JMIR Publications

ABSTRACT

Background:

Off-label drug prescribing is prevalent in medicine, including psychiatry, often due to unmet therapeutic needs and failures of standard treatments. The PSYHAMM project, funded by the French Research Agency, investigates these practices. To support this research, a clinical data warehouse with advanced data analysis tools has been developed and deployed. This system integrates both structured and unstructured data from electronic health records, facilitating comprehensive data analysis. The goal is to improve understanding, regulation, and safety of off-label drug use in psychiatry by providing insights into prescribing patterns and their impacts, ultimately contributing to better clinical guidelines and patient care.

Objective:

This study aims to evaluate the effectiveness of a clinical data warehouse in detecting off-label prescriptions in psychiatry.

Methods:

The PSYHAMM data analysis involved a retrospective study of pathology-medication pairs to evaluate the diagnostic accuracy of a computerized system. This system was compared with manual checks performed by a psychiatrist. The evaluation process included verifying if the condition identified by PSYHAMM was documented in the medical record, assessing diagnostic accuracy with tolerance for schizoaffective disorders, and ensuring the identified treatment was current or prescribed in the past. Precision was measured as the number of relevant documents retrieved divided by the total number of documents proposed. Logistic regression analysis was conducted to determine the impact of precise diagnosis, broad diagnosis, and identified treatment on detecting off-label situations.

Results:

The study analyzed 197 records, identifying 14 unique drug-pathology combinations. Bipolar disorder treated with sodium valproate represented the majority of cases (54.8%), followed by schizophrenia treated with sodium valproate (18.8%). The overall precision for detecting off-label situations was 51.3%. The precise diagnosis achieved a precision of 75.6%, while the broad diagnosis showed a higher precision of 84.8%. The identified treatment had a precision of 61.4% and the highest impact on detecting off-label situations (coefficient 6.62, P<.001). The primary challenge was temporal discrepancies, such as distinguishing between acute and chronic conditions, which led to incorrect classification in 48.7% of cases.

Conclusions:

The PSYHAMM project demonstrates the potential of automated systems to accurately identify off-label prescriptions in psychiatry. Despite the promising results, challenges such as temporal discrepancies and data completeness need to be addressed. The findings underscore the importance of continuous refinement and expansion of automated systems, incorporating additional data sources and advanced analytics, to enhance their reliability and effectiveness in clinical practice. Future research should focus on integrating real-time data analytics and expanding to multiple institutions to improve the accuracy and utility of off-label detection systems.