key: cord-0714066-eon23hm4 authors: Adwibowo, A. title: Fuzzy logic assisted COVID 19 safety assessment of dental care date: 2020-06-22 journal: nan DOI: 10.1101/2020.06.18.20134841 sha: 380ccf365fd6e4d9055059072f32f9b5d35f9b2e doc_id: 714066 cord_uid: eon23hm4 Uncertainty is significant when assessing a risk of certain health care facility conditions especially the facility that prone to the COVID 19 risk. One solution to deal with an uncertainty in health situation assessment is through fuzzy inference system. For that reason, this study aims to develop fuzzy assisted system to assess the safety of dental care related to the sets of patient and environmental conditions. The fuzzy system allows assessment based on the patient body temperature, travel history, dental care ventilation rate, and disinfection frequency. The fuzzy system incorporates several steps including fuzzification, fuzzy regulation, and defuzzification. As a result of this study, the fuzzy system is able to assess and identify the risk of dental care according to the patient health status and hygiene conditions of dental care as well. To conclude, fuzzy system used in this study has offered the advantage of assessing at any situation as for patient and environmental factor predicts the safety of dental care. Dental care should be aware on the exposure risks since it is an occupation with a high potential for exposure. On behalf of these exposure risks, all dental care providers must always be cautious and meticulous in mitigating the risk as well as develop and provide clear and easy guidelines and methods to manage early safety measures against any risk (Peditto et al. 2020 ). Dental care needs improved effective strategies for risk prevention and reduction. Nonetheless, one of the main challenges in the dental care is the difficulty in the various issues including patient and history identification, Currently, dental care at all times is encouraged to competently follow crossinfection preventive measures (Odeh et al. 2020 The fuzzy logic rules developed in this study was following Dhiman and Sharma (2020), Muka et al. (2017) , Princy and Dhenakaran (2016) , and Walia et al. (2016) . The steps are as follows: It is fundamental to first consider all necessary preventive measure parameters that contribute to minimize the risk during visit to dental care. All measures should cover aspects of patients and environments of dental care. Correspondingly, a set of patient and environmental aspects of dental care along with membership function and linguistic ranges were listed in Table 1 . Membership functions were selected for each value of the input parameters. The degree of an input belongs to a fuzzy set is denoted by membership function ranging from 0 to 1 and expressed as µ. Membership functions were developed for each parameter along with their µ values. The fuzzy inference system to diagnose the dental care risks is developed using 4 input parameters (Table 1 ) and 1 output as available in Figure 1 . Those inputs and outputs were . CC-BY-NC-ND 4.0 International license It is made available under a is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. The copyright holder for this preprint this version posted June 22, 2020. . https://doi.org/10.1101/2020.06.18.20134841 doi: medRxiv preprint further divided into 3 linguistic ranges denoting the risk levels ranging from low, medium, to high. The "if then" rules were used to analyze the inputs to generate the risk levels. The fuzzy inference system is consisting of 3 steps, including fuzzification or developing the membership function by translating and denoting (µ = 0 -1) the linguistic ranges, fuzzy regulation or developing the "if then" rules, and defuzzification. This study has developed 4 input fuzzy set . CC-BY-NC-ND 4.0 International license It is made available under a is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. The copyright holder for this preprint this version posted June 22, 2020. . CC-BY-NC-ND 4.0 International license It is made available under a is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. First define the rules as follows: 1. If patient's body temperature is high and dental care ventilation rate is low then the risk is high. 2. If patient's body temperature is medium and dental care ventilation rate is medium then the risk is medium. Calculate the risk of dental care using fuzzification if patient's body temperature is 36.9 0 C and the ventilation rate is 620 m 3 /h. 3. Based on the rules, the fuzzification values are "If patient's body temperature is high (µ = 0.8) and dental care ventilation rate is low (µ = 0.8) then the risk is high", the high risk is equal to minimum µ equal to 0.8. and µ = 0.2 (dental care ventilation rate is medium), then the medium risk is equal to minimum µ equal to 0.2. 5. The next step is plotting the µ = 0.2 with the risk level of risk fuzzy sets (30) and the µ = 0.8 with the risk level of risk fuzzy sets (90) ( Figure 6 ). The calculation as follows: To conclude with patient's body temperature is 36.9 0 C and the ventilation rate sets to 620 m 3 /h, the risk of dental care is 78%. The fuzzy system can assist the dental care to project the risk that the dental care may pose related to the patient's status and environmental conditions. The risk information can guide the dental care management to make a decision and take a necessary preventive measure. Sets of rule combinations can be developed based on the available inputs (Table 2) . Since this study has recorded 4 input parameters consisting of body temperature, travelling history, ventilation rate, and disinfection frequency and each parameter has 3 linguistic types (low, medium, high), then according to Allahverdi and Ertosun (2018) the numbers of fuzzy rule combinations can be calculated as: 3*3*3*3 = 81 rule combinations Table 3 . Table 3 . Safety and preventive measures in linguistic scale of dental care (Marwaha and Shah 2020, Iqbal 2020). . CC-BY-NC-ND 4.0 International license It is made available under a is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. The copyright holder for this preprint this version posted June 22, 2020 . . https://doi.org/10.1101 /2020 Take proper medical history, body temperature, and travel history (have travelled or have contacted with a person with confirmed 2019-nCoV infection within the past 14 days). Infection control Personal protection equipment, routine cleaning, and disinfection. Self protection Use disposable PPE, the PPE should be worn once and discarded after use, and receive flu vaccine. Since dental care is provided inside an indoor is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. The copyright holder for this preprint this version posted June 22, 2020 . . https://doi.org/10.1101 /2020 unclear and vague. By using the fuzzy system, the boundary of elusive symptoms including fevers, fatigue now is clear and tangible. The fuzzy logics in the field of health care have been widely used and applied in wide ranging of topic from disease diagnosis (Walia et al. 2016 , Walia et al. 2017 Despite there is still a room for improvement, this study has developed a fuzzy system in particular dental care. A patient and environmental status representing the actual conditions of dental care have been represented and calculated in here. The output based on "if then" rules have represented the input parameters conditions. The use of fuzzy system is believed can serve as a dependable and cheap means of diagnosing the risk of dental care may have. Dental care like other health cares is facing ambiguity especially when dealing with many . CC-BY-NC-ND 4.0 International license It is made available under a is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. (which was not certified by peer review) The copyright holder for this preprint this version posted June 22, 2020. . https://doi.org/10.1101/2020.06.18.20134841 doi: medRxiv preprint elusive health, patient, and environment aspects that require decision making immediately. Correspondingly, a fuzzy system can be used as diagnosis tool for dental care providers to make diagnosis, evaluate and assess the risks, and develop the measures. In future, it is recommended that the fuzzy system incorporates more input parameters to represent all possible risks. Fear and Practice Modifications among Dentists to Combat Novel Coronavirus Disease (COVID-19) Outbreak Application of fuzzy logic for risk determination of type 2 diabetes disease Fuzzy logic use in classification of the severity of diabetic medRixv Fuzzy logic approach for infectious disease diagnosis: A methodical evaluation, literature and classification Association of infected probability of COVID-19 with ventilation rates in confined spaces: a Wells-Riley equation based investigation. medRixv Fuzzy Logic Inference System for Identification and Prevention of Coronavirus (COVID-19) Questionnaire to evaluate COVID-19 suspected patient before the dental procedure Safety & Preventive Measures for Dental Health Care Professionals on COVID-19 Rainfall prediction using fuzzy logic COVID-19: Present and Future Challenges for Dental Practice Dentistry during the COVID-19 Epidemic: An Italian Workflow for the Management of Dental Practice Comparison of Triangular and Trapezoidal Fuzzy Membership Function COVID-19 Outbreak: An Overview on Dentistry Design and identification of tuberculosis using Fuzzy Based Decision Support System Cleaning and disinfection of environmental surfaces in the context of COVID-19 A Webbased Fuzzy Inference System Based Tool for Cardiovascular Disease Risk Assessment