 18 |
program directors | 18 |
social problems | 18 |
posted june | 18 |
social interactions | 18 |
learning analytics | 18 |
driven approaches | 18 |
irregular time | 18 |
multivariate logistic | 18 |
th century | 17 |
developed countries | 17 |
basic reproduction | 17 |
routine clinical | 17 |
published data | 17 |
knowledge discovery | 17 |
current research | 17 |
well known | 17 |
mining techniques | 17 |
may cause | 17 |
daily cases | 17 |
quality improvement | 17 |
will use | 17 |
public data | 17 |
young people | 17 |
patients aged | 17 |
text data | 17 |
ems system | 17 |
admitted patients | 17 |
readily available | 17 |
dental caries | 17 |
sequencing data | 17 |
data resources | 17 |
disease management | 17 |
noted earlier | 17 |
including data | 17 |
four different | 17 |
physical distancing | 17 |
many areas | 17 |
textual data | 17 |
independently associated | 17 |
young adults | 17 |
potential impact | 17 |
adversarial networks | 17 |
github repository | 17 |
health indicators | 17 |
disease research | 17 |
vascular disease | 17 |
using multiple | 17 |
urban settings | 17 |
global burden | 17 |
academic medical | 17 |
jurisdictional claims | 17 |
target dataset | 17 |
related ices | 17 |
model development | 17 |
per week | 17 |
individual contact | 17 |
adverse outcomes | 17 |
community members | 17 |
baseline shifts | 17 |
branch length | 17 |
global scale | 17 |
also include | 17 |
online social | 17 |
birth cohort | 17 |
tests performed | 17 |
ehr data | 17 |
storage system | 17 |
different approaches | 17 |
crisis communication | 17 |
analytical tools | 17 |
ed users | 17 |
legal framework | 17 |
will enable | 17 |
cox proportional | 17 |
current status | 17 |
irregularly sampled | 17 |
data distribution | 17 |
new challenges | 17 |
critically ill | 17 |
risks associated | 17 |
high accuracy | 17 |
different aspects | 17 |
making decisions | 17 |
cancer screening | 17 |
population dynamics | 17 |
based techniques | 17 |
drug abuse | 17 |
health decision | 17 |
data suggest | 17 |
large volumes | 17 |
disaster management | 17 |
include data | 17 |
incidence data | 17 |
given time | 17 |
remains neutral | 17 |
economic development | 17 |
potential confounders | 17 |
springer nature | 17 |
disease risk | 17 |
safety outcomes | 17 |
study treatment | 17 |
decision tree | 17 |
body temperature | 17 |
institutional affiliations | 17 |
prevalence data | 17 |
dna sequence | 17 |
protein complexes | 17 |
medicine residents | 17 |
heterogeneous sources | 17 |
conducted using | 17 |
health organizations | 17 |
output data | 17 |
ten years | 17 |
urban communities | 17 |
challenges related | 17 |
mobile network | 17 |
published maps | 17 |
opioid prescribing | 17 |
european data | 17 |
general data | 17 |
case definitions | 17 |
nature remains | 17 |
pandemic preparedness | 17 |
different regions | 17 |
commons license | 17 |
operating systems | 17 |
prior knowledge | 17 |
medical field | 17 |
general health | 17 |
good results | 17 |
secure data | 17 |
sensed data | 17 |
management systems | 17 |
service provider | 16 |
death certificate | 16 |
biological systems | 16 |
valuable information | 16 |
supplementary information | 16 |
food industry | 16 |
methods will | 16 |
computer program | 16 |
significant association | 16 |
collected using | 16 |
critical actions | 16 |
metabolic pathways | 16 |
phylogenetic inference | 16 |
series relations | 16 |
building blocks | 16 |
higher level | 16 |
level risk | 16 |
will result | 16 |
comparative analysis | 16 |
timely manner | 16 |
per month | 16 |
alcohol use | 16 |
interactive web | 16 |
edge computing | 16 |
genome sequence | 16 |
influenza vaccine | 16 |
sudden cardiac | 16 |
scientific literature | 16 |
false discovery | 16 |
different areas | 16 |
based surveillance | 16 |
ai will | 16 |
average age | 16 |
mean score | 16 |
significantly increased | 16 |
contact tracking | 16 |
significant linear | 16 |
posterior distribution | 16 |
last years | 16 |
different parts | 16 |
organ failure | 16 |
based covid | 16 |
secondary outcomes | 16 |
mean square | 16 |
adverse effects | 16 |
web browser | 16 |
data transfer | 16 |
learning technology | 16 |
attending physicians | 16 |
identify potential | 16 |
visit data | 16 |
care data | 16 |
case fatality | 16 |
uncorrelated lognormal | 16 |
epidemiological model | 16 |
become increasingly | 16 |
hiv infection | 16 |
systems based | 16 |
major challenge | 16 |
retrospective chart | 16 |
google trends | 16 |
laboratory data | 16 |
risk groups | 16 |
clustering algorithms | 16 |
research groups | 16 |
multiple locations | 16 |
diabetes mellitus | 16 |
focus group | 16 |
type i | 16 |
disease severity | 16 |
respiratory symptoms | 16 |
last decade | 16 |
several studies | 16 |
warning system | 16 |
tracking project | 16 |
feature engineering | 16 |
comparative study | 16 |
aed use | 16 |
web application | 16 |
useful tool | 16 |
models used | 16 |
image recognition | 16 |
regulatory agencies | 16 |
mental status | 16 |
mental disorders | 16 |
data owner | 16 |
reliable data | 16 |
em residency | 16 |
data users | 16 |
different locations | 16 |
high performance | 16 |
among children | 16 |
high degree | 16 |
community hospital | 16 |
low cost | 16 |
binding sites | 16 |
will focus | 16 |
physical health | 16 |
location information | 16 |
health crisis | 16 |
also found | 16 |
healthcare industry | 16 |
sequence analysis | 16 |
also available | 16 |
geographical location | 16 |
research studies | 16 |
provide useful | 16 |
important issue | 16 |
environmental factors | 16 |
critical events | 16 |
multivariable logistic | 16 |
diagnostic accuracy | 16 |
cancer mortality | 16 |
working party | 16 |
fold change | 16 |
relative humidity | 16 |
quality issues | 16 |
main goal | 16 |
two data | 16 |
information collected | 16 |
viral pneumonia | 16 |
research will | 16 |
two major | 16 |
incubation model | 16 |
learning rate | 16 |
full potential | 16 |
sensor device | 16 |
arrest patients | 16 |
hazard ratio | 16 |
semantic interoperability | 16 |
pattern recognition | 16 |
high blood | 16 |
clustering approach | 16 |
critical role | 16 |
make decisions | 16 |
google scholar | 16 |
long short | 16 |
personal privacy | 16 |
will always | 16 |
trial design | 16 |
different domains | 16 |
admission rate | 16 |
acute myocardial | 16 |
study found | 16 |
anomaly detection | 16 |
patient demographics | 16 |
preliminary results | 16 |
research directions | 16 |
term forecasts | 16 |
past year | 16 |
data controllers | 16 |
sample sizes | 16 |
health policies | 16 |
human beings | 15 |
erasure codes | 15 |
i believe | 15 |
emerging pathogens | 15 |
web pages | 15 |
means clustering | 15 |
laboratory testing | 15 |
error correlation | 15 |
prior studies | 15 |
temporal changes | 15 |
risk estimates | 15 |
probability density | 15 |
temporal distribution | 15 |
epidemiological network | 15 |
resource utilization | 15 |
annotation schema | 15 |
symptom data | 15 |
different models | 15 |
virus spread | 15 |
facial recognition | 15 |
model used | 15 |
transmission patterns | 15 |
purpose limitation | 15 |
distributed storage | 15 |
track covid | 15 |
member state | 15 |
within one | 15 |
standard deviations | 15 |
national institute | 15 |
first level | 15 |
polymerase chain | 15 |
pathogen surveillance | 15 |
chain reaction | 15 |
study also | 15 |
across time | 15 |
model training | 15 |
ml methods | 15 |
learning approaches | 15 |
first one | 15 |
unstructured data | 15 |
acute coronary | 15 |
health risks | 15 |
latent dirichlet | 15 |
prescription drug | 15 |
dimensional data | 15 |
multiple imputation | 15 |
posterior probability | 15 |
food quality | 15 |
data coverage | 15 |
trained research | 15 |
personal devices | 15 |
storage space | 15 |
ai research | 15 |
unique identifier | 15 |
training dataset | 15 |
homeless people | 15 |
time step | 15 |
health response | 15 |
specific disease | 15 |
immunodeficiency virus | 15 |
computational resources | 15 |
operational data | 15 |
news article | 15 |
provide valuable | 15 |
lognormal relaxed | 15 |
computational methods | 15 |
positively associated | 15 |
physiological data | 15 |
care facilities | 15 |
new infections | 15 |
rapid development | 15 |
agent based | 15 |
randomized trial | 15 |
management information | 15 |
wait times | 15 |
media posts | 15 |
controlled vocabulary | 15 |
three categories | 15 |
respiratory pathogen | 15 |
vice versa | 15 |
minimum energy | 15 |
encoded data | 15 |
predictive modeling | 15 |
classic cfr | 15 |
informatics platform | 15 |
platforms like | 15 |
general practice | 15 |
patient visits | 15 |
time required | 15 |
health workers | 15 |
frequent ed | 15 |
dirichlet allocation | 15 |
preventive treatment | 15 |
relatively low | 15 |
care provider | 15 |
data warehouse | 15 |
east respiratory | 15 |
based devices | 15 |
also important | 15 |
coronavirus outbreak | 15 |
use disorder | 15 |
information society | 15 |
diastolic blood | 15 |
dgsapril dataset | 15 |
relational database | 15 |
genomic epidemiology | 15 |
chief complaints | 15 |
significant effect | 15 |
care units | 15 |
rapidly evolving | 15 |
urban area | 15 |
em residents | 15 |
main outcome | 15 |
health tools | 15 |
general practitioners | 15 |
distributed ledger | 15 |
another approach | 15 |
current situation | 15 |
power plants | 15 |
data interoperability | 15 |
access data | 15 |
frequent users | 15 |
collected information | 15 |
biological processes | 15 |
molecular data | 15 |
currently available | 15 |
key role | 15 |
magnetic resonance | 15 |
discovery rate | 15 |
component analysis | 15 |
high resolution | 15 |
health education | 15 |
bayesian networks | 15 |
educational data | 15 |
symptomatic cases | 15 |
total visits | 15 |
temporal dynamics | 15 |
important information | 15 |
research center | 15 |
copy number | 15 |
least two | 15 |
healthcare services | 15 |
infectious agents | 15 |
history data | 15 |
recent study | 15 |
lifestyle factors | 15 |
hiv testing | 15 |
many patients | 15 |
system using | 15 |
baseline characteristics | 15 |
surveillance programs | 15 |
storage overhead | 15 |
analysis results | 15 |
daily number | 15 |
data based | 15 |
load balancing | 15 |
health measures | 15 |
high prevalence | 15 |
incidence rate | 15 |
tools like | 15 |
question answering | 15 |
urban centers | 15 |
ed los | 15 |
different interventions | 15 |
software tools | 15 |
healthcare management | 15 |
significant improvement | 15 |
diverse data | 15 |
web services | 15 |
prehospital setting | 15 |
will occur | 15 |
dependent variable | 15 |
personal health | 15 |
identified using | 15 |
domain knowledge | 15 |
table provides | 15 |
health department | 15 |
previously validated | 15 |
among individuals | 14 |
sensing data | 14 |
pandemic related | 14 |
genome annotation | 14 |
related issues | 14 |
recent work | 14 |
van der | 14 |
also require | 14 |
added value | 14 |
data hunger | 14 |
training program | 14 |
study will | 14 |
acid sequence | 14 |
success rates | 14 |
translational research | 14 |
randomized clinical | 14 |
models will | 14 |
hospital stay | 14 |
section describes | 14 |
virtual identity | 14 |
will remain | 14 |
services organisations | 14 |
smart connected | 14 |
model assumptions | 14 |
table presents | 14 |
cost per | 14 |
effect size | 14 |
proposed architecture | 14 |
higher among | 14 |
laboratory results | 14 |
cell phone | 14 |
capacity building | 14 |
weather data | 14 |
scholarly articles | 14 |
risk management | 14 |
voice recognition | 14 |
health practice | 14 |
microarray data | 14 |
public databases | 14 |
data aggregation | 14 |
industrial marketing | 14 |
significant changes | 14 |
will include | 14 |
truth data | 14 |
clinical outcome | 14 |
low levels | 14 |
fog computing | 14 |
official data | 14 |
based algorithm | 14 |
ambulatory monitoring | 14 |
conceptual framework | 14 |
chronic conditions | 14 |
congestive heart | 14 |
using social | 14 |
life expectancy | 14 |
user data | 14 |
radiation exposure | 14 |
human immunodeficiency | 14 |
information retrieval | 14 |
using twitter | 14 |
health security | 14 |
educational intervention | 14 |
methods used | 14 |
health sector | 14 |
increased mortality | 14 |
starting point | 14 |
epidemic spread | 14 |
cancer cases | 14 |
biological samples | 14 |
influenza season | 14 |
paramount importance | 14 |
saharan africa | 14 |
deep reinforcement | 14 |
diagnostic yield | 14 |
assess whether | 14 |
life cycle | 14 |
environmental conditions | 14 |
transmission network | 14 |
supervised machine | 14 |
ml model | 14 |
statistical monitoring | 14 |
food fraud | 14 |
first stage | 14 |
bayesian phylogenetic | 14 |
data analyses | 14 |
patient safety | 14 |
negative predictive | 14 |
clinical course | 14 |
patient characteristics | 14 |
allow us | 14 |
sir model | 14 |
total distance | 14 |
ml algorithms | 14 |
scoping review | 14 |
context data | 14 |
one must | 14 |
criminal activity | 14 |
potential solution | 14 |
included patients | 14 |
data systems | 14 |
series relation | 14 |
pain scores | 14 |
computational power | 14 |
european parliament | 14 |
hash value | 14 |
gt data | 14 |
will generate | 14 |
local level | 14 |
will improve | 14 |
driven services | 14 |
function will | 14 |
identity management | 14 |
providing information | 14 |
admission rates | 14 |
various countries | 14 |
infected samples | 14 |
massive data | 14 |
national institutes | 14 |
daily living | 14 |
informed decisions | 14 |
improve health | 14 |
data models | 14 |
detailed analysis | 14 |
mean difference | 14 |
dimensional structure | 14 |
higher education | 14 |
molecular interactions | 14 |
drug development | 14 |
image processing | 14 |
clustering methods | 14 |
rater reliability | 14 |
time information | 14 |
network based | 14 |
technological advances | 14 |
crowdsourced data | 14 |
adjusted odds | 14 |
decision rule | 14 |
health issues | 14 |
two categories | 14 |
trusted third | 14 |
previous research | 14 |
one month | 14 |
three types | 14 |
highly sensitive | 14 |
see section | 14 |
subject field | 14 |
huge amount | 14 |
classification system | 14 |
ismts data | 14 |
treatment effects | 14 |
posted november | 14 |
hospital system | 14 |
wearable sensors | 14 |
human populations | 14 |
emerging diseases | 14 |
eligible patients | 14 |
psychiatric disorders | 14 |
marketing management | 14 |
intermittent preventive | 14 |
care professionals | 14 |
patient age | 14 |
rate variability | 14 |
data cleaning | 14 |
fundamental rights | 14 |
drug resistance | 14 |
animal health | 14 |
influenza propagation | 14 |
done using | 14 |
significantly improved | 14 |
future pandemics | 14 |
active surveillance | 14 |
inflammatory response | 14 |
copd patients | 14 |
relatively simple | 14 |
article gdpr | 14 |
ml techniques | 14 |
ethics committee | 14 |
mixing patterns | 14 |
positive cases | 14 |
metropolitan areas | 14 |
daily basis | 14 |
virtual identities | 14 |
avian influenza | 14 |
stored data | 14 |
probability distribution | 14 |
interacting proteins | 14 |
previous section | 14 |
section discusses | 14 |
three major | 14 |
cardiovascular events | 14 |
end users | 13 |
ml min | 13 |
corona virus | 13 |
significant reduction | 13 |
test data | 13 |
approach using | 13 |
large proportion | 13 |
paper presents | 13 |
web server | 13 |
data extracted | 13 |
absolute humidity | 13 |
learning framework | 13 |
homomorphic encryption | 13 |
implemented using | 13 |
single shot | 13 |
discharged patients | 13 |
risk patients | 13 |
first wave | 13 |
analytics tools | 13 |
network architectures | 13 |
family health | 13 |
proportional hazards | 13 |
easily accessible | 13 |
school closure | 13 |
wos publications | 13 |
also discuss | 13 |
study aims | 13 |
numerical differentiation | 13 |
scientific publications | 13 |
human contact | 13 |
method based | 13 |
storage systems | 13 |
household income | 13 |
relative survival | 13 |
acgme core | 13 |
covid tracking | 13 |
tracking system | 13 |
consensus mechanism | 13 |
type ii | 13 |
publication bias | 13 |
low energy | 13 |
omic data | 13 |
towards covid | 13 |
outcome measure | 13 |
partition coefficient | 13 |
global positioning | 13 |
department data | 13 |
local community | 13 |
published research | 13 |
research question | 13 |
quality assessment | 13 |
prospectively collected | 13 |
also includes | 13 |
childhood cancer | 13 |
several countries | 13 |
dimensionality reduction | 13 |
inpatient mortality | 13 |
geographical locations | 13 |
among people | 13 |
research works | 13 |
using bayesian | 13 |
data custodians | 13 |
text files | 13 |
help identify | 13 |
data architecture | 13 |
analysis perspectives | 13 |
screening programme | 13 |
current data | 13 |
blockchain network | 13 |
anonymous credentials | 13 |
public events | 13 |
hospital staff | 13 |
schema evolution | 13 |
epidemic forecasting | 13 |
rates among | 13 |
bearing fault | 13 |
amino acids | 13 |
health emergency | 13 |
program evaluation | 13 |
case definition | 13 |
well established | 13 |
st century | 13 |
york times | 13 |
multinomial test | 13 |
hours post | 13 |
prediction task | 13 |
consumer devices | 13 |
cloud storage | 13 |
june th | 13 |
made possible | 13 |
pathogen sequencing | 13 |
injection drug | 13 |
food insecurity | 13 |
sensor network | 13 |
engineered features | 13 |
human population | 13 |
research database | 13 |
store data | 13 |
crisis management | 13 |
species composition | 13 |
developed using | 13 |
total variation | 13 |
measurement feedback | 13 |
semantic web | 13 |
among men | 13 |
well defined | 13 |
resource center | 13 |
satellite images | 13 |
effective way | 13 |
labelled data | 13 |
retrospective analysis | 13 |
data anonymization | 13 |
underlying data | 13 |
human subjects | 13 |
square tests | 13 |
will still | 13 |
pulmonary embolism | 13 |
privacy risks | 13 |
much better | 13 |
primary objective | 13 |
mendeley readers | 13 |
mortality prediction | 13 |
control groups | 13 |
response system | 13 |
drug design | 13 |
movement patterns | 13 |
asian msm | 13 |
urban ed | 13 |
physical genome | 13 |
cognitive function | 13 |
new approaches | 13 |
evolutionary history | 13 |
data format | 13 |
malware detection | 13 |
financial transactions | 13 |
residency programs | 13 |
reactive protein | 13 |
traditional approach | 13 |
particular interest | 13 |
independent variable | 13 |
west nile | 13 |
disease detection | 13 |
genomic sequence | 13 |
head ct | 13 |
recognition systems | 13 |
well suited | 13 |
cross validation | 13 |
care systems | 13 |
value chain | 13 |
sequencing technologies | 13 |
diagonally interleaved | 13 |
much higher | 13 |
information will | 13 |
daily changes | 13 |
poisson regression | 13 |
per patient | 13 |
recent research | 13 |
without compromising | 13 |
mobile app | 13 |
key challenges | 13 |
trial results | 13 |
proposed model | 13 |
effect sizes | 13 |
related work | 13 |
model also | 13 |
clinical management | 13 |
brain injury | 13 |
altmetric events | 13 |
multivariate time | 13 |
data alone | 13 |
based survey | 13 |
susceptible individuals | 13 |
data support | 13 |
collaborative learning | 13 |
volume eds | 13 |
traditional methods | 13 |
patients seen | 13 |
various kinds | 13 |
new era | 13 |
test instance | 13 |
head trauma | 13 |
patient monitor | 13 |
analysis will | 13 |
optimal number | 13 |
ethnic minority | 13 |
computational models | 13 |
sexual contact | 13 |
examine whether | 13 |
service provision | 13 |
optimization problem | 13 |
blood glucose | 13 |
blockchain platform | 13 |
pandemic response | 13 |
theoretical models | 13 |
two independent | 13 |
rfid tags | 13 |
complex systems | 13 |
regarding data | 13 |
graphical user | 13 |
standard errors | 13 |
information contained | 13 |
ed length | 13 |
data research | 13 |
maximum number | 13 |
strict clock | 13 |
note springer | 13 |
influenza vaccination | 13 |
traffic prediction | 13 |
antibiotic resistance | 13 |
computational biology | 13 |
study shows | 13 |
ct data | 13 |
csv files | 13 |
insurance companies | 13 |
colon cancer | 13 |
paper will | 13 |
metabolic pathway | 13 |
cox regression | 13 |
also consider | 13 |
worth noting | 13 |
different scenarios | 13 |
personalized medicine | 13 |
pain medication | 13 |
quality management | 13 |
property rights | 13 |
feature selection | 13 |
global public | 13 |
sequence similarity | 13 |
evaluate whether | 13 |
may increase | 13 |
mathematical modelling | 13 |
death rates | 13 |
may contribute | 13 |
using ml | 13 |
diagnostic testing | 13 |
people will | 13 |
existing methods | 13 |
care needs | 13 |
binding site | 13 |
semantic annotation | 13 |
distributed software | 13 |
attending physician | 13 |
second step | 13 |
model calibration | 13 |
first transformation | 13 |
differentially private | 12 |
medical history | 12 |
vast majority | 12 |
clinical settings | 12 |
individual health | 12 |
effect estimates | 12 |
weather conditions | 12 |
point likert | 12 |
close proximity | 12 |
mobility restrictions | 12 |
regional differences | 12 |
african countries | 12 |
mobile apps | 12 |
several factors | 12 |
cluster size | 12 |
higher number | 12 |
clinically useful | 12 |
body weight | 12 |
perform better | 12 |
high cost | 12 |
elderly people | 12 |
mda mf | 12 |
major depressive | 12 |
takes place | 12 |
patient information | 12 |
fold cross | 12 |
different formats | 12 |
recovered cases | 12 |
malarial drugs | 12 |
models based | 12 |
protection regulation | 12 |
accountability act | 12 |
urban environments | 12 |
software development | 12 |
golay filter | 12 |
pulmonary cases | 12 |
ssd mobilenet | 12 |
essential services | 12 |
information extraction | 12 |
disease incidence | 12 |
health departments | 12 |
among persons | 12 |
new virus | 12 |
taking place | 12 |
rfid technology | 12 |
originally submitted | 12 |
specific location | 12 |
dialysis patients | 12 |
treatment strategies | 12 |
care settings | 12 |
better outcomes | 12 |
per location | 12 |
longitudinal study | 12 |
epidemics using | 12 |
might need | 12 |
policy document | 12 |
based applications | 12 |
skin cancer | 12 |
trauma centers | 12 |
genv will | 12 |
presence absence | 12 |
one patient | 12 |
research agenda | 12 |
air travel | 12 |
treatment response | 12 |
exact test | 12 |
facebook mentions | 12 |
three years | 12 |
intended use | 12 |
incomplete data | 12 |
passive smoking | 12 |
patients received | 12 |
existing models | 12 |
sentence classification | 12 |
coronary syndrome | 12 |
global traceability | 12 |
health events | 12 |
content analysis | 12 |
initial data | 12 |
sufficient data | 12 |
social security | 12 |
particularly relevant | 12 |
epidemiologic studies | 12 |
generation victoria | 12 |
gene network | 12 |
similar data | 12 |
psi mi | 12 |
healthcare demand | 12 |
dna synthesis | 12 |
influenza viruses | 12 |
strict liability | 12 |
infant mortality | 12 |
based case | 12 |
problem solving | 12 |
interests include | 12 |
adversarial attacks | 12 |
risk stratification | 12 |
emergency response | 12 |
literature search | 12 |
large population | 12 |
vital sign | 12 |
research efforts | 12 |
early diagnosis | 12 |
pneumonia cases | 12 |
government agencies | 12 |
multivariate analyses | 12 |
social change | 12 |
much larger | 12 |
leading cause | 12 |
processed data | 12 |
study aimed | 12 |
genetic algorithm | 12 |
interquartile range | 12 |
speech recognition | 12 |
use different | 12 |
infection control | 12 |
fourth industrial | 12 |
chronic pain | 12 |
project will | 12 |
greater risk | 12 |
point scale | 12 |
digital technology | 12 |
growth rates | 12 |
data size | 12 |
received emails | 12 |
school closures | 12 |
coronavirus data | 12 |
systems science | 12 |
many challenges | 12 |
point cloud | 12 |
patients undergoing | 12 |
ischemic stroke | 12 |
bottle types | 12 |
currently used | 12 |
gs global | 12 |
encrypted data | 12 |
optic nerve | 12 |
personal relationships | 12 |
measured using | 12 |
time window | 12 |
randomly assigned | 12 |
rfid readers | 12 |
go beyond | 12 |
dna sequences | 12 |
mobility behaviors | 12 |
research methods | 12 |
killer whales | 12 |
emergency physician | 12 |
transmission networks | 12 |
cases per | 12 |
disease data | 12 |
criminal justice | 12 |
process data | 12 |
based care | 12 |
pareto front | 12 |
ad hoc | 12 |
csv file | 12 |
make predictions | 12 |
rate variation | 12 |
common among | 12 |
overall quality | 12 |
treatment options | 12 |
high rates | 12 |
standardized data | 12 |
competitive advantage | 12 |
clinical environment | 12 |
based learning | 12 |
retrospective review | 12 |
structural features | 12 |
across many | 12 |
search queries | 12 |
made public | 12 |
recently developed | 12 |
based practices | 12 |
visualization software | 12 |
likelihood ratio | 12 |
test set | 12 |
insurance portability | 12 |
just one | 12 |
current covid | 12 |
past months | 12 |
epidemic transmission | 12 |
control studies | 12 |
traumatic brain | 12 |
communication protocols | 12 |
one might | 12 |
related factors | 12 |
negative consequences | 12 |
identify patients | 12 |
spanish influenza | 12 |
original study | 12 |
error rates | 12 |
xml format | 12 |
statistical comparisons | 12 |
human protein | 12 |
may improve | 12 |
topic level | 12 |
healthcare information | 12 |
social life | 12 |
stereo matching | 12 |
probability distributions | 12 |
streaming data | 12 |
expert consensus | 12 |
closely related | 12 |
wavelet transform | 12 |
chain monte | 12 |
global infectious | 12 |
many studies | 12 |
reproductive health | 12 |
central role | 12 |
covid pandemic | 12 |
pediatric ed | 12 |
molecular evolution | 12 |
based dashboard | 12 |
data fields | 12 |
energy conformations | 12 |
statistical tests | 12 |
proposed solution | 12 |
alongside genv | 12 |
analyzed data | 12 |
prediction using | 12 |
hierarchical clustering | 12 |
representation learning | 12 |
ed volume | 12 |
road traffic | 12 |
pain patients | 12 |
one hundred | 12 |
multiple types | 12 |
general practitioner | 12 |
three groups | 12 |
primary prevention | 12 |
statistical approaches | 12 |
new insights | 12 |
different datasets | 12 |
parameter space | 12 |
computing power | 12 |
spatial data | 12 |
drug treatment | 12 |
rat model | 12 |
put forth | 12 |
safety assessment | 12 |
public policies | 12 |
prognostic factors | 12 |
network structure | 12 |
disease model | 12 |
main components | 12 |
programming language | 12 |
sampling rates | 12 |
main objective | 12 |
human services | 12 |
ethnic groups | 12 |
global data | 12 |
increasingly important | 12 |
data directly | 12 |
quantitative data | 12 |
metadata file | 12 |
create new | 12 |
depressive symptoms | 12 |
control strategies | 12 |
case report | 12 |
several types | 12 |
risk group | 12 |
risk indexes | 12 |
lf elimination | 12 |
health facilities | 12 |
first year | 12 |
sequence alignment | 12 |
democratic republic | 12 |
detection system | 12 |
battery level | 12 |
computing resources | 12 |
telephone follow | 12 |
institutional review | 12 |
count sketch | 12 |
social workers | 12 |
pandemic potential | 12 |
structure prediction | 12 |
differentiation methods | 12 |
new type | 12 |
policy development | 12 |