Prediction of Future Health Care Utilization Through Note-extracted Psychosocial Factors

Abstract

Background: Persons with multimorbidity (≥2 chronic conditions) face an increased risk of poor health outcomes, especially as they age. Psychosocial factors such as social isolation, chronic stress, housing insecurity, and financial insecurity have been shown to exacerbate these outcomes, but are not routinely assessed during the clinical encounter. Our objective was to extract these concepts from chart notes using natural language processing and predict their impact on health care utilization for patients with multimorbidity. Methods: A cohort study to predict the 1-year likelihood of hospitalizations and emergency department visits for patients 65+ with multimorbidity with and without psychosocial factors. Psychosocial factors were extracted from narrative notes; all other covariates were extracted from electronic health record data from a large academic medical center using validated algorithms and concept sets. Logistic regression was performed to predict the likelihood of hospitalization and emergency department visit in the next year. Results: In all, 76,479 patients were eligible; the majority were White (89%), 54% were female, with mean age 73. Those with psychosocial factors were older, had higher baseline utilization, and more chronic illnesses. The 4 psychosocial factors all independently predicted future utilization (odds ratio=1.27–2.77, C-statistic=0.63). Accounting for demographics, specific conditions, and previous utilization, 3 of 4 of the extracted factors remained predictive (odds ratio=1.13–1.86) for future utilization. Compared with models with no psychosocial factors, they had improved discrimination. Individual predictions were mixed, with social isolation predicting depression and morbidity; stress predicting atherosclerotic cardiovascular disease onset; and housing insecurity predicting substance use disorder morbidity. Discussion: Psychosocial factors are known to have adverse health impacts, but are rarely measured; using natural language processing, we extracted factors that identified a higher risk segment of older adults with multimorbidity. Combining these extraction techniques with other measures of social determinants may help catalyze population health efforts to address psychosocial factors to mitigate their health impacts.

Improving ascertainment of suicidal ideation and suicide attempt with natural language processing

“…This NLP system can be applied to any unstructured clinical text common in EHRs and is feasible to apply at scale (~ 200 M notes here). This information retrieval approach would be portable to other health systems and has been used for the investigation of social determinants of health [13][14][15] . Clinical implications of this work include its potential to improve ascertainment of these important outcomes across heterogeneous medical systems.…”

“…Issues with ascertainment undermine accurate estimates of rates of suicidal outcomes, appropriate resource allocation, quality improvement, and risk assessment 2,5,6 .Like other behavioral health traits, alternative ascertainment approaches via patient self-report, health information exchange, public health surveillance, and natural language processing (NLP) have been tested to assess improvement from diagnostic codes [7][8][9][10][11][12] . The latter, NLP, has been used to improve ascertainment of social determinants of health to augment effective sample size for clinical modeling [13][14][15] .Suicidal ideation and suicide attempt share attributes common to clinical outcomes that lack biomarkers or reliable structured data representation. NLP provides a scalable means of extracting relevant signal to identify such outcomes using clinical unstructured text.…”

“…Like other behavioral health traits, alternative ascertainment approaches via patient self-report, health information exchange, public health surveillance, and natural language processing (NLP) have been tested to assess improvement from diagnostic codes [7][8][9][10][11][12] . The latter, NLP, has been used to improve ascertainment of social determinants of health to augment effective sample size for clinical modeling [13][14][15] .…”

Psychosocial Data

“…Dorr and colleagues have developed an NLP system to extract 4 psychosocial factors from clinical notes and conducted a preliminary evaluation which suggests that all 4 factors were predictive of future health care utilization 2. Their study within a single academic medical center should prompt further testing and refinement using data from other health systems, alternative study designs, and additional health and social outcomes.…”

“…Dorr and colleagues have developed an NLP system to extract 4 psychosocial factors from clinical notes and conducted a preliminary evaluation which suggests that all 4 factors were predictive of future health care utilization. 2 Their study within a single academic medical center should prompt further testing and refinement using data from other health systems, alternative study designs, and additional health and social outcomes. To promote confidence in the validity of NLP systems and wider adoption, system performance should be benchmarked against gold standards using datasets where systematically collected structured psychosocial information is available.…”