Comparing and validating medication complexity from insurance claims against electronic health records

Medication Regimen Complexity Index Score at Admission as a Predictor of Inpatient Outcomes: A Machine Learning Approach

BACKGROUND

In the intensive care unit, traditional scoring systems use illness severity and/or organ failure to determine prognosis, and this usually rests on the patient's condition at admission. In spite of the importance of medication reconciliation, the usefulness of home medication histories as predictors of clinical outcomes remains unexplored.

METHODS

A retrospective cohort study was conducted using the medical records of 322 intensive care unit (ICU) patients. The predictors of interest included the medication regimen complexity index (MRCI) at admission, the Acute Physiology and Chronic Health Evaluation (APACHE) II, the Sequential Organ Failure Assessment (SOFA) score, or a combination thereof. Outcomes included mortality, length of stay, and the need for mechanical ventilation. Machine learning algorithms were used for outcome classification after correcting for class imbalances in the general population and across the racial continuum.

RESULTS

The home medication model could predict all clinical outcomes accurately 70% of the time. Among Whites, it improved to 80%, whereas among non-Whites it remained at 70%. The addition of SOFA and APACHE II yielded the best models among non-Whites and Whites, respectively. SHapley Additive exPlanations (SHAP) values showed that low MRCI scores were associated with reduced mortality and LOS, yet an increased need for mechanical ventilation.

CONCLUSION

Home medication histories represent a viable addition to traditional predictors of health outcomes.

Clinical Utility of Medication-Based Risk Scores to Reduce Polypharmacy and Potentially Avoidable Healthcare Utilization

The management of multiple chronic health conditions often requires patients to be exposed to polypharmacy to improve their health and enhance their quality of life. However, exposure to polypharmacy has been associated with an increased risk for adverse effects, drug-drug interactions, inappropriate prescribing, medication nonadherence, increased healthcare utilization such as emergency department visits and hospitalizations, and costs. Medication-based risk scores have been utilized to identify patients who may benefit from deprescribing interventions and reduce rates of inappropriate prescribing. These risk scores may also be utilized to prompt targeted discussions between patients and providers regarding medications or medication classes contributing to an individual’s risk for harm, eventually leading to the deprescribing of the offending medication(s). This opinion will describe existing medication-based risk scores in the literature, their utility in identifying patients at risk for specific adverse events, and how they may be incorporated in healthcare settings to reduce rates of potentially inappropriate polypharmacy and avoidable healthcare utilization and costs.