ABSTRACT
Deep Learning and Machine Learning are becoming more and more popular as their algorithms get progressively better, and their use is expected to have the large effect on improving the health care system. Also, the pandemic was a chance to show how adding AI to healthcare infrastructure could help, since infrastructures around the world are overworked and falling apart. These new technologies can be used to fight COVID-19 because they are flexible and can be changed. Based on these facts, we looked at how the ML and DL-based models can be used to deal with the COVID-19 pandemic problem and what the pros and cons of each are. This paper gives a full look at the different ways to find COVID-19. We looked at the COVID-19 issues in a systematic way and then rated the methods and techniques for finding it based on their availability, ease of use, accuracy, and cost. We have also shown in pictures how well each of the detection techniques works. We did a comparison of different detection models based on the above factors. This helps researchers understand the different methods and the pros and cons of using them as the basis for their research. In the last part, we talk about the open challenges and research questions that come with putting these techniques together with other detection methods.
ABSTRACT
PURPOSE: Adherence to self-administered biologic disease-modifying antirheumatic drugs (bDMARDs) is necessary for therapeutic benefit. Health-system specialty pharmacies (HSSPs) have reported high adherence rates across several disease states; however, adherence outcomes in rheumatoid arthritis (RA) populations have not yet been established. METHODS: We performed a multisite retrospective cohort study including patients with RA and 3 or more documented dispenses of bDMARDs from January through December 2018. Pharmacy claims were used to calculate proportion of days covered (PDC). Electronic health records of patients with a PDC of <0.8 were reviewed to identify reasons for gaps in pharmacy claims (true nonadherence or appropriate treatment holds). Outcomes included median PDC across sites, reasons for treatment gaps in patients with a PDC of <0.8, and the impact of adjusting PDC when accounting for appropriate therapy gaps. RESULTS: There were 29,994 prescriptions for 3,530 patients across 20 sites. The patient cohort was mostly female (75%), with a median age of 55 years (interquartile range [IQR], 42-63 years). The median PDC prior to chart review was 0.94 (IQR, 0.83-0.99). Upon review, 327 patients had no appropriate treatment gaps identified, 6 patients were excluded due to multiple unquantifiable appropriate gaps, and 420 patients had an adjustment in the PDC denominator due to appropriate treatment gaps (43 instances of days' supply adjusted based on discordant days' supply information between prescriptions and physician administration instructions, 11 instances of missing fills added, and 421 instances of clinically appropriate treatment gaps). The final median PDC after accounting for appropriate gaps in therapy was 0.95 (IQR, 0.87-0.99). CONCLUSION: This large, multisite retrospective cohort study was the first to demonstrate adherence rates across several HSSPs and provided novel insights into rates and reasons for appropriate gaps in therapy.