Use of Machine Learning and Artificial Intelligence Methods in Geriatric Mental Health Research Involving Electronic Health Record or Administrative Claims Data: A Systematic Review

Abstract

Introduction: Electronic health records (EHR) and administrative healthcare data (AHD) are frequently used in geriatric mental health research to answer various health research questions. However, there is an increasing amount and complexity of data available that may lend itself to alternative analytic approaches using machine learning (ML) or artificial intelligence (AI) methods. We performed a systematic review of the current application of ML or AI approaches to the analysis of EHR and AHD in geriatric mental health.Methods: We searched MEDLINE, Embase, and PsycINFO to identify potential studies. We included all articles that used ML or AI methods on topics related to geriatric mental health utilizing EHR or AHD data. We assessed study quality either by Prediction model Risk OF Bias ASsessment Tool (PROBAST) or Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) checklist.Results: We initially identified 391 articles through an electronic database and reference search, and 21 articles met inclusion criteria. Among the selected studies, EHR was the most used data type, and the datasets were mainly structured. A variety of ML and AI methods were used, with prediction or classification being the main application of ML or AI with the random forest as the most common ML technique. Dementia was the most common mental health condition observed. The relative advantages of ML or AI techniques compared to biostatistical methods were generally not assessed. Only in three studies, low risk of bias (ROB) was observed according to all the PROBAST domains but in none according to QUADAS-2 domains. The quality of study reporting could be further improved.Conclusion: There are currently relatively few studies using ML and AI in geriatric mental health research using EHR and AHD methods, although this field is expanding. Aside from dementia, there are few studies of other geriatric mental health conditions. The lack of consistent information in the selected studies precludes precise comparisons between them. Improving the quality of reporting of ML and AI work in the future would help improve research in the field. Other courses of improvement include using common data models to collect/organize data, and common datasets for ML model validation.

Machine learning functional impairment classification with electronic health record data

“…Previous research in developing predictive models for conditions related to poor function has primarily concentrated on frailty or cognitive impairment 28,29 . These models have used both unstructured and structured EHR data elements and have achieved AUCs ranging from 0.7 to 0.9 18,30–32 . In contrast, our study is the first to focus on predicting impaired performance of daily living activities, utilizing only predictors available in structured patient data from the EHR, making data abstraction and analysis more feasible, reliable, timely, and lower cost compared to also using unstructured data.…”

“…0.9. 18,[30][31][32] In contrast, our study is the first to focus on predicting impaired performance of daily living activities, utilizing only predictors available in structured patient data from the EHR, making data abstraction and analysis more feasible, reliable, timely, and lower cost compared to also using unstructured data. Despite this difference, our results are comparable to those of previous models.…”

Identifying Medicare beneficiaries with Alzheimer's disease and related dementia using home health OASIS assessments

“…Racial and ethnic diversity 23,24 and disease severity are known factors shaping the ability of algorithms to distinguish true positives 25 . Enduring concerns about the lack of consistent information provided across studies make it challenging to compare predictive modeling algorithms to analyze EHR and administrative data between studies in geriatric mental health 26 …”

“…25 Enduring concerns about the lack of consistent information provided across studies make it challenging to compare predictive modeling algorithms to analyze EHR and administrative data between studies in geriatric mental health. 26 The prediction of recognized dementia, operationalized as a CCW diagnosis of ADRD, has implications for the measurement of cognitive impairment across postacute care settings and in home health specifically. Knox and colleagues developed a clinically informed equivalence between the Functional Assessment Staging Tool as a method for staging individuals with dementia using various OASIS items, and showed a significant relationship between increased severity and the risk of potentially preventable hospital readmission.…”

Use of Electronic Medical Records (EMR) in Gerontology: Benefits, Considerations and a Promising Future

“…Figure 2 Summary of benefits and limitations of using electronic medical records. 2,3,[5][6][7][8][9][10][11][12][13][14]16,33 risk, as determined by the Hospital Frailty Risk Score, have increased 30-day mortality, longer hospital stays and higher readmission rates, although the score's ability to differentiate outcomes at the individual level is limited. 16 This initial identification, however, can be useful in making decisions about follow-up care.…”