Dataset Information

Clinical notes: An untapped opportunity for improving risk prediction for hospitalization and emergency department visit during home health care.

ABSTRACT:

Background/objective

Between 10 and 25% patients are hospitalized or visit emergency department (ED) during home healthcare (HHC). Given that up to 40% of these negative clinical outcomes are preventable, early and accurate prediction of hospitalization risk can be one strategy to prevent them. In recent years, machine learning-based predictive modeling has become widely used for building risk models. This study aimed to compare the predictive performance of four risk models built with various data sources for hospitalization and ED visits in HHC.

Methods

Four risk models were built using different variables from two data sources: structured data (i.e., Outcome and Assessment Information Set (OASIS) and other assessment items from the electronic health record (EHR)) and unstructured narrative-free text clinical notes for patients who received HHC services from the largest non-profit HHC organization in New York between 2015 and 2017. Then, five machine learning algorithms (logistic regression, Random Forest, Bayesian network, support vector machine (SVM), and Naïve Bayes) were used on each risk model. Risk model performance was evaluated using the F-score and Precision-Recall Curve (PRC) area metrics.

Results

During the study period, 8373/86,823 (9.6%) HHC episodes resulted in hospitalization or ED visits. Among five machine learning algorithms on each model, the SVM showed the highest F-score (0.82), while the Random Forest showed the highest PRC area (0.864). Adding information extracted from clinical notes significantly improved the risk prediction ability by up to 16.6% in F-score and 17.8% in PRC.

Conclusion

All models showed relatively good hospitalization or ED visit risk predictive performance in HHC. Information from clinical notes integrated with the structured data improved the ability to identify patients at risk for these emergent care events.

SUBMITTER: Song J

PROVIDER: S-EPMC9825202 | biostudies-literature | 2022 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Clinical notes: An untapped opportunity for improving risk prediction for hospitalization and emergency department visit during home health care.

Song Jiyoun J Hobensack Mollie M Bowles Kathryn H KH McDonald Margaret V MV Cato Kenrick K Rossetti Sarah Collins SC Chae Sena S Kennedy Erin E Barrón Yolanda Y Sridharan Sridevi S Topaz Maxim M

Journal of biomedical informatics 20220226

<h4>Background/objective</h4>Between 10 and 25% patients are hospitalized or visit emergency department (ED) during home healthcare (HHC). Given that up to 40% of these negative clinical outcomes are preventable, early and accurate prediction of hospitalization risk can be one strategy to prevent them. In recent years, machine learning-based predictive modeling has become widely used for building risk models. This study aimed to compare the predictive performance of four risk models built with v ...[more]

PMID: 35231649

Similar Datasets

Project description:BackgroundAbout one in five patients receiving home healthcare (HHC) services are hospitalized or visit an emergency department (ED) during a home care episode. Early identification of at-risk patients can prevent these negative outcomes. However, risk indicators, including language in clinical notes that indicate a concern about a patient, are often hidden in narrative documentation throughout their HHC episode.ObjectiveThe aim of the study was to develop an automated natural language processing (NLP) algorithm to identify concerning language indicative of HHC patients' risk of hospitalizations or ED visits.MethodsThis study used the Omaha System-a standardized nursing terminology that describes problems/signs/symptoms that can occur in the community setting. First, five HHC experts iteratively reviewed the Omaha System and identified concerning concepts indicative of HHC patients' risk of hospitalizations or ED visits. Next, we developed and tested an NLP algorithm to identify these concerning concepts in HHC clinical notes automatically. The resulting NLP algorithm was applied on a large subset of narrative notes (2.3 million notes) documented for 66,317 unique patients ( n = 87,966 HHC episodes) admitted to one large HHC agency in the Northeast United States between 2015 and 2017.ResultsA total of 160 Omaha System signs/symptoms were identified as concerning concepts for hospitalizations or ED visits in HHC. These signs/symptoms belong to 31 of the 42 available Omaha System problems. Overall, the NLP algorithm showed good performance in identifying concerning concepts in clinical notes. More than 18% of clinical notes were detected as having at least one concerning concept, and more than 90% of HHC episodes included at least one Omaha System problem. The most frequently documented concerning concepts were pain, followed by issues related to neuromusculoskeletal function, circulation, mental health, and communicable/infectious conditions.ConclusionOur findings suggest that concerning problems or symptoms that could increase the risk of hospitalization or ED visit were frequently documented in narrative clinical notes. NLP can automatically extract information from narrative clinical notes to improve our understanding of care needs in HHC. Next steps are to evaluate which concerning concepts identified in clinical notes predict hospitalization or ED visit.

Project description:ImportanceTrauma of hospitalization refers to the depersonalizing and stressful experience of a hospital admission and is hypothesized to increase the risk of readmission after discharge.ObjectivesTo characterize the trauma of hospitalization by measuring patient-reported disturbances in sleep, mobility, nutrition, and mood among medical inpatients, and to examine the association between these disturbances and the risk of unplanned return to hospital after discharge.Design, setting, and participantsThis prospective cohort study enrolled participants between September 1, 2016, and September 1, 2017, at 2 academic hospitals in Toronto, Canada. Participants were adults admitted to the internal medicine ward for more than 48 hours. Participants were interviewed before discharge using a standardized questionnaire to assess sleep, mobility, nutrition, and mood. Responses for each domain were dichotomized as disturbance or no disturbance. Disturbance in 3 or 4 domains (the upper tertile) was considered high trauma of hospitalization, and disturbance in 0 to 2 domains (the lower 2 tertiles) was considered low trauma.Main outcome and measuresThe primary outcome was readmission or emergency department visit within 30 days of discharge. The association between trauma of hospitalization and the primary outcome was examined using logistic regression, adjusted for age; sex; length of stay; Charlson Comorbidity Index Score; Laboratory-Based Acute Physiology Score; and baseline disturbances in sleep, mobility, nutrition, and mood.ResultsA total of 207 patients participated, of whom 82 (39.6%) were women and 125 (60.4%) were men, with a mean (SD) age of 60.3 (16.8) years. Among the 207 participants, 75 (36.2%) reported sleep disturbance, 162 (78.3%) reported mobility disturbance, 114 (55.1%) reported nutrition disturbance, and 48 (23.2%) reported mood disturbance. Nearly all participants (192 [92.8%]) described a disturbance in at least 1 domain, and 61 participants (29.5%) had high trauma exposure. A statistically significant 15.8% greater absolute risk of readmission or emergency department visit was found in participants with high trauma (37.7%; 95% CI, 25.9%-51.1%) compared with those with low trauma (21.9%; 95% CI, 15.7%-29.7%), which remained statistically significant after adjusting for baseline characteristics (adjusted odds ratio, 2.52; 95% CI, 1.24-5.17; P = .01) and propensity score matching (odds ratio, 2.47; 95% CI, 1.11-5.73; P = .03).Conclusions and relevanceDisturbances in sleep, mobility, nutrition, and mood were common in medical inpatients; such trauma of hospitalization may be associated with a greater risk of 30-day readmission or emergency department visit after hospital discharge.

Project description:BackgroundAn increasing number of falls among community-living older adults are reported in emergency calls. Data on evidence of appropriate fall prevention interventions are limited and challenges in recruiting this population in randomized trials are acknowledged.PurposeThe main aim of this study was to provide demographic data, circumstance and fall-related outcomes of the population in the RISING-DOM study [Impact d'une évaluation des facteurs de RISque de chute et d'une prise en charge personnalisée, sur la mortalité et l'institutionnalisation, après INtervention du SAMU chez la personne âGée à DOMicile], a multicenter, randomized interventional trial involving community-dwelling older adults who have experienced a fall at home and were not hospitalized. Additionally, the challenges of remote recruitment in this population were discussed.Patients and methodsParticipants were identified through the Occitania Emergency Observatory database. Participant recruitment and data collection were performed through telephone interviews (October 2019-March 2022). Additionally, a sample survey of Emergency Medical Services calls was carried out.ResultsOut of the 1151 individuals screened, a total of 951 participants were included in the trial follow-up, resulting in an acceptance rate of 82.62%. The screening delay was extended due to the COVID-19 pandemic. Recruiting difficulties were mainly related to identifying potential participants, unavailable contact information and unreachability. Participants' mean age was 84.1 years, 65.8% were women, and 44.3% lived alone. Pain was the most frequent outcome (53%). In the previous year, 73.5% of participants reported experiencing a fall, with 66.7% of those falls requiring assistance from Emergency Medical Services (EMS). Nearly, 40% did not take proactive steps to prevent future falls and walking aids (79.8%) were the most common preventive action.ConclusionIndicators of a high-risk group of falls have been identified underscoring the need for appropriate fall interventions in the target population. Challenges of large sampling for randomized fall prevention trials were provided.Trial registrationClinicaltrials.gov identifier: NCT04132544. Registration date: 18/10/2019. https://www.clinicaltrials.gov/ct2/show/NCT04132544?term=rising-dom&draw=2&rank=1.

Project description:BackgroundHome care (HC) is a critical component of the ongoing restructuring of healthcare in Canada. It impacts three dimensions of healthcare delivery: primary healthcare, chronic disease management, and aging at home strategies. The purpose of our study is to investigate a significant safety dimension of HC, the occurrence of adverse events and their related outcomes. The study reports on the incidence of HC adverse events, the magnitude of the events, the types of events that occur, and the consequences experienced by HC clients in the province of Ontario.MethodsA retrospective cohort design was used, utilizing comprehensive secondary databases available for Ontario HC clients from the years 2008 and 2009. The data were derived from the Canadian Home Care Reporting System, the Hospital Discharge Abstract Database, the National Ambulatory Care Reporting System, the Ontario Mental Health Reporting System, and the Continuing Care Reporting System. Descriptive analysis was used to identify the type and frequency of the adverse events recorded and the consequences of the events. Logistic regression analysis was used to examine the association between the events and their consequences.ResultsThe study found that the incident rate for adverse events for the HC clients included in the cohort was 13%. The most frequent adverse events identified in the databases were injurious falls, injuries from other than a fall, and medication-related incidents. With respect to outcomes, we determined that an injurious fall was associated with a significant increase in the odds of a client requiring long-term-care facility admission and of client death. We further determined that three types of events, delirium, sepsis, and medication-related incidents were associated directly with an increase in the odds of client death.ConclusionsOur study concludes that 13% of clients in homecare experience an adverse event annually. We also determined that an injurious fall was the most frequent of the adverse events and was associated with increased admission to long-term care or death. We recommend the use of tools that are presently available in Canada, such as the Resident Assessment Instrument and its Clinical Assessment Protocols, for assessing and mitigating the risk of an adverse event occurring.

Dataset Information

Clinical notes: An untapped opportunity for improving risk prediction for hospitalization and emergency department visit during home health care.

Background/objective

Methods

Results

Conclusion

Publications

Clinical notes: An untapped opportunity for improving risk prediction for hospitalization and emergency department visit during home health care.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets