RESUMEN
BACKGROUND: To provide quality care, modern health care systems must match and link data about the same patient from multiple sources, a function often served by master patient index (MPI) software. Record linkage in the MPI is typically performed manually by health care providers, guided by automated matching algorithms. These matching algorithms must be configured in advance, such as by setting the weights of patient attributes, usually by someone with knowledge of both the matching algorithm and the patient population being served. OBJECTIVE: We aimed to develop and evaluate a machine learning-based software tool, which automatically configures a patient matching algorithm by learning from pairs of patient records previously linked by humans already present in the database. METHODS: We built a free and open-source software tool to optimize record linkage algorithm parameters based on historical record linkages. The tool uses Bayesian optimization to identify the set of configuration parameters that lead to optimal matching performance in a given patient population, by learning from prior record linkages by humans. The tool is written assuming only the existence of a minimal HTTP application programming interface (API), and so is agnostic to the choice of MPI software, record linkage algorithm, and patient population. As a proof of concept, we integrated our tool with SantéMPI, an open-source MPI. We validated the tool using several synthetic patient populations in SantéMPI by comparing the performance of the optimized configuration in held-out data to SantéMPI's default matching configuration using sensitivity and specificity. RESULTS: The machine learning-optimized configurations correctly detect over 90% of true record linkages as definite matches in all data sets, with 100% specificity and positive predictive value in all data sets, whereas the baseline detects none. In the largest data set examined, the baseline matching configuration detects possible record linkages with a sensitivity of 90.2% (95% CI 88.4%-92.0%) and specificity of 100%. By comparison, the machine learning-optimized matching configuration attains a sensitivity of 100%, with a decreased specificity of 95.9% (95% CI 95.9%-96.0%). We report significant gains in sensitivity in all data sets examined, at the cost of only marginally decreased specificity. The configuration optimization tool, data, and data set generator have been made freely available. CONCLUSIONS: Our machine learning software tool can be used to significantly improve the performance of existing record linkage algorithms, without knowledge of the algorithm being used or specific details of the patient population being served.
RESUMEN
In the health systems of many countries, there is neither a requirement to collect a minimum set of demographic information during patient registration nor a standard way of identifying patients. This impedes the provision of integrated, good-quality care for individual patients and, at the system level, prevents generation of the high-quality data necessary for effective management and continuous improvement. Assigning each patient a unique identifier (UID) to create a master patient index (MPI) is therefore essential to ensure data interoperability across all the points of patient care within a health system. Although advances in technology are shifting the boundary between civil registration and personal identification, the additional value of an MPI/UID system lies in the technical and operational capacity to ensure that clinical data are safely and securely managed. Moreover, operationalization of MPI/UID data enables the establishment of an evidence-based, constantly improving "learning health system" with feedback loops that allow measurement, evaluation and visualization of performance over time. The Ministry of Health and Sports of Myanmar is actively engaged in a multistakeholder collaborative process working towards a nationwide MPI/UID system. Demonstration pilots are planned for both online and offline modes of operation for HIV/AIDS, mother and child health (including eliminating mother-to-child transmission of HIV and syphilis) and hospital settings, which are expected to open up the potential for expansion to all health interventions and facilities. With the implementation of the MPI/UID system under way in Myanmar, the Ministry of Health and Sports is laying the foundation to put individuals at the centre of care and deliver a lifelong service for all.
