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

Enhancing readmission prediction models by integrating insights from home healthcare notes: Retrospective cohort study

BACKGROUND

Hospital readmission is an important indicator of inpatient care quality and a significant driver of increasing medical costs. Therefore, it is important to explore the effects of postdischarge information, particularly from home healthcare notes, on enhancing readmission prediction models. Despite the use of Natural Language Processing (NLP) and machine learning in prediction model development, current studies often overlook insights from home healthcare notes.

OBJECTIVE

This study aimed to develop prediction models for 30-day readmissions using home healthcare notes and structured data. In addition, it explored the development of 14- and 180-day prediction models using variables in the 30-day model.

DESIGN

A retrospective observational cohort study.

SETTING(S)

This study was conducted at Ajou University School of Medicine in South Korea.

PARTICIPANTS

Data from electronic health records, encompassing demographic characteristics of 1819 participants, along with information on conditions, drug, and home healthcare, were utilized.

METHODS

Two distinct models were developed for each prediction window (30-, 14-, 180-day): the traditional model, which utilized structured variables alone, and the common data model (CDM)-NLP model, which incorporated structured and topic variables extracted from home healthcare notes. BERTopic facilitated topic generation and risk probability, representing the likelihood of documents being assigned to specific topics. Feature selection involved experimenting with various algorithms. The best-performing algorithm, determined using the area under the receiver operating characteristic curve (AUROC), was used for model development. Model performance was assessed using various learning metrics including AUROC.

RESULTS

Among 1819 patients, 251 (13.80 %) experienced 30-day readmission. The least absolute shrinkage and selection operator was used for feature extraction and model development. The 15 structured features were used in the traditional model. Moreover, five additional topic variables from the home healthcare notes were applied in the CDM-NLP model. The AUROC of the traditional model was 0.739 (95 % CI: 0.672-0.807). The AUROC of the CDM-NLP model was high at 0.824 (95 % CI: 0.768-0.880), which indicated an outstanding performance. The topics in the CDM-NLP model included emotional distress, daily living functions, nutrition, postoperative status, and cardiorespiratory issues. In extended prediction model development for 14- and 180-day readmissions, the CDM-NLP consistently outperformed the traditional model.

CONCLUSIONS

This study developed effective prediction models using both structured and unstructured data, thereby emphasizing the significance of postdischarge information from home healthcare notes in readmission prediction.

Does synthetic data augmentation improve the performances of machine learning classifiers for identifying health problems in patient-nurse verbal communications in home healthcare settings?

BACKGROUND

Identifying health problems in audio-recorded patient-nurse communication is important to improve outcomes in home healthcare patients who have complex conditions with increased risks of hospital utilization. Training machine learning classifiers for identifying problems requires resource-intensive human annotation.

OBJECTIVE

To generate synthetic patient-nurse communication and to automatically annotate for common health problems encountered in home healthcare settings using GPT-4. We also examined whether augmenting real-world patient-nurse communication with synthetic data can improve the performance of machine learning to identify health problems.

DESIGN

Secondary data analysis of patient-nurse verbal communication data in home healthcare settings.

METHODS

The data were collected from one of the largest home healthcare organizations in the United States. We used 23 audio recordings of patient-nurse communications from 15 patients. The audio recordings were transcribed verbatim and manually annotated for health problems (e.g., circulation, skin, pain) indicated in the Omaha System Classification scheme. Synthetic data of patient-nurse communication were generated using the in-context learning prompting method, enhanced by chain-of-thought prompting to improve the automatic annotation performance. Machine learning classifiers were applied to three training datasets: real-world communication, synthetic communication, and real-world communication augmented by synthetic communication.

RESULTS

Average F1 scores improved from 0.62 to 0.63 after training data were augmented with synthetic communication. The largest increase was observed using the XGBoost classifier where F1 scores improved from 0.61 to 0.64 (about 5% improvement). When trained solely on either real-world communication or synthetic communication, the classifiers showed comparable F1 scores of 0.62-0.61, respectively.

CONCLUSION

Integrating synthetic data improves machine learning classifiers' ability to identify health problems in home healthcare, with performance comparable to training on real-world data alone, highlighting the potential of synthetic data in healthcare analytics.

CLINICAL RELEVANCE

This study demonstrates the clinical relevance of leveraging synthetic patient-nurse communication data to enhance machine learning classifier performances to identify health problems in home healthcare settings, which will contribute to more accurate and efficient problem identification and detection of home healthcare patients with complex health conditions.

Natural Language Processing Applied to Clinical Documentation in Post-acute Care Settings: A Scoping Review

OBJECTIVES

To determine the scope of the application of natural language processing to free-text clinical notes in post-acute care and provide a foundation for future natural language processing-based research in these settings.

DESIGN

Scoping review; reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines.

SETTING AND PARTICIPANTS

Post-acute care (ie, home health care, long-term care, skilled nursing facilities, and inpatient rehabilitation facilities).

METHODS

PubMed, Cumulative Index of Nursing and Allied Health Literature, and Embase were searched in February 2023. Eligible studies had quantitative designs that used natural language processing applied to clinical documentation in post-acute care settings. The quality of each study was appraised.

RESULTS

Twenty-one studies were included. Almost all studies were conducted in home health care settings. Most studies extracted data from electronic health records to examine the risk for negative outcomes, including acute care utilization, medication errors, and suicide mortality. About half of the studies did not report age, sex, race, or ethnicity data or use standardized terminologies. Only 8 studies included variables from socio-behavioral domains. Most studies fulfilled all quality appraisal indicators.

CONCLUSIONS AND IMPLICATIONS

The application of natural language processing is nascent in post-acute care settings. Future research should apply natural language processing using standardized terminologies to leverage free-text clinical notes in post-acute care to promote timely, comprehensive, and equitable care. Natural language processing could be integrated with predictive models to help identify patients who are at risk of negative outcomes. Future research should incorporate socio-behavioral determinants and diverse samples to improve health equity in informatics tools.

Social Risk Factors are Associated with Risk for Hospitalization in Home Health Care: A Natural Language Processing Study

OBJECTIVE

This study aimed to develop a natural language processing (NLP) system that identified social risk factors in home health care (HHC) clinical notes and to examine the association between social risk factors and hospitalization or an emergency department (ED) visit.

DESIGN

Retrospective cohort study.

SETTING AND PARTICIPANTS

We used standardized assessments and clinical notes from one HHC agency located in the northeastern United States. This included 86,866 episodes of care for 65,593 unique patients. Patients received HHC services between 2015 and 2017.

METHODS

Guided by HHC experts, we created a vocabulary of social risk factors that influence hospitalization or ED visit risk in the HHC setting. We then developed an NLP system to automatically identify social risk factors documented in clinical notes. We used an adjusted logistic regression model to examine the association between the NLP-based social risk factors and hospitalization or an ED visit.

RESULTS

On the basis of expert consensus, the following social risk factors emerged: Social Environment, Physical Environment, Education and Literacy, Food Insecurity, Access to Care, and Housing and Economic Circumstances. Our NLP system performed "very good" with an F score of 0.91. Approximately 4% of clinical notes (33% episodes of care) documented a social risk factor. The most frequently documented social risk factors were Physical Environment and Social Environment. Except for Housing and Economic Circumstances, all NLP-based social risk factors were associated with higher odds of hospitalization and ED visits.

CONCLUSIONS AND IMPLICATIONS

HHC clinicians assess and document social risk factors associated with hospitalizations and ED visits in their clinical notes. Future studies can explore the social risk factors documented in HHC to improve communication across the health care system and to predict patients at risk for being hospitalized or visiting the ED.

Future advancement of health care through standardized nursing terminologies: reflections from a Friends of the National Library of Medicine workshop honoring Virginia K. Saba

OBJECTIVE

To honor the legacy of nursing informatics pioneer and visionary, Dr. Virginia Saba, the Friends of the National Library of Medicine convened a group of international experts to reflect on Dr. Saba's contributions to nursing standardized nursing terminologies.

PROCESS

Experts led a day-and-a-half virtual update on nursing's sustained and rigorous efforts to develop and use valid, reliable, and computable standardized nursing terminologies over the past 5 decades. Over the course of the workshop, policymakers, industry leaders, and scholars discussed the successful use of standardized nursing terminologies, the potential for expanded use of these vetted tools to advance healthcare, and future needs and opportunities. In this article, we elaborate on this vision and key recommendations for continued and expanded adoption and use of standardized nursing terminologies across settings and systems with the goal of generating new knowledge that improves health.

CONCLUSION

Much of the promise that the original creators of standardized nursing terminologies envisioned has been achieved. Secondary analysis of clinical data using these terminologies has repeatedly demonstrated the value of nursing and nursing's data. With increased and widespread adoption, these achievements can be replicated across settings and systems.

FHIR-up! Advancing knowledge from clinical data through application of standardized nursing terminologies within HL7® FHIR®

Health Level 7®'s (HL7) Fast Healthcare Interoperability Resources® (FHIR®) is leading new efforts to make data available to healthcare clinicians, administrators, and leaders. Standardized nursing terminologies were developed to enable nursing's voice and perspective to be visible within the healthcare data ecosystem. The use of these SNTs has been shown to improve care quality and outcomes, and to provide data for knowledge discovery. The role of SNTs in describing assessments and interventions and measuring outcomes is unique in health care, and synergistic with the purpose and goals of FHIR. FHIR acknowledges nursing as a discipline of interest and yet the use of SNTs within the FHIR ecosystem is rare. The purpose of this article is to describe FHIR, SNTs, and the potential for synergy in the use of SNTs with FHIR. Toward improving understanding how FHIR works to transport and store knowledge and how SNTs work to convey meaning, we provide a framework and examples of SNTs and their coding for use within FHIR solutions. Finally, we offer recommendations for the next steps to advance FHIR-SNT collaboration. Such collaboration will advance both nursing specifically and health care in general, and most importantly, improve population health.

Uncovering hidden trends: identifying time trajectories in risk factors documented in clinical notes and predicting hospitalizations and emergency department visits during home health care

OBJECTIVE

This study aimed to identify temporal risk factor patterns documented in home health care (HHC) clinical notes and examine their association with hospitalizations or emergency department (ED) visits.

MATERIALS AND METHODS

Data for 73 350 episodes of care from one large HHC organization were analyzed using dynamic time warping and hierarchical clustering analysis to identify the temporal patterns of risk factors documented in clinical notes. The Omaha System nursing terminology represented risk factors. First, clinical characteristics were compared between clusters. Next, multivariate logistic regression was used to examine the association between clusters and risk for hospitalizations or ED visits. Omaha System domains corresponding to risk factors were analyzed and described in each cluster.

RESULTS

Six temporal clusters emerged, showing different patterns in how risk factors were documented over time. Patients with a steep increase in documented risk factors over time had a 3 times higher likelihood of hospitalization or ED visit than patients with no documented risk factors. Most risk factors belonged to the physiological domain, and only a few were in the environmental domain.

DISCUSSION

An analysis of risk factor trajectories reflects a patient's evolving health status during a HHC episode. Using standardized nursing terminology, this study provided new insights into the complex temporal dynamics of HHC, which may lead to improved patient outcomes through better treatment and management plans.

CONCLUSION

Incorporating temporal patterns in documented risk factors and their clusters into early warning systems may activate interventions to prevent hospitalizations or ED visits in HHC.

Predicting emergency department visits and hospitalizations for patients with heart failure in home healthcare using a time series risk model

OBJECTIVES

Little is known about proactive risk assessment concerning emergency department (ED) visits and hospitalizations in patients with heart failure (HF) who receive home healthcare (HHC) services. This study developed a time series risk model for predicting ED visits and hospitalizations in patients with HF using longitudinal electronic health record data. We also explored which data sources yield the best-performing models over various time windows.

MATERIALS AND METHODS

We used data collected from 9362 patients from a large HHC agency. We iteratively developed risk models using both structured (eg, standard assessment tools, vital signs, visit characteristics) and unstructured data (eg, clinical notes). Seven specific sets of variables included: (1) the Outcome and Assessment Information Set, (2) vital signs, (3) visit characteristics, (4) rule-based natural language processing-derived variables, (5) term frequency-inverse document frequency variables, (6) Bio-Clinical Bidirectional Encoder Representations from Transformers variables, and (7) topic modeling. Risk models were developed for 18 time windows (1-15, 30, 45, and 60 days) before an ED visit or hospitalization. Risk prediction performances were compared using recall, precision, accuracy, F1, and area under the receiver operating curve (AUC).

RESULTS

The best-performing model was built using a combination of all 7 sets of variables and the time window of 4 days before an ED visit or hospitalization (AUC = 0.89 and F1 = 0.69).

DISCUSSION AND CONCLUSION

This prediction model suggests that HHC clinicians can identify patients with HF at risk for visiting the ED or hospitalization within 4 days before the event, allowing for earlier targeted interventions.

Year 2022 in Medical Natural Language Processing: Availability of Language Models as a Step in the Democratization of NLP in the Biomedical Area

OBJECTIVES

To analyse the content of publications within the medical Natural Language Processing (NLP) domain in 2022.

METHODS

Automatic and manual preselection of publications to be reviewed, and selection of the best NLP papers of the year. Analysis of the important issues.

RESULTS

Three best papers have been selected. We also propose an analysis of the content of the NLP publications in 2022, stressing on some of the topics.

CONCLUSION

The main trend in 2022 is certainly related to the availability of large language models, especially those based on Transformers, and to their use by non-NLP researchers. This leads to the democratization of the NLP methods. We also observe the renewal of interest to languages other than English, the continuation of research on information extraction and prediction, the massive use of data from social media, and the consideration of needs and interests of patients.

Self-reported gaps in care coordination and preventable adverse outcomes among older adults receiving home health care

BACKGROUND

Older adults see multiple outpatient providers and increasingly use home health care (HHC) services. Previous studies attempting to draw inferences about the association between HHC use and patient outcomes have been mixed. Whether HHC is associated with care coordination and how both influence outcomes are unknown. In addition, prior studies have not taken the patient perspective into account. We examined the association between receiving HHC and self-reported gaps in care coordination and separately, preventable adverse outcomes.

METHODS

The analysis for this cross-sectional study was conducted between October 2021 and June 2022, using data on 4296 Medicare beneficiaries from the Reasons for Geographic and Racial Differences in Stroke (REGARDS) study who completed a survey on care coordination from 2017 to 2018. The associations between the receipt of HHC and two outcomes (a gap in care coordination, and separately, a preventable adverse event) were examined with Poisson models with robust standard errors. Potential confounders were accounted for through propensity score-based inverse probability weighting.

RESULTS

Among 4296 participants, 430 (10%) received HHC and they were older and had more comorbidities and ambulatory visits than those without HHC. HHC was not associated with differences in self-reported gaps in care coordination (33.3% HHC vs. 32.5% no-HHC, p = 0.70). HHC recipients reported more preventable drug-drug interactions (9.1% vs. 4.0%, p < 0.001) but not more preventable ED visits or hospital admissions. In IPW-adjusted models, HHC was not associated with gaps in care coordination (p = 0.60) but was associated with double the risk of a preventable adverse outcome (aRR 2.06; CI: 1.37, 3.10, p < 0.001).

CONCLUSIONS

HHC recipients were significantly more likely (than those without HHC) to report a potentially preventable adverse event (particularly a drug-drug interaction), suggesting an opportunity to improve patient safety by leveraging the observations of older adults receiving HHC.

The identification of clusters of risk factors and their association with hospitalizations or emergency department visits in home health care

AIMS

To identify clusters of risk factors in home health care and determine if the clusters are associated with hospitalizations or emergency department visits.

DESIGN

A retrospective cohort study.

METHODS

This study included 61,454 patients pertaining to 79,079 episodes receiving home health care between 2015 and 2017 from one of the largest home health care organizations in the United States. Potential risk factors were extracted from structured data and unstructured clinical notes analysed by natural language processing. A K-means cluster analysis was conducted. Kaplan-Meier analysis was conducted to identify the association between clusters and hospitalizations or emergency department visits during home health care.

RESULTS

A total of 11.6% of home health episodes resulted in hospitalizations or emergency department visits. Risk factors formed three clusters. Cluster 1 is characterized by a combination of risk factors related to "impaired physical comfort with pain," defined as situations where patients may experience increased pain. Cluster 2 is characterized by "high comorbidity burden" defined as multiple comorbidities or other risks for hospitalization (e.g., prior falls). Cluster 3 is characterized by "impaired cognitive/psychological and skin integrity" including dementia or skin ulcer. Compared to Cluster 1, the risk of hospitalizations or emergency department visits increased by 1.95 times for Cluster 2 and by 2.12 times for Cluster 3 (all p < .001).

CONCLUSION

Risk factors were clustered into three types describing distinct characteristics for hospitalizations or emergency department visits. Different combinations of risk factors affected the likelihood of these negative outcomes.

IMPACT

Cluster-based risk prediction models could be integrated into early warning systems to identify patients at risk for hospitalizations or emergency department visits leading to more timely, patient-centred care, ultimately preventing these events.

PATIENT OR PUBLIC CONTRIBUTION

There was no involvement of patients in developing the research question, determining the outcome measures, or implementing the study.

Machine learning applied to electronic health record data in home healthcare: A scoping review

OBJECTIVE

Despite recent calls for home healthcare (HHC) to integrate informatics, the application of machine learning in HHC is relatively unknown. Thus, this study aimed to synthesize and appraise the literature describing the application of machine learning to predict adverse outcomes (e.g., hospitalization, mortality) using electronic health record (EHR) data in the HHC setting. Our secondary aim was to evaluate the comprehensiveness of predictors used in the machine learning algorithms guided by the Biopsychosocial Model.

METHODS

During March 2022 we conducted a literature search in four databases: PubMed, Embase, CINAHL, and Scopus. Inclusion criteria were 1) describing services provided in the HHC setting, 2) applying machine learning algorithms to predict adverse outcomes, defined as outcomes related to patient deterioration, 3) using EHR data and 4) focusing on the adult population. Predictors were mapped to the Biopsychosocial Model. A risk of bias analysis was conducted using the Prediction Model Risk Of Bias Assessment Tool.

RESULTS

The final sample included 20 studies. Eighteen studies used predictors from standardized assessments integrated in the EHR. The most common outcome of interest was hospitalization (55%), followed by mortality (25%). Psychological predictors were frequently excluded (35%). Tree based algorithms were most frequently applied (75%). Most studies demonstrated high or unclear risk of bias (75%).

CONCLUSION

Future studies in HHC should consider incorporating machine learning algorithms into clinical decision support systems to identify patients at risk. Based on the Biopsychosocial model, psychological and interpersonal characteristics should be used along with biological characteristics to enhance risk prediction. To facilitate the widespread adoption of machine learning, stakeholders should encourage standardization in the HHC setting.