Investigating perceptions and attitude toward telenursing among undergraduate nursing students for the future of nursing education: a cross-sectional study.

BACKGROUND: Telenursing is poised to emerge as a novel healthcare delivery system in the digital age. Hence, understanding nursing students' perspectives and readiness is pivotal for its effective implementation. This study investigated nursing students' perceptions regarding, and attitudes toward, telenursing and the factors that influenced their attitudes based on the technology acceptance model. METHODS: This study used a cross-sectional descriptive approach. The participants consisted of 188 nursing students (first to fourth year) enrolled in the College of Nursing in Korea. Differences in attitudes toward telenursing were analyzed using independent t-test and one-way analysis of variance. Pearson's correlation coefficient was used to examine the correlations between the main variables. Factors that influenced attitudes toward telenursing were analyzed using multiple regression. RESULTS: Of the participants, 65.4% lacked substantial awareness of telenursing and 19.1% had prior telenursing experience. Although prospects on telenursing indicated that 90.4% had an optimistic view, face-to-face nursing was heavily preferred for both satisfactory and favored healthcare delivery. Many cited the Internet as their source of knowledge, and only 18.6% had received telenursing education. Attitude toward telenursing was significantly more positive among those with experience of telenursing, telenursing observation in clinical practice, and telenursing education exposure. The regression model was statistically significant (F = 67.445, p < .000). Factors, such as perceived usefulness, social influence, innovativeness, and self-efficacy, influenced attitudes toward telenursing. CONCLUSIONS: Nursing students exhibited a lack of substantial awareness of telenursing; however, they simultaneously displayed a positive outlook. This lack of comprehensive understanding could stem from the absence of formal education in telenursing. Understanding and utilizing the potential of telenursing could be significantly aided by nursing students' education and knowledge. Thus, it is necessary to include telenursing education in the nursing curriculum. The skills and knowledge required for telenursing clinical practice can be developed through telenursing education. Such preparedness will affect nurses' attitudes and intentions and the quality of telenursing offered to patients in the future.

Navigating the Landscape of Telemedicine Research: A Topic Modeling Approach for the Present and Future.

Introduction: Telemedicine, which is the provision of remote clinical services via telecommunication technology, has undergone an upsurge since the COVID-19 pandemic. To capture this paradigm, this study surveyed telemedicine literature, including postpandemic publications, to identify dominant research themes and temporal trends and suggest directions for future research. Methods: A corpus of 56,445 telemedicine studies is sourced from PubMed. Latent Dirichlet allocation (LDA) topic modeling performed using the Konstanz Information Miner platform. The textual data for topic modeling were processed by following standard procedures for natural language processing. Moreover, the term frequency-inverse document frequency approach was used to capture the importance of words within the corpus. We assessed perplexity, coherence, and the elbow method to determine the optimal number of topics for modeling. Results: The findings confirm the surge in telemedicine research after 2020, signifying its prominence. LDA topic modeling reveals seven distinct research themes, with the most prominent topic being "patient satisfaction" (21.38%) followed by "perspectives and challenges" (17.95%), and "smartphone apps" (14.32%). Furthermore, the results demonstrate a noticeable shift in topics from screening to therapeutic applications of telemedicine. Conclusions: This study serves as a guide for a broad range of telemedicine research topics. This synthesis of themes reflects the commitment of scholars to address the changing dynamics and health care needs, such as the COVID-19 pandemic, aging in place, smartphone usage, and technological advancement. The analysis also reveals flexible research responses to policy and contextual shifts, highlighting the collective drive to broaden the application of telemedicine in community health care.

Health Information Technology Adoption at U.S. Home Health Care Agencies: Results from a Multi-Methods Study.

Health information technology (HIT) holds potential to transform Home Health Care (HHC), yet, little is known about its adoption in this setting. In the context of infection prevention and control, we aimed to: (1) describe challenges associated with the adoption of HIT, for example, electronic health records (EHR) and telehealth and (2) examine HHC agency characteristics associated with HIT adoption. We conducted in-depth interviews with 41 staff from 13 U.S. HHC agencies (May-October 2018), then surveyed a stratified random sample of 1506 agencies (November 2018-December 2019), of which 35.6% participated (N = 536 HHC agencies). We applied analytic weights, generating nationally-representative estimates, and computed descriptive statistics, bivariate and multivariable analyses. Four themes were identified: (1) Reflections on providing HHC without EHR; (2) Benefits of EHR; (3) Benefits of other HIT; (4) Challenges with HIT and EHR. Overall, 10% of the agencies did not have an EHR; an additional 2% were in the process of acquiring one. Sixteen percent offered telehealth, and another 4% were in the process of acquiring telehealth services. In multivariable analysis, EHR use varied significantly by geographic location and ownership, and telehealth use varied by geographic location, ownership, and size. Although HIT use has increased, our results indicate that many HHC agencies still lack the HIT needed to implement technological solutions to improve workflow and quality of care. Future research should examine the impact of HIT on patient outcomes and the impact of the COVID-19 pandemic on HIT use in HHC.

Types and Effects of Telenursing in Home Health Care: A Systematic Review and Meta-Analysis.

Purpose: This systematic review aimed to identify the types and effectiveness of telenursing in home health care (HHC) compared to conventional HHC. Methods: This study followed the Preferred Reporting Items for Systematic Review and Meta-Analysis 2020 guidelines. A random-effects meta-analysis was performed. The risk of bias was assessed using the Risk of Bias 2.0 tool. The quality of bias was evaluated using the Grading of Recommendations Assessment, Development, and Evaluation system. Results: A total of 17 studies published between 2003 and 2022 were included in the review. The majority of the targeted health conditions of the patients were chronic obstructive pulmonary disease or congestive heart failure (70%). We categorized telenursing interventions according to different technology (N = 4) and nursing (N = 7) types. Among the identified types of nursing, fundamental nursing to monitor patients' symptoms was the most representative. Telemonitoring was found to be the most common technology type, followed by synchronous technology using video or telephone. The telenursing outcomes, including health care utilization, physiological/psychological outcomes, and quality of life, varied. In the meta-analysis, participants who received telenursing reported fewer hospital admissions (standardized mean difference [SMD]: -0.18; confidence interval [95% CI]: -0.43 to -0.02) and emergency department visits (SMD: -0.28; 95% CI: -0.45 to -0.10). Conclusion: Telenursing in HHC tends to improve the quality of life and could result in many benefits, including a reduction in health care utilization and facilitating the management of chronic diseases. These results ultimately represent the potential effectiveness of telenursing in community health care settings.

Development and evaluation of a problem-based learning simulation module for home-visit nursing.

OBJECTIVES: Although home-visit healthcare programs in Korea are expected to expand, providing hands-on experience to nursing students may be limited. This study aimed to develop and evaluate a problem-based learning (PBL) simulation module that reflects home-visit healthcare services provided by public health centers for pre-frail older adults. DESIGN AND SAMPLE: The simulation module, including PBL as prebriefing, was developed by the researchers and revised based on expert reviews. The module was evaluated using a mixed-method embedded one-group post-test-only design with focus group interviews (FGIs). Quantitative data (n = 29) were collected between April and June, 2021. FGIs (n = 10) were conducted twice in June 2021, and qualitative data were analyzed using an inductive content analysis approach. RESULTS: The average score of the Simulation Design Scale was 4.67 ± 0.36. The overall mean score of the Educational Practices Questionnaire was 4.75 ± 0.37. Three themes emerged from the FGIs: immersive learning experience, changes in perspective on nursing, and enhanced nursing competency. CONCLUSION: This PBL-based simulation module was evaluated as a systematic learning process in which nursing students could become self-directed learners, interacting and collaborating with colleagues, instructors, and environments. The module encourages them to practice home visit services.

Developing a Classification Algorithm for Prediabetes Risk Detection From Home Care Nursing Notes: Using Natural Language Processing.

This study developed and validated a rule-based classification algorithm for prediabetes risk detection using natural language processing from home care nursing notes. First, we developed prediabetes-related symptomatic terms in English and Korean. Second, we used natural language processing to preprocess the notes. Third, we created a rule-based classification algorithm with 31 484 notes, excluding 315 instances of missing data. The final algorithm was validated by measuring accuracy, precision, recall, and the F1 score against a gold standard testing set (400 notes). The developed terms comprised 11 categories and 1639 words in Korean and 1181 words in English. Using the rule-based classification algorithm, 42.2% of the notes comprised one or more prediabetic symptoms. The algorithm achieved high performance when applied to the gold standard testing set. We proposed a rule-based natural language processing algorithm to optimize the classification of the prediabetes risk group, depending on whether the home care nursing notes contain prediabetes-related symptomatic terms. Tokenization based on white space and the rule-based algorithm were brought into effect to detect the prediabetes symptomatic terms. Applying this algorithm to electronic health records systems will increase the possibility of preventing diabetes onset through early detection of risk groups and provision of tailored intervention.

Natural Language Processing of Nursing Notes: An Integrative Review.

Natural language processing includes a variety of techniques that help to extract meaning from narrative data. In healthcare, medical natural language processing has been a growing field of study; however, little is known about its use in nursing. We searched PubMed, EMBASE, and CINAHL and found 689 studies, narrowed to 43 eligible studies using natural language processing in nursing notes. Data related to the study purpose, patient population, methodology, performance evaluation metrics, and quality indicators were extracted for each study. The majority (86%) of the studies were conducted from 2015 to 2021. Most of the studies (58%) used inpatient data. One of four studies used data from open-source databases. The most common standard terminologies used were the Unified Medical Language System and Systematized Nomenclature of Medicine, whereas nursing-specific standard terminologies were used only in eight studies. Full system performance metrics (eg, F score) were reported for 61% of applicable studies. The overall number of nursing natural language processing publications remains relatively small compared with the other medical literature. Future studies should evaluate and report appropriate performance metrics and use existing standard nursing terminologies to enable future scalability of the methods and findings.

Military Doctors' and Nurses' Perceptions of Telemedicine and the Factors Affecting Use Intention.

Purpose: This study investigated military doctors' and nurses' perceptions of telemedicine and the factors influencing their intention to use it based on the unified theory of acceptance and use of technology. Method: This study adopted a questionnaire-based, cross-sectional descriptive approach. It used a web questionnaire for data collection over a 5-week period, starting in June 2021. Results: A total of 72.6% of participants indicated that telemedicine is required in the military. The intention to use telemedicine was significantly higher among women, younger individuals (<30 years), and military nurses. In addition, factors such as voluntariness of use, performance expectancy, social influence, and facilitating conditions positively affected the intention to use telemedicine. Conclusions: To improve military doctors' and nurses' use and understanding of telemedicine, consensus must be reached regarding its use in military contexts. Discussions that incorporate opposing views should be encouraged as well. Moreover, the voluntariness of use significantly affected respondents' intention to use telemedicine. There is an urgent need, therefore, for in-depth analyses of the various factors associated with voluntariness of use of telemedicine; the resulting insights could be used to encourage military doctors and nurses to adopt telemedicine. Finally, along with promoting the use of smartphones for medical consultation among military personnel, military nurses' role should be extended to include health consultation using smartphones. This could promote the active use of telemedicine in military nursing, which could contribute to health promotion among military personnel.

A cross-sectional study on public health nurses' disaster competencies and influencing factors during the COVID-19 pandemic in Korea.

Public health nurses are performing various roles during the COVID-19 pandemic: counseling, surveillance, specimen collection, epidemiological investigation, education, and vaccination. This study investigated their disaster competencies in the context of emerging infectious diseases, and identified their influencing factors based on Deci and Ryan's self-determination theory. A convenience sample of 242 was selected from public health nurses working in a metropolitan city of South Korea. Data were collected using a structured questionnaire and analyzed using descriptive statistics, t-test, one-way ANOVA, Pearson's correlation, and multiple regression analysis using the SPSS Statistics ver. 23.0. Results showed that the significant factors influencing disaster competencies included "willingness to respond to a disaster," "preventive behavior," "experience of receiving education on emerging infectious diseases response," "public health center experience," "job satisfaction," and "education." This regression model explained 33.2% of the variance in disaster competencies. "Willingness to respond to a disaster" was the strongest factor affecting disaster competencies. Based on these results, it is concluded that interventions to improve disaster competencies and psychological well-being of public health nurses are needed. Additionally, strategies such as creating a supportive work environment, deploying experienced nurses primarily on the front line, and reducing the tasks of permanent public health nurses should be implemented.

Gender differences in the relationship between informal caregiving and subjective health: the mediating role of health promoting behaviors.

BACKGROUND: In most of developed societies, the prevalence of informal care is on the rise due to rapid population ageing. This study investigates longitudinal associations between informal caregiving and health among caregivers and potential gender differences in this relationship. Moreover, drawing on the Health Promotion Model, this study examines the mediating role of health promoting behaviors in the link between informal caregiving and caregiver's health. METHODS: Seven waves of a large-scale (N = 9,608), a nationally representative longitudinal study of middle- and old-aged adults in Korea between 2006 and 2018, were used. To address the possibility of omitted variable bias, this study employed ordinary least squares models with lagged dependent variables (OLS-LDV) as well as fixed effects (FE) models. Univariate Sobel-Goodman mediation tests were used. RESULTS: Findings from OLS-LDV models showed that transition into informal caregiving is negatively associated with health satisfaction and self-rated health. FE results also suggest that our results are robust to controlling for unobserved heterogeneity. In the model where informal caregiving is interacted with gender, we found that these associations were largely driven by women caregivers. Results from Sobel-Goodman tests revealed that a decrease in regular exercise partially explains the observed association between informal caregiving and subjective health outcomes (11% for health satisfaction and 8% for self-rated health). CONCLUSIONS: Although informal caregiving can be a rewarding role, it poses a threat to caregiver's subjective health. Findings of this hold important implications and provide evidence in support of a gender-conscious approach to improve the health and well-being of informal caregivers.

Detecting Language Associated With Home Healthcare Patient's Risk for Hospitalization and Emergency Department Visit.

BACKGROUND: About 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. OBJECTIVE: The 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. METHODS: This 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. RESULTS: A 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. CONCLUSION: Our 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.

Exploring prevalence of wound infections and related patient characteristics in homecare using natural language processing.

We aimed to create and validate a natural language processing algorithm to extract wound infection-related information from nursing notes. We also estimated wound infection prevalence in homecare settings and described related patient characteristics. In this retrospective cohort study, a natural language processing algorithm was developed and validated against a gold standard testing set. Cases with wound infection were identified using the algorithm and linked to Outcome and Assessment Information Set data to identify related patient characteristics. The final version of the natural language processing vocabulary contained 3914 terms and expressions related to the presence of wound infection. The natural language processing algorithm achieved overall good performance (F-measure = 0.88). The presence of wound infection was documented for 1.03% (n = 602) of patients without wounds, for 5.95% (n = 3232) of patients with wounds, and 19.19% (n = 152) of patients with wound-related hospitalisation or emergency department visits. Diabetes, peripheral vascular disease, and skin ulcer were significantly associated with wound infection among homecare patients. Our findings suggest that nurses frequently document wound infection-related information. The use of natural language processing demonstrated that valuable information can be extracted from nursing notes which can be used to improve our understanding of the care needs of people receiving homecare. By linking findings from clinical nursing notes with additional structured data, we can analyse related patients' characteristics and use them to develop a tailored intervention that may potentially lead to reduced wound infection-related hospitalizations.

Predictive Risk Models for Wound Infection-Related Hospitalization or ED Visits in Home Health Care Using Machine-Learning Algorithms.

OBJECTIVE: Wound infection is prevalent in home healthcare (HHC) and often leads to hospitalizations. However, none of the previous studies of wounds in HHC have used data from clinical notes. Therefore, the authors created a more accurate description of a patient's condition by extracting risk factors from clinical notes to build predictive models to identify a patient's risk of wound infection in HHC. METHODS: The structured data (eg, standardized assessments) and unstructured information (eg, narrative-free text charting) were retrospectively reviewed for HHC patients with wounds who were served by a large HHC agency in 2014. Wound infection risk factors were identified through bivariate analysis and stepwise variable selection. Risk predictive performance of three machine learning models (logistic regression, random forest, and artificial neural network) was compared. RESULTS: A total of 754 of 54,316 patients (1.39%) had a hospitalization or ED visit related to wound infection. In the bivariate logistic regression, language describing wound type in the patient's clinical notes was strongly associated with risk (odds ratio, 9.94; P < .05). The areas under the curve were 0.82 in logistic regression, 0.75 in random forest, and 0.78 in artificial neural network. Risk prediction performance of the models improved (by up to 13.2%) after adding risk factors extracted from clinical notes. CONCLUSIONS: Logistic regression showed the best risk prediction performance in prediction of wound infection-related hospitalization or ED visits in HHC. The use of data extracted from clinical notes can improve the performance of risk prediction models.

An integrative review on mothers' experiences of online breastfeeding peer support: Motivations, attributes and effects.

Information on the experiences surrounding online breastfeeding peer support among breastfeeding mothers and its effects on breastfeeding outcomes is growing yet to be synthesized. The aim of this review was to synthesize the evidence of mothers' experiences of online breastfeeding peer support. An integrative review was conducted. Five electronic databases were searched. Two reviewers independently screened the articles for inclusion. The inclusion criteria were (1) involved original data focusing on mothers' experiences of online breastfeeding peer support, (2) participants who were mothers who were breastfeeding or had experiences of breastfeeding and (3) studies focusing on interaction and communication among mothers through online communities. In total, 14 publications met the inclusion criteria. Breastfeeding mothers turned to online groups when they felt isolated, lacked professional support or preferred online support over face-to-face support. Online breastfeeding peer support was characterized as a virtual community, with easy access, availability and a wealth of resources from actual experiences of mothers. It empowered breastfeeding mothers and resulted in changes in breastfeeding outcomes and perceptions. The positive aspects of online breastfeeding peer support have recently garnered more attention. This review provided baseline data and evidence to supplement and improve the current breastfeeding support system for breastfeeding mothers. The evidence on the effectiveness of online breastfeeding peer support for influencing breastfeeding outcomes remains inconclusive. Further empirical studies with rigorous study designs are warranted.

Identifying Urinary Tract Infection-Related Information in Home Care Nursing Notes.

OBJECTIVES: Urinary tract infection (UTI) is common in home care but not easily captured with standard assessment. This study aimed to examine the value of nursing notes in detecting UTI signs and symptoms in home care. DESIGN: The study developed a natural language processing (NLP) algorithm to automatically identify UTI-related information in nursing notes. SETTING AND PARTICIPANTS: Home care visit notes (n = 1,149,586) and care coordination notes (n = 1,461,171) for 89,459 patients treated in the largest nonprofit home care agency in the United States during 2014. MEASURES: We generated 6 categories of UTI-related information from literature and used the Unified Medical Language System (UMLS) to identify a preliminary list of terms. The NLP algorithm was tested on a gold standard set of 300 clinical notes annotated by clinical experts. We used structured Outcome and Assessment Information Set data to extract the frequency of UTI-related emergency department (ED) visits or hospitalizations and explored time-patterns in documentation of UTI-related information. RESULTS: The NLP system achieved very good overall performance (F measure = 0.9, 95% CI: 0.87-0.93) based on the test results obtained by using the notes for patients admitted to the ED or hospital due to UTI. UTI-related information was significantly more prevalent (P < .01 for all the tests) in home care episodes with UTI-related ED admission or hospitalization vs the general patient population; 81% of home care episodes with UTI-related hospitalization or ED admission had at least 1 category of UTI-related information vs 21.6% among episodes without UTI-related hospitalization or ED admission. Frequency of UTI-related information documentation increased in advance of UTI-related hospitalization or ED admission, peaking within a few days before the event. CONCLUSIONS AND IMPLICATIONS: Information in nursing notes is often overlooked by stakeholders and not integrated into predictive modeling for decision-making support, but our findings highlight their value in early risk identification and care guidance. Health care administrators should consider using NLP to extract clinical data from nursing notes to improve early detection and treatment, which may lead to quality improvement and cost reduction.

Observation of Hand Hygiene Practices in Home Health Care.

OBJECTIVE: To describe nurse hand hygiene practices in the home health care (HHC) setting, nurse adherence to hand hygiene guidelines, and factors associated with hand hygiene opportunities during home care visits. DESIGN: Observational study of nurse hand hygiene practices. SETTING: and Participants: Licensed practical/vocational and registered nurses were observed in the homes of patients being served by a large nonprofit HHC agency. METHODS: Two researchers observed 400 home care visits conducted by 50 nurses. The World Health Organization's "5 Moments for Hand Hygiene" validated observation tool was used to record opportunities and actual practices of hand hygiene, with 3 additional opportunities specific to the HHC setting. Patient assessment data available in the agency electronic health record and a nurse demographic questionnaire were also collected to describe patients and nurse participants. RESULTS: A total of 2014 opportunities were observed. On arrival in the home was the most frequent opportunity (n = 384), the least frequent was after touching a patient's surroundings (n = 43). The average hand hygiene adherence rate was 45.6% after adjusting for clustering at the nurse level. Adherence was highest after contact with body fluid (65.1%) and lowest after touching a patient (29.5%). The number of hand hygiene opportunities was higher when patients being served were at increased risk of an infection-related emergency department visit or hospitalization and when the home environment was observed to be "dirty." No nurse or patient demographic characteristics were associated with the rate of nurse hand hygiene adherence. CONCLUSIONS AND IMPLICATIONS: Hand hygiene adherence in HHC is suboptimal, with rates mirroring those reported in hospital and outpatient settings. The connection between poor hand hygiene and infection transmission has been well studied, and it has received widespread attention with the outbreak of SARS-CoV-2. Agencies can use results found in this study to better inform quality improvement initiatives.

Free-Text Documentation of Dementia Symptoms in Home Healthcare: A Natural Language Processing Study.

BACKGROUND: Little is known about symptom documentation related to Alzheimer's disease and related dementias (ADRD) by home healthcare (HHC) clinicians. OBJECTIVE: This study: (1) developed a natural language processing (NLP) algorithm that identifies common neuropsychiatric symptoms of ADRD in HHC free-text clinical notes; (2) described symptom clusters and hospitalization or emergency department (ED) visit rates for patients with and without these symptoms. METHOD: We examined a corpus of -2.6 million free-text notes for 112,237 HHC episodes among 89,459 patients admitted to a non-profit HHC agency for post-acute care with any diagnosis. We used NLP software (NimbleMiner) to construct indicators of six neuropsychiatric symptoms. Structured HHC assessment data were used to identify known ADRD diagnoses and construct measures of hospitalization/ED use during HHC. RESULTS: Neuropsychiatric symptoms were documented for 40% of episodes. Common clusters included impaired memory, anxiety and/or depressed mood. One in three episodes without an ADRD diagnosis had documented symptoms. Hospitalization/ED rates increased with one or more symptoms present. CONCLUSION: HHC providers should examine episodes with neuropsychiatric symptoms but no ADRD diagnoses to determine whether ADRD diagnosis was missed or to recommend ADRD evaluation. NLP-generated symptom indicators can help to identify high-risk patients for targeted interventions.

Home Healthcare Clinical Notes Predict Patient Hospitalization and Emergency Department Visits.

BACKGROUND: About 30% of home healthcare patients are hospitalized or visit an emergency department (ED) during a home healthcare (HHC) episode. Novel data science methods are increasingly used to improve identification of patients at risk for negative outcomes. OBJECTIVES: The aim of the study was to identify patients at heightened risk hospitalization or ED visits using HHC narrative data (clinical notes). METHODS: This study used a large database of HHC visit notes (n = 727,676) documented for 112,237 HHC episodes (89,459 unique patients) by clinicians of the largest nonprofit HHC agency in the United States. Text mining and machine learning algorithms (Naïve Bayes, decision tree, random forest) were implemented to predict patient hospitalization or ED visits using the content of clinical notes. Risk factors associated with hospitalization or ED visits were identified using a feature selection technique (gain ratio attribute evaluation). RESULTS: Best performing text mining method (random forest) achieved good predictive performance. Seven risk factors categories were identified, with clinical factors, coordination/communication, and service use being the most frequent categories. DISCUSSION: This study was the first to explore the potential contribution of HHC clinical notes to identifying patients at risk for hospitalization or an ED visit. Our results suggest that HHC visit notes are highly informative and can contribute significantly to identification of patients at risk. Further studies are needed to explore ways to improve risk prediction by adding more data elements from additional data sources.

Decision-making Factors Associated With Telehealth Adoption by Patients With Heart Failure at Home: A Qualitative Study.

Telehealth has been reported to be effective in helping patients with heart failure manage their symptoms at home. Despite this, the adoption rate for telehealth among home care patients with heart failure is low, and there is limited research on reasons for this. This study was undertaken to explore factors associated with patients' decisions to adopt telehealth at home. A qualitative descriptive study underpinned by the Unified Theory of Acceptance Use of Technology model was conducted using semi-structured telephone interviews with patients with heart failure (N = 20) referred for telehealth. Interviews were analyzed using a mixture of deductive and inductive coding. Among the theoretical model elements, the perceived usefulness of the technology (performance expectancy), the availability of clinical/technical support (facilitating conditions), and the opinion of other individuals important to the patient (social influence) were associated with telehealth initiation. However, the ease of use (effort expectancy) was not an associated factor. Other factors such as experience, knowledge, confidence, satisfaction, and attitudes were also associated with the decision. Identification of factors related to higher telehealth initiation rates can be used to inform individualized care planning by nurses. Knowledge of such associations can inform referral process to improve the efficiency and utilization of telehealth.