Impact of a machine learning based decision support for Urinary Tract Infections: Prospective observational study in 36 primary care practices (Preprint)

BACKGROUND There is increasing attention for machine learning based clinical decision support systems (CDSS), but their added value and pitfalls are very rarely evaluated at the frontline of clinical practice. We have implemented a CDSS to aid general practitioners (GP) with the treatment of patients with urinary tract infections (UTI). UTIs are a large health burden worldwide and the scientific evidence for clinically effective treatments with increased risk of a complicated UTI is limited. OBJECTIVE In this study, we prospectively assess the impact of this CDSS on treatment success and change in antibiotic prescription behavior of the physician. Doing so, we hope to identify drivers and obstacles for positively impacting the quality of healthcare practice with machine learning. METHODS The CDSS was developed as a joint effort by Pacmed, Nivel and LUMC. The CDSS presents the expected outcomes of treatments together with context information needed to assess the expected outcomes well. Treatment success was defined as a subsequent period of 28 days where no new antibiotic treatment for the UTI was needed. In this prospective observational study, 36 primary care practices used the software for a period of four months, starting in November 2017. Twenty-nine control practices were identified through a propensity score matching procedure. All analyses have been done on electronic health records from the Nivel Primary Care database. Patients for which the software has been used have been identified in the Nivel database through a sequential matching procedure using the CDSS usage data. To evaluate treatment success, we have compared the proportion of successful treatments prior and during the study within the treatment arm. The same analysis has been done for the control practices and for the subgroup of patients we were sure of the software has been used for. All analyses were statistically tested by two-sided z-tests with an alpha level of .05. In assessing the difference of treatment success for several patient subgroups, Bonferroni corrections were applied. Lastly, the antibiotic prescription behavior of the physicians was analyzed through the same z-tests. RESULTS In the treatment practices, 4998 patients were included in the period of time before the implementation study, 3422 patients were included during the implementation period. In the control practices, 5044 patients were included before the implementation period, 3360 patients were included during. The proportion of successful treatments increased significantly from 75% to 80% on average in the treatment practices (z=5.47, p<.001). In the control practices, no significant difference was detected (76% before and 76% during the pilot, z=0.02, p=0.98). We have been able to identify 734 out of 1200 patients in the CDSS usage database in the Nivel database. For these patients, of whom we are certain the software has been used for, the proportion of successful treatments during the study was 83%. This is a statistically significant difference with the 75% of successful treatments prior to the study in the treatment practices (z=4.95, p<.001). CONCLUSIONS The introduction of the CDSS as intervention in the 36 treatment practices was associated with statistically significant improved treatment success. We have excluded temporal effects and validated the result with the subgroup analysis in patients for whom we are certain the software was used. The study shows important strengths and points of attention for the development and implementation of a machine learning based CDSS in clinical practice. CLINICALTRIAL The trial was registered on ClinicalTrials.gov under the Identifier NCT04408976.

Role of Physician’s Personality on their Drug Prescription Behavior

Physicians Prescription behavior is the results of 4P's namely Product, Physicians, Promotion, and Patient's expectation. In today's world of evidence-based medicine with ever-growing demand in patient expectations, physician- Patient-centric managing a pathological condition is gaining acceptance from the normal disease management approach. Like all citizenry is Unique; similarly, physicians also possess a singular personality that responds differently even to an equivalent stimulus. Aiming for better patient care and Patient expectations, research work across the world has been administered for identifying the perfect physician personality traits right from selection of specialty, knowledge dissemination during the study period, and managing patients during the Practice sessions. However, there's little, or no research conducted thus far, in understanding the "Physician's personality" make-up focussing on their motives, values, preferences in their professional practice. Understanding "physician's personality" traits will lay a robust foundation for developing effective medico-marketing initiatives from the pharmaceutical industry with the assistance of smart and customized marketing initiatives resulting in a healthy environment for physician-Pharma association towards adopting better therapeutic interventions for patient benefit. This review is an effort to specialize in the research work done thus far in understanding the impact of "physician's personality" aimed toward improving patient care. Further research in understanding "Physician's personality" and its role in physicians prescribing decisions will help the Pharma industry towards developing much needed medico-marketing initiatives with optimal utilization of resources towards disseminating the latest therapeutic interventions to the physicians for better patient care which is the stepping stone for Physician-patient centric management.

Antimicrobial stewardship: The influence of behavioral nudging on renal-function–based appropriateness of dosing

Failure to adjust doses may contribute to adverse events. We evaluated the effectiveness of providing the estimated glomerular filtration rate on appropriateness of dosing for antimicrobials. The approach increased appropriateness of dosing from 33.9% to 41.4% (P < .001). Nudging prescription behavior can boost strategies for adequate antimicrobial prescription.

“Let the Sunshine In”: The Impact of Industry Payment Disclosure on Physician Prescription Behavior

Disclosing marketing payments to physicians resulted in a robust decline in both branded and generic prescriptions in three best-seller classes, likely because of physician self-monitoring.

Social and Behavioral Theories and Physician’s Prescription Behavior

The efficacy, safety, and cost of medication are the major concerns for a patient; thus, this research addresses factors that influence the physician’s prescription behavior. The objective of the undertaken study is the empirical testing of a novel conceptual model that was newly developed by the previous literature, which is based on behavioral and social theories. The considered model explains the association between marketing efforts, pharmacist factors, patient characteristics, and the physician’s decision to prescribe a drug. This unique model also includes the influence of cost and benefit ratio, drug characteristics, physician’s persistence, and trustworthiness as moderating variables. This model is useful for analyzing the prospects of marketing. We have collected 984 physicians’ responses from the urban centers of Pakistan through a structured questionnaire. We have used Structural equation modelling (SEM) based multivariate techniques such as exploratory and confirmatory factor analysis, and conditional process modelling to explore the direct and indirect relationship amongst the exogenous, moderating, and endogenous variables. The findings of the study demonstrated that marketing efforts, patient’s characteristics, and pharmacist factors have a positive and significant influence on the physician’s decision to prescribe medicines. The moderation analysis exhibited the significant effect of drug characteristics, cost–benefit ratio, physician’s persistence, and trustworthiness in a relationship between exogenous and endogenous variables. The results of the undertaken study are helpful for the marketers of the pharmaceutical industry to save wasteful marketing expenditures for the product portfolios, and measured variables may help to make meaningful marketing strategies for the physician’s prescription that provide optimum Returns on Investment (ROI) of their investments.