Exploring patient medication adherence and data mining methods in clinical big data: A contemporary review

Abstract

BackgroundIncreasingly, patient medication adherence data are being consolidated from claims databases and electronic health records (EHRs). Such databases offer an indirect avenue to gauge medication adherence in our data‐rich healthcare milieu. The surge in data accessibility, coupled with the pressing need for its conversion to actionable insights, has spotlighted data mining, with machine learning (ML) emerging as a pivotal technique. Nonadherence poses heightened health risks and escalates medical costs. This paper elucidates the synergistic interaction between medical database mining for medication adherence and the role of ML in fostering knowledge discovery.MethodsWe conducted a comprehensive review of EHR applications in the realm of medication adherence, leveraging ML techniques. We expounded on the evolution and structure of medical databases pertinent to medication adherence and harnessed both supervised and unsupervised ML paradigms to delve into adherence and its ramifications.ResultsOur study underscores the applications of medical databases and ML, encompassing both supervised and unsupervised learning, for medication adherence in clinical big data. Databases like SEER and NHANES, often underutilized due to their intricacies, have gained prominence. Employing ML to excavate patient medication logs from these databases facilitates adherence analysis. Such findings are pivotal for clinical decision‐making, risk stratification, and scholarly pursuits, aiming to elevate healthcare quality.ConclusionAdvanced data mining in the era of big data has revolutionized medication adherence research, thereby enhancing patient care. Emphasizing bespoke interventions and research could herald transformative shifts in therapeutic modalities.

Diagnosis and management of inflammatory bowel disease

“…In addition to determining the optimal treatment plan, strict drug adherence is important in IBD because of its recurrence. 203 An increasing number of treatments are expected to emerge in the future in the field of IBD; however, early detection, diagnosis, and treatment are more important (Figure 3).…”

The hospital frailty risk score effectively predicts adverse outcomes in patients with atrial fibrillation in the intensive care unit

“…The study used structured query language (SQL) to extract the data 20 . The following data were extracted:…”

“…The MIMIC-IV combines electronic medical records from different sources, providing researchers with a vast amount of data that includes patient demographics, vital statistics, laboratory results, and diagnoses. The diagnoses were made using the International Classi cation of Diseases, Ninth Revision (ICD-9) and Tenth Revision (ICD-10) codes 20,21 . As the data in this database were deidenti ed, informed consent from patients was not required for this study.…”

A Novel Approach to Dementia Prediction Leveraging Recursive Feature Elimination and Decision Tree

“…Other inputs include cardiovascular health, drug and smoking use, stress level, and demographic factors. In total, LIBRA's 42 entries provide a multidimensional profile of lifestyle factors affecting brain health [28].…”

“…Many previous studies have evaluated the diagnostic utility of BALI, LIBRA, and DTI separately [28]. For example, several studies using BALI-derived volumetrics such as hippocampal atrophy have demonstrated accuracy in distinguishing Alzheimer's patients from controls [29].…”