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.

Exploring the full potential of the electronic health record: the application of natural language processing for clinical practice.

The electronic health record contains valuable patient data and offers opportunities to administer and analyze patients' individual needs longitudinally. However, most information in the electronic health record is currently stored in unstructured text notations. Natural Language Processing (NLP), a branch of artificial intelligence that enables computers to understand, interpret, and generate human language, can be used to delve into unstructured text data to uncover valuable insights and knowledge. This article discusses different types of NLP, the potential of NLP for cardiovascular nursing, and how to get started with NLP as a clinician.

Relationship between hemoglobin and specific cognitive domain among older adults using network analysis.

OBJECTIVES: Hemoglobin (Hgb) is associated with cognitive function, with low and high levels of Hgb leading to impaired cerebral oxygenation and perfusion. Yet, current studies focused on understanding the association between Hgb and cognitive function without consideration for each cognitive domain. Thus, this study aims to identify and visualize potentially interactive associations between Hgb and specific cognitive domains among older adults. METHOD: This is a secondary data analysis using Wave II data from the National Social Life, Health, and Aging Project (NSHAP) and included 1022 older adults aged between 65 and 85 years. The network structure of three different models was estimated to understand the association between specific cognitive domains and Hgb in a mixed graphical model using the R-package 'mgm'. Model 1 did not adjust for any covariates, Model 2 adjusted for age and gender, and Model 3 adjusted for all covariates. RESULTS: Among all cognitive domains, the visuospatial (edge weight = 0.06-0.10) and memory domains (0.04-0.07) were associated with Hgb in all three models Though not present in Model 3, the attention domain was associated with Hgb in Model 1 and Model 2 (0.08-0.11). In addition, the predictability of Hgb was the highest (8.1%) in Model 3. CONCLUSION: Findings from this study suggest that cognition should be considered as a multidimensional construct, and its specific cognitive domain should be carefully assessed and managed in relation to Hgb among older adults.

Identifying stigmatizing language in clinical documentation: A scoping review of emerging literature.

BACKGROUND: Racism and implicit bias underlie disparities in health care access, treatment, and outcomes. An emerging area of study in examining health disparities is the use of stigmatizing language in the electronic health record (EHR). OBJECTIVES: We sought to summarize the existing literature related to stigmatizing language documented in the EHR. To this end, we conducted a scoping review to identify, describe, and evaluate the current body of literature related to stigmatizing language and clinician notes. METHODS: We searched PubMed, Cumulative Index of Nursing and Allied Health Literature (CINAHL), and Embase databases in May 2022, and also conducted a hand search of IEEE to identify studies investigating stigmatizing language in clinical documentation. We included all studies published through April 2022. The results for each search were uploaded into EndNote X9 software, de-duplicated using the Bramer method, and then exported to Covidence software for title and abstract screening. RESULTS: Studies (N = 9) used cross-sectional (n = 3), qualitative (n = 3), mixed methods (n = 2), and retrospective cohort (n = 1) designs. Stigmatizing language was defined via content analysis of clinical documentation (n = 4), literature review (n = 2), interviews with clinicians (n = 3) and patients (n = 1), expert panel consultation, and task force guidelines (n = 1). Natural language processing was used in four studies to identify and extract stigmatizing words from clinical notes. All of the studies reviewed concluded that negative clinician attitudes and the use of stigmatizing language in documentation could negatively impact patient perception of care or health outcomes. DISCUSSION: The current literature indicates that NLP is an emerging approach to identifying stigmatizing language documented in the EHR. NLP-based solutions can be developed and integrated into routine documentation systems to screen for stigmatizing language and alert clinicians or their supervisors. Potential interventions resulting from this research could generate awareness about how implicit biases affect communication patterns and work to achieve equitable health care for diverse populations.

Documentation of social determinants of health across individuals from different racial and ethnic groups in home healthcare.

INTRODUCTION: Home healthcare (HHC) enables patients to receive healthcare services within their homes to manage chronic conditions and recover from illnesses. Recent research has identified disparities in HHC based on race or ethnicity. Social determinants of health (SDOH) describe the external factors influencing a patient's health, such as access to care and social support. Individuals from racially or ethnically minoritized communities are known to be disproportionately affected by SDOH. Existing evidence suggests that SDOH are documented in clinical notes. However, no prior study has investigated the documentation of SDOH across individuals from different racial or ethnic backgrounds in the HHC setting. This study aimed to (1) describe frequencies of SDOH documented in clinical notes by race or ethnicity and (2) determine associations between race or ethnicity and SDOH documentation. DESIGN: Retrospective data analysis. METHODS: We conducted a cross-sectional secondary data analysis of 86,866 HHC episodes representing 65,693 unique patients from one large HHC agency in New York collected between January 1, 2015, and December 31, 2017. We reported the frequency of six SDOH (physical environment, social environment, housing and economic circumstances, food insecurity, access to care, and education and literacy) documented in clinical notes across individuals reported as Asian/Pacific Islander, Black, Hispanic, multi-racial, Native American, or White. We analyzed differences in SDOH documentation by race or ethnicity using logistic regression models. RESULTS: Compared to patients reported as White, patients across other racial or ethnic groups had higher frequencies of SDOH documented in their clinical notes. Our results suggest that race or ethnicity is associated with SDOH documentation in HHC. CONCLUSION: As the study of SDOH in HHC continues to evolve, our results provide a foundation to evaluate social information in the HHC setting and understand how it influences the quality of care provided. CLINICAL RELEVANCE: The results of this exploratory study can help clinicians understand the differences in SDOH across individuals from different racial and ethnic groups and serve as a foundation for future research aimed at fostering more inclusive HHC documentation practices.

Addressing bias in preterm birth research: The role of advanced imputation techniques for missing race and ethnicity in perinatal health data.

OBJECTIVES: To evaluate the effectiveness of Bayesian Improved Surname Geocoding (BISG) and Bayesian Improved First Name Surname Geocoding (BIFSG) in estimating race and ethnicity, and how they influence odds ratios for preterm birth. METHODS: We analyzed hospital birth admission electronic health records (EHR) data (N = 9985). We created two simulation sets with 40 % of race and ethnicity data missing randomly or more likely for non-Hispanic black birthing people who had preterm birth. We calculated C-statistics to evaluate how accurately BISG and BIFSG estimate race and ethnicity. We examined the association between race and ethnicity and preterm birth using logistic regression and reported odds ratios (OR). RESULTS: BISG and BIFSG showed high accuracy for most racial and ethnic categories (C-statistics = 0.94-0.97, 95 % confidence intervals [CI] = 0.92-0.97). When race and ethnicity were not missing at random, BISG (OR = 1.25, CI = 0.97-1.62) and BIFSG (OR = 1.38, CI = 1.08-1.76) resulted in positive estimates mirroring the true association (OR = 1.68, CI = 1.34-2.09) for Non-Hispanic Black birthing people, while traditional methods showed contrasting estimates (Complete case OR = 0.62, CI = 0.41-0.94; multiple imputation OR = 0.63, CI = 0.40-0.98). CONCLUSIONS: BISG and BIFSG accurately estimate missing race and ethnicity in perinatal EHR data, decreasing bias in preterm birth research, and are recommended over traditional methods to reduce potential bias.

Natural Language Processing to Identify Home Health Care Patients at Risk for Becoming Incapacitated With No Evident Advance Directives or Surrogates.

OBJECTIVES: Home health care patients who are at risk for becoming Incapacitated with No Evident Advance Directives or Surrogates (INEADS) may benefit from timely intervention to assist them with advance care planning. This study aimed to develop natural language processing algorithms for identifying home care patients who do not have advance directives, family members, or close social contacts who can serve as surrogate decision-makers in the event that they lose decisional capacity. DESIGN: Cross-sectional study of electronic health records. SETTING AND PARTICIPANTS: Patients receiving post-acute care discharge services from a large home health agency in New York City in 2019 (n = 45,390 enrollment episodes). METHODS: We developed a natural language processing algorithm for identifying information documented in free-text clinical notes (n = 1,429,030 notes) related to 4 categories: evidence of close relationships, evidence of advance directives, evidence suggesting lack of close relationships, and evidence suggesting lack of advance directives. We validated the algorithm against Gold Standard clinician review for 50 patients (n = 314 notes) to calculate precision, recall, and F-score. RESULTS: Algorithm performance for identifying text related to the 4 categories was excellent (average F-score = 0.91), with the best results for "evidence of close relationships" (F-score = 0.99) and the worst results for "evidence of advance directives" (F-score = 0.86). The algorithm identified 22% of all clinical notes (313,290 of 1,429,030) as having text related to 1 or more categories. More than 98% of enrollment episodes (48,164 of 49,141) included at least 1 clinical note containing text related to 1 or more categories. CONCLUSIONS AND IMPLICATIONS: This study establishes the feasibility of creating an automated screening algorithm to aid home health care agencies with identifying patients at risk of becoming INEADS. This screening algorithm can be applied as part of a multipronged approach to facilitate clinician support for advance care planning with patients at risk of becoming INEADS.

Developing a Personalized Meal Recommendation System for Chinese Older Adults: Observational Cohort Study.

BACKGROUND: China's older population is facing serious health challenges, including malnutrition and multiple chronic conditions. There is a critical need for tailored food recommendation systems. Knowledge graph-based food recommendations offer considerable promise in delivering personalized nutritional support. However, the integration of disease-based nutritional principles and preference-related requirements needs to be optimized in current recommendation processes. OBJECTIVE: This study aims to develop a knowledge graph-based personalized meal recommendation system for community-dwelling older adults and to conduct preliminary effectiveness testing. METHODS: We developed ElCombo, a personalized meal recommendation system driven by user profiles and food knowledge graphs. User profiles were established from a survey of 96 community-dwelling older adults. Food knowledge graphs were supported by data from websites of Chinese cuisine recipes and eating history, consisting of 5 entity classes: dishes, ingredients, category of ingredients, nutrients, and diseases, along with their attributes and interrelations. A personalized meal recommendation algorithm was then developed to synthesize this information to generate packaged meals as outputs, considering disease-related nutritional constraints and personal dietary preferences. Furthermore, a validation study using a real-world data set collected from 96 community-dwelling older adults was conducted to assess ElCombo's effectiveness in modifying their dietary habits over a 1-month intervention, using simulated data for impact analysis. RESULTS: Our recommendation system, ElCombo, was evaluated by comparing the dietary diversity and diet quality of its recommended meals with those of the autonomous choices of 96 eligible community-dwelling older adults. Participants were grouped based on whether they had a recorded eating history, with 34 (35%) having and 62 (65%) lacking such data. Simulation experiments based on retrospective data over a 30-day evaluation revealed that ElCombo's meal recommendations consistently had significantly higher diet quality and dietary diversity compared to the older adults' own selections (P<.001). In addition, case studies of 2 older adults, 1 with and 1 without prior eating records, showcased ElCombo's ability to fulfill complex nutritional requirements associated with multiple morbidities, personalized to each individual's health profile and dietary requirements. CONCLUSIONS: ElCombo has shown enhanced potential for improving dietary quality and diversity among community-dwelling older adults in simulation tests. The evaluation metrics suggest that the food choices supported by the personalized meal recommendation system surpass autonomous selections. Future research will focus on validating and refining ElCombo's performance in real-world settings, emphasizing the robust management of complex health data. The system's scalability and adaptability pinpoint its potential for making a meaningful impact on the nutritional health of older adults.

Using Natural Language Processing to Identify Home Health Care Patients at Risk for Diagnosis of Alzheimer's Disease and Related Dementias.

This study aimed to: (1) validate a natural language processing (NLP) system developed for the home health care setting to identify signs and symptoms of Alzheimer's disease and related dementias (ADRD) documented in clinicians' free-text notes; (2) determine whether signs and symptoms detected via NLP help to identify patients at risk of a new ADRD diagnosis within four years after admission. This study applied NLP to a longitudinal dataset including medical record and Medicare claims data for 56,652 home health care patients and Cox proportional hazard models to the subset of 24,874 patients admitted without an ADRD diagnosis. Selected ADRD signs and symptoms were associated with increased risk of a new ADRD diagnosis during follow-up, including: motor issues; hoarding/cluttering; uncooperative behavior; delusions or hallucinations; mention of ADRD disease names; and caregiver stress. NLP can help to identify patients in need of ADRD-related evaluation and support services.

A rapid review on current and potential uses of large language models in nursing.

BACKGROUND: The application of large language models across commercial and consumer contexts has grown exponentially in recent years. However, a gap exists in the literature on how large language models can support nursing practice, education, and research. This study aimed to synthesize the existing literature on current and potential uses of large language models across the nursing profession. METHODS: A rapid review of the literature, guided by Cochrane rapid review methodology and PRISMA reporting standards, was conducted. An expert health librarian assisted in developing broad inclusion criteria to account for the emerging nature of literature related to large language models. Three electronic databases (i.e., PubMed, CINAHL, and Embase) were searched to identify relevant literature in August 2023. Articles that discussed the development, use, and application of large language models within nursing were included for analysis. RESULTS: The literature search identified a total of 2028 articles that met the inclusion criteria. After systematically reviewing abstracts, titles, and full texts, 30 articles were included in the final analysis. Nearly all (93 %; n = 28) of the included articles used ChatGPT as an example, and subsequently discussed the use and value of large language models in nursing education (47 %; n = 14), clinical practice (40 %; n = 12), and research (10 %; n = 3). While the most common assessment of large language models was conducted by human evaluation (26.7 %; n = 8), this analysis also identified common limitations of large language models in nursing, including lack of systematic evaluation, as well as other ethical and legal considerations. DISCUSSION: This is the first review to summarize contemporary literature on current and potential uses of large language models in nursing practice, education, and research. Although there are significant opportunities to apply large language models, the use and adoption of these models within nursing have elicited a series of challenges, such as ethical issues related to bias, misuse, and plagiarism. CONCLUSION: Given the relative novelty of large language models, ongoing efforts to develop and implement meaningful assessments, evaluations, standards, and guidelines for applying large language models in nursing are recommended to ensure appropriate, accurate, and safe use. Future research along with clinical and educational partnerships is needed to enhance understanding and application of large language models in nursing and healthcare.

The ChatGPT Effect: Nursing Education and Generative Artificial Intelligence.

This article examines the potential of generative artificial intelligence (AI), such as ChatGPT (Chat Generative Pre-trained Transformer), in nursing education and the associated challenges and recommendations for their use. Generative AI offers potential benefits such as aiding students with assignments, providing realistic patient scenarios for practice, and enabling personalized, interactive learning experiences. However, integrating generative AI in nursing education also presents challenges, including academic integrity issues, the potential for plagiarism and copyright infringements, ethical implications, and the risk of producing misinformation. Clear institutional guidelines, comprehensive student education on generative AI, and tools to detect AI-generated content are recommended to navigate these challenges. The article concludes by urging nurse educators to harness generative AI's potential responsibly, highlighting the rewards of enhanced learning and increased efficiency. The careful navigation of these challenges and strategic implementation of AI is key to realizing the promise of AI in nursing education. [J Nurs Educ. 2024;63(X):XXX-XXX.].

Home Care Clinicians' Perspectives on Advance Care Planning for Patients at Risk for Becoming Incapacitated With No Evident Advance Directives or Surrogates.

Advance care planning is important and timely for patients receiving home health services; however, opportunities to facilitate awareness and engagement in this setting are often missed. This qualitative descriptive study elicited perspectives of home health nurses and social workers regarding barriers and facilitators to creating advance care plans in home health settings, with particular attention to patients with few familial or social contacts who can serve as surrogate decision-makers. We interviewed 15 clinicians employed in a large New York City-based home care agency in 2021-2022. Participants reported a multitude of barriers to supporting patients with advance care planning at the provider level (eg, lack of time and professional education, deferment, discomfort), patient level (lack of knowledge, mistrust, inadequate support, deferment, language barriers), and system level (eg, discontinuity of care, variations in advance care planning documents, legal concerns, lack of institutional protocols and centralized information). Participants noted that greater socialization and connection to existing educational resources regarding the intended purpose, scope, and applicability of advance directives could benefit home care patients.

Technological Challenges and Solutions in Emergency Remote Teaching for Nursing: An International Cross-Sectional Survey.

OBJECTIVES: With the sudden global shift to online learning modalities, this study aimed to understand the unique challenges and experiences of emergency remote teaching (ERT) in nursing education. METHODS: We conducted a comprehensive online international cross-sectional survey to capture the current state and firsthand experiences of ERT in the nursing discipline. Our analytical methods included a combination of traditional statistical analysis, advanced natural language processing techniques, latent Dirichlet allocation using Python, and a thorough qualitative assessment of feedback from open-ended questions. RESULTS: We received responses from 328 nursing educators from 18 different countries. The data revealed generally positive satisfaction levels, strong technological self-efficacy, and significant support from their institutions. Notably, the characteristics of professors, such as age (p = 0.02) and position (p = 0.03), influenced satisfaction levels. The ERT experience varied significantly by country, as evidenced by satisfaction (p = 0.05), delivery (p = 0.001), teacher-student interaction (p = 0.04), and willingness to use ERT in the future (p = 0.04). However, concerns were raised about the depth of content, the transition to online delivery, teacher-student interaction, and the technology gap. CONCLUSIONS: Our findings can help advance nursing education. Nevertheless, collaborative efforts from all stakeholders are essential to address current challenges, achieve digital equity, and develop a standardized curriculum for nursing education.

The ChatGPT effect and transforming nursing education with generative AI: Discussion paper.

AIM: The aim of this study is to present the possibilities of nurse education in the use of the Chat Generative Pre-training Transformer (ChatGPT) tool to support the documentation process. BACKGROUND: The success of the nursing process is based on the accuracy of nursing diagnoses, which also determine nursing interventions and nursing outcomes. Educating nurses in the use of artificial intelligence in the nursing process can significantly reduce the time nurses spend on documentation. DESIGN: Discussion paper. METHODS: We used a case study from Train4Health in the field of preventive care to demonstrate the potential of using Generative Pre-training Transformer (ChatGPT) to educate nurses in documenting the nursing process using generative artificial intelligence. Based on the case study, we entered a description of the patient's condition into Generative Pre-training Transformer (ChatGPT) and asked questions about nursing diagnoses, nursing interventions and nursing outcomes. We further synthesized these results. RESULTS: In the process of educating nurses about the nursing process and nursing diagnosis, Generative Pre-training Transformer (ChatGPT) can present potential patient problems to nurses and guide them through the process from taking a medical history, setting nursing diagnoses and planning goals and interventions. Generative Pre-training Transformer (ChatGPT) returned appropriate nursing diagnoses, but these were not in line with the North American Nursing Diagnosis Association - International (NANDA-I) classification as requested. Of all the nursing diagnoses provided, only one was consistent with the most recent version of the North American Nursing Diagnosis Association - International (NANDA-I). Generative Pre-training Transformer (ChatGPT) is still not specific enough for nursing diagnoses, resulting in incorrect answers in several cases. CONCLUSIONS: Using Generative Pre-training Transformer (ChatGPT) to educate nurses and support the documentation process is time-efficient, but it still requires a certain level of human critical-thinking and fact-checking.

Examining racial differences in the network structure and properties of specific cognitive domains among older adults.

Older adults oftentimes experience cognitive aging which leads to varying degrees of cognitive impairment. Previous studies have found that racial and ethnic disparities exist in the prevalence and severity of cognitive impairment among older adults. Yet, little is known on the relationship among specific cognitive domains and how this relationship differs between African American and White older adults. This is a secondary data analysis of Wave II (2010-2011) data from the National Social Life, Health, and Aging Project (NSHAP). A total of 2,471 older adults aged between 65 and 85 years old (African American n = 452, White n = 2019) were included. Network analysis was used to visualize and characterize the network structure and to examine network stability. Then, network comparison test was conducted to compare the network properties of the cognitive network structure between African American and White older adults. African American older adults had a lower cognitive function in all cognitive domains than White older adults. While there was no significant difference in global strength, there was a significant difference in the network structure and strength centrality measure between the two groups (p < 0.05). The invariance edge strength test found the language-visuospatial edge to be significantly stronger in African American older adults. Clinicians need to understand the different cognitive function across multiple cognitive domains between African American and White older adults and routinely offer targeted and timely cognitive assessment and management in this population.

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.

Utilizing patient-nurse verbal communication in building risk identification models: the missing critical data stream in home healthcare.

BACKGROUND: In the United States, over 12 000 home healthcare agencies annually serve 6+ million patients, mostly aged 65+ years with chronic conditions. One in three of these patients end up visiting emergency department (ED) or being hospitalized. Existing risk identification models based on electronic health record (EHR) data have suboptimal performance in detecting these high-risk patients. OBJECTIVES: To measure the added value of integrating audio-recorded home healthcare patient-nurse verbal communication into a risk identification model built on home healthcare EHR data and clinical notes. METHODS: This pilot study was conducted at one of the largest not-for-profit home healthcare agencies in the United States. We audio-recorded 126 patient-nurse encounters for 47 patients, out of which 8 patients experienced ED visits and hospitalization. The risk model was developed and tested iteratively using: (1) structured data from the Outcome and Assessment Information Set, (2) clinical notes, and (3) verbal communication features. We used various natural language processing methods to model the communication between patients and nurses. RESULTS: Using a Support Vector Machine classifier, trained on the most informative features from OASIS, clinical notes, and verbal communication, we achieved an AUC-ROC = 99.68 and an F1-score = 94.12. By integrating verbal communication into the risk models, the F-1 score improved by 26%. The analysis revealed patients at high risk tended to interact more with risk-associated cues, exhibit more "sadness" and "anxiety," and have extended periods of silence during conversation. CONCLUSION: This innovative study underscores the immense value of incorporating patient-nurse verbal communication in enhancing risk prediction models for hospitalizations and ED visits, suggesting the need for an evolved clinical workflow that integrates routine patient-nurse verbal communication recording into the medical record.

Using Natural Language Processing to Identify Stigmatizing Language in Labor and Birth Clinical Notes.

INTRODUCTION: Stigma and bias related to race and other minoritized statuses may underlie disparities in pregnancy and birth outcomes. One emerging method to identify bias is the study of stigmatizing language in the electronic health record. The objective of our study was to develop automated natural language processing (NLP) methods to identify two types of stigmatizing language: marginalizing language and its complement, power/privilege language, accurately and automatically in labor and birth notes. METHODS: We analyzed notes for all birthing people > 20 weeks' gestation admitted for labor and birth at two hospitals during 2017. We then employed text preprocessing techniques, specifically using TF-IDF values as inputs, and tested machine learning classification algorithms to identify stigmatizing and power/privilege language in clinical notes. The algorithms assessed included Decision Trees, Random Forest, and Support Vector Machines. Additionally, we applied a feature importance evaluation method (InfoGain) to discern words that are highly correlated with these language categories. RESULTS: For marginalizing language, Decision Trees yielded the best classification with an F-score of 0.73. For power/privilege language, Support Vector Machines performed optimally, achieving an F-score of 0.91. These results demonstrate the effectiveness of the selected machine learning methods in classifying language categories in clinical notes. CONCLUSION: We identified well-performing machine learning methods to automatically detect stigmatizing language in clinical notes. To our knowledge, this is the first study to use NLP performance metrics to evaluate the performance of machine learning methods in discerning stigmatizing language. Future studies should delve deeper into refining and evaluating NLP methods, incorporating the latest algorithms rooted in deep learning.

An Examination of the Non-linear Relationship Between Cognition and Total Hemoglobin Among the Cognitively Normal Older Adults by Gender.

Objectives: This exploratory study aimed to identify the potential non-linear relationship between hemoglobin (Hgb) and cognition among cognitively normal older adults and how this relationship differs in terms of gender in generalized additive models (GAM). Methods: This is a secondary data analysis using Wave II (2010-2011) data from the National Social Life, Health, and Aging Project. A generalized additive model was used to understand the non-linear relationship between Hgb and cognition, and to identify critical Hgb point related to cognition. Results: While both genders had a non-linear association between Hgb and cognition, the degree of non-linearity was more pronounced in male older adults with EDF value close to 2. The inflection point of 15.10 g/dL for male older adults and inflection point of 11.72 g/dL for female older adults were obtained. Conclusion: Further studies are needed to validate these results and develop precision medicine approaches to integrate these results into clinical practice.