key: cord-0993958-sxvr133g authors: Jena, Kalyan Kumar; Bhoi, Sourav Kumar; Prasad, Mukesh; Puthal, Deepak title: A fuzzy rule-based efficient hospital bed management approach for coronavirus disease-19 infected patients date: 2021-01-27 journal: Neural Comput Appl DOI: 10.1007/s00521-021-05719-y sha: d09f9af9ac72b568d9e32fec8966f26274b6516f doc_id: 993958 cord_uid: sxvr133g Coronavirus disease-19 (COVID-19) is a very dangerous infectious disease for the entire world in the current scenario. Coronavirus spreads from one person to another person very rapidly. It spreads exponentially throughout the globe. Everyone should be cautious to avoid the spreading of this novel disease. In this paper, a fuzzy rule-based approach using priority-based method is proposed for the management of hospital beds for COVID-19 infected patients in the worst-case scenario where the number of hospital beds is very less as compared to the number of COVID-19 infected patients. This approach mainly attempts to minimize the number of hospital beds as well as emergency beds requirement for the treatment of COVID-19 infected patients to handle such a critical situation. In this work, higher priority has given to severe COVID-19 infected patients as compared to mild COVID-19 infected patients to handle this critical situation so that the survival probability of the COVID-19 infected patients can be increased. The proposed method is compared with first-come first-serve (FCFS)-based method to analyze the practical problems that arise during the assignment of hospital beds and emergency beds for the treatment of COVID-19 patients. The simulation of this work is carried out using MATLAB R2015b. COVID-19 58 ] is a novel infectious disease on the global scale which is very dangerous in nature. This virus has declared as a global pandemic by World Health Organization (WHO) [58] . Currently, there are around 498 lakhs COVID-19 positive cases, 12.5 lakh death cases, and 215 countries are affected by this novel COVID-19 [58] [59] [60] . As this virus spreads from one person to another person rapidly an exponential manner, so every individual of different countries should focus on the following precautions to break the spreading chain of this virus. • Social distancing • Staying at home if no emergency work • Use of masks at work as well as marketing places • Cleaning of hand properly at regular intervals • Avoid touching of face, eyes, mouth and nose • Avoid mass gatherings As the situation becomes very worst day by day, so it is very much essential to be ready with the hospital beds for the treatment of COVID-19 infected patients. However, in the practical scenario, the number of hospital beds available for the treatment of such patients is very less as compared to the number of infected cases due to the rapidly spreading of this disease. Hence, hospital bed management is a very challenging issue for the government of every country as well as states. In this work, a fuzzy rule-based approach using priority-based method is proposed to solve this serious issue by considering the worst-case scenario. The main contributions of this work are stated as follows. • A fuzzy rule-based approach using priority-based method is proposed to minimize the number of hospital beds and emergency beds requirement for the treatment of COVID-19 infected patients. • This approach mainly focuses on the priority-based method where severe COVID-19 infected patients have assigned higher priority as compared to mildly infected patients to increase the survival probability of the patients. • This approach is compared with the FCFS-based method to study the practical scenario of hospital beds as well as emergency beds assignments to the COVID-19 infected patients. • The simulation of proposed work is carried out using MATLAB R2015b. The rest of the paper is organized as follows. Section 2 describes related works, Sect. 3 describes the proposed methodology, Sect. 4 describes results and discussion, and Sect. 5 describes the conclusion of this work. Different works have carried out by different researchers related to COVID-19 . Some of the works are described as follows. Wong et al. [1] focused on the measurement of the response of operating room outbreak by considering a large tertiary hospital in Singapore. Meares et al. [2] emphasized on a system break mechanism as well as a queuing theory model that specifies regarding the requirement of intensive care beds during the COVID-19 pandemic. Tan et al. [3] focused on the preparation of the operating room for COVID-19 outbreak, and it mainly deals with the national heart center, Singapore. Huang et al. [4] emphasized on the infection control as well as management in an emergency situation against the spread of COVID-19 in a radiology department. Hick et al. [6] focused on the planning related to health care, crisis standards of care due to the spreading of novel coronavirus SARS-COV-2. Pu et al. [7] emphasized on the screening as well as management of confirmed or suspected COVID-19 patients by considering a tertiary hospital which is outside the Hubei province. Li et al. [11] focused on the demand for inpatient as well as ICU beds for the treatment of COVID-19 patients in the USA by analyzing the scenario of Chinese cities. Tanne et al. [15] emphasized on the mechanisms for the tackling of coronavirus on a global scale by the doctors as well as by the healthcare systems. Zunyou et al. [21] focused on the analysis of COVID-19 outbreaks in China to gain important lessons as well as characteristics from this situation by summarizing a report of 72,314 cases from the Chinese center for disease control and prevention. Roosa et al. [23] emphasized on the realtime forecasts in China from February 5, 2020, to February 24, 2020, related to COVID-19 epidemic. In this work, we have focused on the scenario where the number of hospital beds (B) is very less as compared to the number of COVID-19 infected patients (C), i.e., B \ \ C. So, it is a challenging task to assign the hospital beds to the COVID-19 infected patients efficiently in this scenario. The proposed work can provide a solution to handle this critical situation. This work mainly focuses on fuzzy rulebased approach [49] [50] [51] [52] [53] that uses priority-based method [54, 55] to manage and assign the hospital beds for the treatment of COVID-19 infected patients. The proposed approach is compared with the FCFS-based [56, 57] approach to analyze the practical scenario during the assignment of hospital beds. The fuzzy rule-based approach mainly focuses on the ''IF-THEN'' rule. When we consider ''if P is X then Q is Y,'' then ''P is X'' is known as the premise and ''Q is Y'' is known as consequent. So, as per this rule, the consequent value will be decided by considering the premise value. In our work, all the COVID-19 infected patients will be grouped into two categories such as mild and severe. As per the proposed approach, more priority is assigned to severe cases as compared to mild cases to increase the survival rate of the patients. So, by applying fuzzy rulebased approach using the priority-based method, if any patients with the severe category will arise, then they will be immediately assigned with the hospital beds for six weeks (42 days). After six weeks, severe patients will be either cured or dead, but they have to release the beds. If any patients with mild cases will arise, then they will be kept in home isolation with doctor's careful advice for two weeks (14 days) as the survival probability for these patients is high. After two weeks if the patients with the mild case will be cured, then they will be careful for further days with doctor's advice; otherwise, these patients will be severe and will be assigned with hospital beds for next six weeks if the hospital beds are available in that situation. After six weeks, patients with mild cases will be cured. In case of unavailability of hospital beds, emergency beds will be assigned to the severe patients. The hospital beds as well as emergency beds will be properly sanitized as per COVID-19 guidelines before assign to COVID-19 infected patients. The proposed fuzzy rule-based approach is represented in Table 1 . The proposed methodology is mentioned in Fig. 1 . The proposed algorithm is mentioned in Algorithm 1. Whereas by applying FCFS-based method, all the COVID-19 infected patients will be assigned with hospital beds and it does not matter whether the cases are mild or severe. In this situation, it is very difficult to handle all the cases in the worst-case scenario and it may increase the death rate as compared to the survival rate. So, if more number of patients with mild cases will be assigned with hospital beds at the initial situation, then there may not be any bed available for the patients with severe cases which lead to the higher death rate. The FCFS-based mechanism is mentioned in Algorithm 2. As per the report, around 80% of cases are mild, 20% of cases are severe, and 5% cases lead to death out of total COVID-19 infected cases in the current scenario. It will take around two weeks to cure the patients with mild cases and around 6 weeks to cure the patients with severe cases. In this work, we have considered that 80% of cases are mild, 20% of cases are severe, 90% cases will be cured cases, and 10% cases will be death cases. A patient with a severe case will be either cured or dead after six weeks, and the patient with a mild case will be either cured or severe after two weeks. In our work, for severe cases, the probability of survival for the cure is assigned with 0.8 that means P Survival (Severe-Cure) = 0.8 and the probability of survival for death is assigned with 0.2 that means P Survival (Severe-Death) = 0.2. So, the total probability is 1 as the sum of probability of survival for cure and death case is 1. It is represented using Eq. 1. Similarly, for mild cases, the probability of survival for the cure is assigned with 0.8 that means P Survival (Mild-Cure) = 0.8 and the probability of survival for the cases which will be changed from mild to severe is 0.2 that means P Survival (Mild to Severe) = 0.2. So, the total probability is 1 and it is represented using Eq. 2. P Survival ðMild-CureÞ þ P Survival ðMild to SevereÞ ¼ 1 When any mild case changes to the severe case, then its probability of survival will be changed to 0.5 that means P Survival (ms) = 0.5 where ms represents that the mild case is changed to severe case. In this situation, we have considered the survival probability as 0.5 because after changing the mild case to severe case, the probability of survival depends on the availability of hospital bed and the patient will be cured if assigns with a bed for treatment immediately otherwise the probability for death will be higher. Hence, we have considered the probability as 0.5 in this case that means P Survival (ms-Cure) = 0.5 and P Survival (ms-Death) = 0.5 where P Survival (ms-Cure) represents the probability of survival for cure and P Survival (ms-Death) represents the probability of survival for death when mild case changes to severe case. So, the total probability is 1 and it can be represented using Eq. 3. P Survival ðms-CureÞ þ P Survival ðms-DeathÞ ¼ 1 In our work, we have referred the week-wise data of COVID-19 infected patients from February 2, 2020, to July 26, 2020, in India from the source [60] and it is mentioned in Tables 2 and 3 . Graphically, it can be represented as shown in Fig. 2 . Our main objective is to show the hospital beds as well as emergency beds requirement by considering the number of active cases as on July 26, 2020, by applying the proposed method and to compare with FCFSbased method. As per the report, out of total COVID-19 infected cases, 20% of cases are severe. Hence, from Tables 2 and 3, we The simulation of the proposed work is carried out using MATLAB R2015b [61] . From the analysis of Tables 2, 3 and Fig. 2 by using the proposed approach, a minimum of 280 beds is required for 1000 number of infected patients (active cases) in the worst-case scenario. So, if 1000 active cases are normalized to 10 active cases, then the minimum number of bed requirement is 2.8. 2.8 can be considered as Confirmed 2 3 3 3 3 39 113 403 1139 4293 9211 17,305 27,890 42,779 67,177 Recovered 0 0 2 3 3 3 13 23 102 329 1086 2854 6523 11,763 20,970 Dead 0 0 0 0 0 0 2 7 27 118 332 560 881 1463 2214 Active 2 3 1 0 0 36 98 373 1010 3843 7790 13,888 20,483 29,549 43,989 Table 3 Week-wise COVID-19 data in India from 17th May 2020 to 26th July 2020 either 2 or 3. In our work, we have analyzed the status of the number of bed requirement by considering 2 and 3 beds, 4 and 6 beds, 6 and 9 beds, 8 and 12 beds separately for 10, 20, 30 and 40 active cases, respectively, by applying normalization mechanism. As 80% of cases are mild and 20% cases are severe, so out of 10 active cases 8 can be considered as mild cases and 2 can be considered as severe cases. Similarly, out of 20 active cases, 16 can be considered as mild cases and 4 can be considered as severe cases. Again, out of 30 active cases, 24 can be considered as mild cases and 6 can be considered as severe cases, and out of 40 active cases, 32 can be considered as mild cases and 8 can be considered as severe cases. As we have assumed that 10% of cases are death cases, so out of 10, 20, 30 and 40 active cases, the death cases will be 1, 2, 3 and 4, respectively. Again, we have assumed that 10% mild cases will be changed to severe cases although almost all the mild cases have recovered. So, out of 10, 20, 30 and 40 active cases, change from mild to severe cases will be 1, 2, 3 and 4, respectively. The proposed method is analyzed using 10, 20, 30 and 40 cases separately and compared with the FCFS-based method. By referring to Eqs. 1, 2 and 3, we assume that out of 10 active cases, the patients with mild cases are represented as M1, M2, M3, M4, M5, M6, M7 and M8 and the patients with severe cases are represented as S1 and S2. We have assigned randomly the probability of 0.2, 0.8, 0.8, 0.8, 0.8, 0.8, 0.8 and 0.8 to M1, M2, M3, M4, M5, M6, M7 and M8, respectively, and the probability of 0.2 and 0.8 to S1 and S2, respectively. We have also assigned that in each week two number of active cases will arise up to first five weeks by using uniform distribution mechanism and these two cases may be mild or severe or any combination of mild and severe cases. By using this concept, we have analyzed 76 cases by applying the proposed approach for 10 number of active cases by considering 2 hospital beds such as B1, B2 and 3 hospital beds such as B1, B2, B3 separately and compared with FCFS-based approach. These 10 numbers of active cases will be normalized to any number of active cases to describe the assignment of hospital beds and emergency beds to the COVID-19 infected patients. In this work, we have mainly focused on the assignment of hospital beds and emergency beds to the COVID-19 infected patients by considering the total number of active cases as on July 26, 2020. Here, the hospital beds are represented as B1, B2, B3, …., Bm and the emergency beds are represented as E1, E2, E3, …., En. Here, m and n represent the number of hospital beds and emergency beds, respectively. Some of the cases are described by applying Algorithms 1 and 2 as follows. Week 5 S1, S2 M1, M7, M8, S1, S2 Assign bed B2 to S1 and E3 to S2 for 42 days M5, M6: Cured 0 0 Week 6 -M1, S1, S2 E1, E2: Removed M7, M8: Cured 0 0 Week 7 -M1, S1, S2 -0 0 Week 8 -M1, S1, S2 -0 0 Week 9 -S1, S2 Assign B1 to S2 and E3 to S2 for next 14 days E3: Removed M1: Cured 0 0 Week 10 -S1, S2 --0 0 Week 11 ---S1: Dead Week Fig. 3 Week-wise hospital bed status of case 1.1 using the proposed approach Case 3.4: (FCFS-based approach: 10 active cases with 3 beds) Week New case Active case Bed assignment Cured/dead case Emergency bed requirement Week 1 S1, M2 S1, M2 Assign B1 to S1 for 42 days and B2 to M2 for 14 days Week Number of Emergency Bed Required Week Number of Emergency Bed Required Week 1 Week 2 Week 3 Week 4 Week 5 Week 6 Week 7 Week 8 Week 9 Week 10 Week 11 Week 12 Week 13 Week Number of Emergency Bed Required Fig. 11 Week-wise hospital bed status of case 3.1 using the proposed approach Week 1 Week 2 Week 3 Week 4 Week 5 Week 6 Week 7 Week 8 Week 9 Week 10 Week 11 Week 12 Week 13 Week Number of Emergency Bed Required Fig. 12 Week-wise hospital bed status of case 3.2 using FCFSbased approach Neural Computing and Applications 9, 10, 11, 12, 13 and 14, and Tables 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14 and 15, it is observed that the proposed approach can able to minimize the number of hospital emergency beds requirement as compared to FCFS-based approach in the worst-case scenario. The FCFS-based approach requires relatively more number of hospital beds and it creates challenging situations for the treatment of COVID-19 infected patients. The proposed approach can handle some cases with the available number of hospital beds without using any emergency beds for their treatment. From Tables 4 and 5, it is observed that when the number of active cases is 10 and number of available beds are 2, then from case-1.1, 1.2, the number of emergency bed requirements by using proposed approach is 1 and by using FCFS-based approach is 5, from case-2.1, 2.2, the number of emergency bed requirements by using proposed approach is 1 and by using FCFS-based approach is 3, from case-3.1, 3.2, the number of emergency bed requirements by using proposed approach is 0 and by using FCFS-based approach is 4. Similarly, when the number of active cases is 10 and number of available beds are 3, from case-1.3, 1.4, the number of emergency bed requirements by using proposed approach is 0 and by using FCFS-based approach is 4, from case-2.3, 2.4, the number of emergency bed requirements by using proposed approach is 0 and by using FCFS-based approach is 2, from case-3.3, 3.4, the number of emergency bed requirements by using proposed approach is 0 and by using FCFS-based approach is 3. Similarly, the emergency bed requirements for 20, 30, 40, 1000 and 484,041 active cases by using normalized mechanism are mentioned in Tables 6, 7 This paper proposed a fuzzy rule-based approach using the priority-based method to assign hospital beds for the COVID-19 infected patients in the worst-case scenario where the number of hospital beds is very less as compared to the number of patients. This work focuses on the minimization of the number of hospital beds as well as emergency beds requirement in this critical situation. The proposed method is compared with the FCFS-based method by focusing on the number of hospital bed as well as the emergency bed assignment to the COVID-19 infected patients. From the results, it is concluded that the proposed method can handle this critical situation by assigning minimum the number of hospital beds and emergency beds to the COVID-19 infected patients as compared FCFS-based method. The proposed method is also able to handle some cases without assigning any emergency beds the COVID-19 infected patients. This approach can help the government of different countries as well as states to take initiatives accordingly for the assignment of hospital beds to the COVID-19 infected patients in a better way to increase their survival probability. This work will be extended to analyze several cases of hospital bed assignment to COVID19 infected patients by considering the scenarios where the number of positive cases will arise randomly in different weeks. Preparing for a COVID-19 pandemic: a review of operating room outbreak response measures in a large tertiary hospital in Singapore When a system breaks: a queuing theory model for the number of intensive care beds needed during the COVID-19 pandemic Response and operating room preparation for the COVID-19 outbreak: a perspective from the National Heart Centre Singapore The battle against coronavirus disease 2019 (COVID-19): emergency management and infection control in a radiology department Maternal health care management during the outbreak of coronavirus disease 2019 (COVID-19) Duty to plan: health care, crisis standards of care, and novel coronavirus SARS-CoV-2 Screening and managing of suspected or confirmed novel coronavirus (COVID-19) patients: experiences from a tertiary hospital outside Hubei province. medRxiv A model to estimate bed demand for COVID-19 related hospitalization. medRxiv Makeshift hospitals for COVID-19 patients: where health-care workers and patients need sufficient ventilation for more protection Maximizing the calm before the storm: tiered surgical response plan for novel coronavirus The demand for inpatient and ICU beds for COVID-19 in the US: lessons from Chinese cities. medRxiv Critical care utilization for the COVID-19 outbreak in Lombardy, Italy: early experience and forecast during an emergency response The COVID-19 outbreak and spsychiatric hospitals in China: managing challenges through mental health service reform CSC expert consensus on principles of clinical management of patients with severe emergent cardiovascular diseases during the COVID-19 epidemic COVID-19: how doctors and healthcare systems are tackling coronavirus worldwide Hospital preparedness for COVID-19: a practical guide from a critical care perspective Covid19 control in China during mass population movements at new year How will country-based mitigation measures influence the course of the COVID-19 epidemic? COVID-19 and Italy: what next? Isolation, quarantine, social distancing and community containment: pivotal role for old-style public health measures in the novel coronavirus (2019-ncov) outbreak Characteristics of and important lessons from the coronavirus disease 2019 (COVID-19) outbreak in china: summary of a report of 72314 cases from the Chinese center for disease control and prevention Pre-emptive low cost social distancing and enhanced hygiene implemented before local COVID-19 transmission could decrease the number and severity of cases Real-time forecasts of the COVID-19 epidemic in china from Mass masking in the COVID-19 epidemic: people need guidance Impact of non-pharmaceutical interventions (npis) to reduce covid19 mortality and healthcare demand. Imperial College COVID-19 Response Team COVID-19 social distancing will be in place for months Chowell G (2020) Short-term forecasts of the COVID-19 epidemic in Guangdong and Zhejiang COVID-19 science report: social distancing & lockdowns COVID-19 and rationally layered social distancing Review of the clinical characteristics of coronavirus disease 2019 (COVID-19) Mahase E (2020) COVID-19: UK starts social distancing after new model points to 260000 potential deaths COVID-19-navigating the uncharted COVID-19: preparing for superspreader potential among Umrah pilgrims to Saudi Arabia Defining the epidemiology of covid19-studies needed Transmission potential of the novel coronavirus (COVID-19) onboard the diamond princess cruises ship Can we contain the COVID-19 outbreak with the same measures as for sars? COVID-19: social distancing, ace 2 receptors, protease inhibitors and beyond? Stopping the spread of COVID-19 Looming threat of COVID-19 infection in Africa: act collectively, and fast Reactive social distancing in a sir model of epidemics such as COVID-19 The impact of social distancing and epicenter lockdown on the COVID-19 epidemic in mainland china: a data-driven seiqr model study. medRxiv A blueprint for pediatric emergency resource reallocation during the COVID-19 pandemic: an NYC hospital experience Clinical predictors of mortality due to COVID-19 based on an analysis of data of 150 patients from Wuhan. China Presumed asymptomatic carrier transmission of COVID-19 The epidemiological characteristics of an outbreak of 2019 novel coronavirus diseases (COVID-19) in China Critical care crisis and some recommendations during the COVID-19 epidemic in china Forecasting COVID-19 impact on hospital bed-days, ICU-days, ventilator-days and deaths by US state in the next 4 months Physiotherapy management for COVID-19 in the acute hospital setting: clinical practice recommendations Composite Monte Carlo decision making under high uncertainty of novel coronavirus epidemic using hybridized deep learning and fuzzy rule induction Toward development of PreVoid alerting system for nocturnal enuresis patients: a fuzzy-based approach for determining the level of liquid encased in urinary bladder Supplier selection for vendor-managed inventory in healthcare using fuzzy multi-criteria decision-making approach An integrated approach for evaluating hospital service quality with linguistic preferences Fuzzy logic based optimization algorithm. Recent metaheuristics algorithms for parameter identification Priority based round robin (PBRR) CPU scheduling algorithm Priority-based task scheduling method over cloudlet using a swarm intelligence algorithm Comparative analysis between first-come-first-serve (FCFS) and shortest-job-first (SJF) scheduling algorithms First-come-first-served queues with multiple servers and customer classes Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations Conflict of interest We have no conflicts of interest to disclose.