Preventive & Decentralized Health Care with the Application of Artificial Intelligence

Abstract

The emergence of novel medications has altered performance in the healthcare industry. Artificial intelligence (AI) has improved medical procedures by helping professionals make better decisions about disorders of complex and unpredictable systems. The application of artificial intelligence in preventive and decentralized health care is helpful in disease prevention. Information about disease prevention can be dispersed in the decentralized healthcare units and in the community to prevent disease outbreaks. For the health care system to integrate disparate systems and improve the accuracy of medical electronic records (ER) and a more patient-centric approach to care are direly needed. The current study was designed to apply artificial intelligence in decentralized healthcare settings to maintain electronic records, ensure patient privacy, and implement preventive measures. A total of 200 Patients, with diabetes (n=100) and Alzheimer (n=100), presented to the clinic and were assigned Pid and device Did through which patients were screened. Data about the potential risk factors was collected through a predesigned questionnaire including open-ended and close-ended (di and trichotomous questions) specific to the disease condition. The collected information was organized in MS Excel and subjected to analysis through SPSS for evaluation of significant risk factors based on chi-square. The significantly associated risk factors (p<0.05) in both cases were age, gender, BMI, physical activity, smoking, blood pressure, family history, alcohol consumption, stress, sleep disorder, and environmental factors. But specific to the disease condition, plasma levels of calcium and vitamins were significant in Alzheimer’s patients while diet plan and risk score were significant in diabetes. In the case of Alzheimer’s patient records, most of the infected age group was above 58 years as the mean value was 61.05 (S.E=1.304; SD=13.04) with median=60, mode=58 and that of diabetes was above 33 years with mean 42.93 (S.E=1.09; SD=10.94); median 43 and mode 33. Other numerical variables Viz; blood pressure (mean=142.93/89.01+12.97/4.25), risk score (mean=6.87+2), and BMI (mean=28.17+3.26) for diabetes but physical activity (2.56hrs+1.4), and cognitive activity (2.59hrs+1.98) for Alzheimer's patients were observed. The correlation analysis of quantitative variables for diabetes depicts the positive and strong association among blood pressure (diastolic), risk score, and BMI. While it was negative among age, systolic blood pressure, risk score, and BMI. Among Alzheimer patients’ correlation analysis depicts the negative association of BMI and physical activity with age and cognitive activity. However, BMI and physical activity have a positive correlation with each. Cognitive activity has a negative correlation (inverse relation) with all the quantitative factors. The obtained information was dispersed to the public under decentralized conditions for disease prevention using AI. Further studies on other diseases can be performed for their prevention under a decentralized model for information dissemination and data collection at a large scale.