RELIABLY DETECTING COVID-19 IS CRITICAL FOR DIAGNOSIS AND DISEASE CONTROL. HOWEVER, IMBALANCED DATA IN MEDICAL DATASETS POSE SIGNIFICANT CHALLENGES FOR MACHINE LEARNING MODELS, LEADING TO BIAS AND POOR GENERALIZATION. THE DATASET OBTAINED FROM THE EPIVIGILA SYSTEM AND THE CHILEAN EPIDEMIOLOGICAL SURVEILLANCE PROCESS CONTAINS INFORMATION ON OVER 6,000,000 PATIENTS, BUT, LIKE MANY CURRENT DATASETS, IT SUFFERS FROM CLASS IMBALANCE. TO ADDRESS THIS ISSUE, WE APPLIED VARIOUS MACHINE LEARNING ALGORITHMS, BOTH WITH AND WITHOUT SAMPLING METHODS, AND COMPARED THEM USING DIFFERENT CLASSIFICATION AND DIAGNOSTIC METRICS SUCH AS PRECISION, SENSITIVITY, SPECIFICITY, LIKELIHOOD RATIO POSITIVE, AND DIAGNOSTIC ODDS RATIO. OUR RESULTS SHOWED THAT APPLYING SAMPLING METHODS TO THIS DATASET IMPROVED THE METRIC VALUES AND CONTRIBUTED TO MODELS WITH BETTER GENERALIZATION. EFFECTIVELY MANAGING IMBALANCED DATA IS CRUCIAL FOR RELIABLE COVID-19 DIAGNOSIS. THIS STUDY ENHANCES THE UNDERSTANDING OF HOW MACHINE LEARNING TECHNIQUES CAN IMPROVE DIAGNOSTIC RELIABILITY AND CONTRIBUTE TO BETTER PATIENT OUTCOMES.

IDENTIFYING THE CLINICAL NEEDS TO EVALUATE AND MANAGE THE TREATMENT AND MONITORING OF CANCER PATIENTS IS A MULTIDIMENSIONAL CHALLENGE IN HEALTHCARE INSTITUTIONS. IN THIS REGARD, ELECTRONIC HEALTH RECORDS (EHRS) ARE BENEFICIAL FOR MANAGING CLINICAL INFORMATION; HOWEVER, EHRS FOCUSED EXCLUSIVELY ON PATIENTS WITH CANCER HAVE NOT BEEN SUFFICIENTLY ADOPTED. IN CHILE, THE NEED FOR ONCOLOGY EHR HAS ONLY BEEN BRIEFLY ADDRESSED, RESULTING IN INSUFFICIENT UPDATED AND SYSTEMATIZED INFORMATION ON ONCOLOGY PATIENTS. IN THIS PAPER, WE PROPOSE THE DESIGN OF AN ONCOLOGY EHR THAT MANAGES CRITICAL VARIABLES AND PROCESSES FOR THE TREATMENT AND MONITORING OF PATIENTS WITH CANCER IN CHILE. WE USED A SYSTEMATIC METHODOLOGY TO DESIGN A SOFTWARE ARCHITECTURE ORIENTED TO FOCUS GROUPS AND INTERVIEWS TO ELICIT THE REQUIREMENTS AND NEEDS OF STAKEHOLDERS. WE CREATED AND DESCRIBED AN EHR DESIGN THAT CONSIDERS FOUR MODULES THAT GROUP AND MANAGE THE MAIN VARIABLES AND PROCESSES THAT ARE CRITICAL FOR TREATING AND MONITORING ONCOLOGY PATIENTS. ENABLING AND DESIGNING A TREATMENT AND MONITORING REGISTRY FOR CANCER PATIENTS IN CHILE IS ESSENTIAL BECAUSE IT ALLOWS FOR THE EVALUATION OF STRATEGIC CLINICAL DECISIONS IN FAVOR OF PATIENTS.

THE MINI-MENTAL STATE EXAMINATION (MMSE) IS THE MOST WIDELY USED COGNITIVE TEST FOR ASSESSING WHETHER SUSPECTED SYMPTOMS ALIGN WITH COGNITIVE IMPAIRMENT OR DEMENTIA. THE RESULTS OF THIS TEST ARE MEANINGFUL FOR CLINICIANS BUT EXHIBIT HIGHLY UNBALANCED DISTRIBUTIONS IN STUDIES AND ANALYSES REGARDING THE CLASSIFICATION OF PATIENTS WITH COGNITIVE IMPAIRMENT. THIS IS A COMPLEX PROBLEM WHEN A LARGE NUMBER OF MMSE TESTS ARE ANALYSED. THEREFORE, DATA BALANCING AND CLASSIFICATION TECHNIQUES ARE CRUCIAL TO SUPPORT DECISION-MAKING IN DISTINGUISHING PATIENTS WITH COGNITIVE IMPAIRMENT IN AN EFFECTIVE AND EFFICIENT MANNER. THIS STUDY EXPLORES MACHINE LEARNING TECHNIQUES FOR DATA BALANCING AND CLASSIFICATION USING A REAL UNBALANCED DATASET CONSISTING OF MMSE TEST RESPONSES COLLECTED FROM 103 ELDERLY PATIENTS PARTICIPATING IN A CHILEAN PATIENT MONITORING PROJECT. WE USED 8 DATA CLASSIFICATION TECHNIQUES AND FIVE DATA BALANCING TECHNIQUES. WE EVALUATED THE PERFORMANCE OF THE TECHNIQUES USING THE FOLLOWING METRICS: SENSITIVITY, SPECIFICITY, F1-SCORE, LIKELIHOOD RATIO (LR+ AND LR-), DIAGNOSTIC ODDS RATIO (DOR), AND THE AREA UNDER THE ROC CURVE (AUC). FROM THE SET OF DATA BALANCING AND CLASSIFICATION TECHNIQUES USED IN THIS STUDY, THE RESULTS INDICATE THAT SYNTHETIC MINORITY OVERSAMPLING AND RANDOM FOREST BALANCING TECHNIQUES IMPROVE THE ACCURACY OF COGNITIVE IMPAIRMENT DIAGNOSIS. THE RESULTS OBTAINED IN THIS STUDY SUPPORT CLINICAL DECISION-MAKING REGARDING EARLY CLASSIFICATION OR EXCLUSION OF OLDER ADULT PATIENTS WITH SUSPECTED COGNITIVE IMPAIRMENT.

CONTEXT: SOFTWARE ENGINEERING IS DEDICATED TO THE SYSTEMATIC AND EFFICIENT DEVELOPMENT OF SOFTWARE, WHICH NECESSITATES THE ACTIVE PARTICIPATION OF ALL TEAM MEMBERS AND A RECOGNITION OF THEIR UNIQUE SKILLS AND ABILITIES, INCLUDING THOSE WITH AUTISM SPECTRUM DISORDERS (ASD). THE INCLUSION OF INDIVIDUALS WITH ASD PRESENTS NEW PERSPECTIVES, YET THERE IS A LACK OF SYSTEMATIC EVIDENCE REGARDING THE PRIMARY OBSTACLES AND POTENTIAL BENEFITS ASSOCIATED WITH THEIR INCLUSION.

ARCHITECTS OFTEN EVALUATE AND ANALYZE APPLICATION FRAMEWORKS THAT IMPLEMENT ARCHITECTURAL PATTERNS THAT STRUCTURE SOFTWARE DESIGNS TO ADDRESS QUALITY ATTRIBUTE CONCERNS. TO SATISFY THE QUALITY ATTRIBUTES THROUGH ARCHITECTURAL PATTERNS, THESE MUST BE COMPLEMENTED BY ARCHITECTURAL TACTICS. ALTHOUGH ARCHITECTURAL PATTERNS PACK ARCHITECTURAL TACTICS, THERE HAS BEEN LITTLE DISCUSSION ON THE EFFECT OF USING ARCHITECTURAL TACTICS TO SUPPORT ARCHITECTURAL PATTERNS TO SELECT APPLICATION FRAMEWORKS IN ARCHITECTURAL DESIGN. THIS STUDY REPORTS A CONTROLLED EXPERIMENT WITH IT PROFESSIONALS (N = 28) THAT EVALUATES ARCHITECTURAL PATTERNS AND TACTICS TO SELECT APPLICATION FRAMEWORKS. TWO SCENARIOS ARE CONSIDERED. SCENARIO 1 INCLUDED ARCHITECTURAL PATTERNS AND TACTICS AS DECISION MECHANISMS, WHILE SCENARIO 2 CONSIDERED ONLY ARCHITECTURAL PATTERNS. WE USED PRECISION, RECALL, AND A CUSTOM EFFICIENCY METRIC TO COMPARE THE SCENARIOS. THE RESULTS INDICATE THAT SCENARIO 1 PRODUCES MORE PRAGMATIC AND EFFICIENT SOLUTIONS THAN SCENARIO 2 DOES. ARCHITECTURAL TACTICS REDUCE SPACE FOR SOLUTIONS TO MAKE MORE PRECISE DECISIONS REGARDING ARCHITECTURAL DESIGN.