PLOS digital health最新文献

The Scottish Patients at Risk of Re-Admission and Admission (SPARRA) score predicts individual risk of emergency hospital admission for approximately 80% of the Scottish population. It was developed using routinely collected electronic health records, and is used by primary care practitioners to inform anticipatory care, particularly for individuals with high healthcare needs. We comprehensively assess the SPARRA score across population subgroups defined by age, sex, ethnicity, socioeconomic deprivation, and geographic location. For these subgroups, we consider differences in overall performance, score distribution, and false positive and negative rates, using causal methods to identify effects mediated through age, sex, and deprivation. We show that the score is well-calibrated across subgroups, but that rates of false positives and negatives vary widely, mediated by various causes including variability in demographic characteristics, admission reasons, and potentially differential data availability. Our work assists practitioners in the application and interpretation of the SPARRA score in population subgroups.

Neonatal apneas and hypopneas present a serious risk for healthy infant development. Treating these adverse events requires frequent manual stimulation by skilled personnel, which can lead to alarm fatigue. This study aims to develop and validate an interpretable model that can predict apneas and hypopneas. Automatically predicting these adverse events before they occur would enable the use of methods for automatic intervention. We propose a neural additive model to predict individual occurrences of neonatal apnea and hypopnea and apply it to a physiological dataset from infants with Robin sequence at risk of upper airway obstruction. The dataset will be made publicly available together with this study. Our proposed model allows the prediction of individual apneas and hypopneas, achieving an average AuROC of 0.80 when discriminating segments of polysomnography recordings starting 15 seconds before the onset of apneas and hypopneas from control segments. Its additive nature makes the model inherently interpretable, which allowed insights into how important a given signal modality is for prediction and which patterns in the signal are discriminative. For our problem of predicting apneas and hypopneas in infants with Robin sequence, prior irregularities in breathing-related modalities as well as decreases in SpO2 levels were especially discriminative. Our prediction model presents a step towards an automatic prediction of neonatal apneas and hypopneas in infants at risk for upper airway obstruction. Together with the publicly released dataset, it has the potential to facilitate the development and application of methods for automatic intervention in clinical practice.

Periodontitis is a complex and microbiome-related inflammatory condition impacting dental supporting tissues. Emphasizing the potential of Clinical Decision Support Systems (CDSS), this study aims to facilitate early diagnosis of periodontitis by extracting patients' information collected as dental charts and notes. We developed a CDSS to predict the stage and grade of periodontitis using natural language processing (NLP) techniques including bidirectional encoder representation for transformers (BERT). We compared the performance of BERT with that of a baseline feature-engineered model. A secondary data analysis was conducted using 309 anonymized patient periodontal charts and corresponding clinician's notes obtained from the university periodontal clinic. After data preprocessing, we added a classification layer on top of the pre-trained BERT model to classify the clinical notes into their corresponding stage and grades. Then, we fine-tuned the pre-trained BERT model on 70% of our data. The performance of the model was evaluated on 32 unseen new patients' clinical notes. The results were compared with the output of a baseline feature-engineered algorithm coupled with MLP techniques to classify the stage and grade of periodontitis. Our proposed BERT model predicted the patients' stage and grade with 77% and 75% accuracy, respectively. MLP model showed that the accuracy of correct classification of stage and grade of the periodontitis on a set of 32 new unseen data was 59.4% and 62.5%, respectively. The BERT model could predict the periodontitis stage and grade on the same new dataset with higher accuracy (66% and 72%, respectively). The utilization of BERT in this context represents a groundbreaking application in dentistry, particularly in CDSS. Our BERT model outperformed baseline models, even with reduced information, promising efficient review of patient notes. This integration of advanced NLP techniques with CDSS frameworks holds potential for timely interventions, preventing complications and reducing healthcare costs.

Pharmaceutical care in the majority of developing countries is hindered by a lack of techniques, limitations in mobility, and a shortage of staff to provide patient care. However, there is no evidence that professionals intend to use telepharmacy in patient care. To fill this gap, this study was designed to examine whether pharmacists, physicians, and nursing professionals intend to use telepharamcy in their care practice.A cross-sectional investigation was carried out from November 29 to December 30, 2023. A study was conducted at all Hawassa public hospitals. A total of 592 Pharmacists, Physicians, and nurses participated. Simple random sampling and proportional allocation were utilized. A structured self-administered questionnaire was used, and a 5% pretest was administered. The data were entered into Epi Data 4.6 and exported to SPSS 26. The AMOS 23 SEM was also used to describe and assess the degree and significance of the relationships between variables.51.4% (304/592) (95% CI, 47.2-55.4) of the participants intended to use telepharmacy. Performance expectancy (β = 0.23, p-value <0.05), social influence (β = 0.295, p-value <0.05), and digital literacy (β = 0.309, p-value <0.001) had positive relationships with the intention to use telepharmacy. Age and gender were also moderators of performance expectancy in telepharmacy.Overall, Pharmacists', Physicians', and nurses' intentions to use telepharamcy were found to be promising for the future. Performance expectancy, social influence, and digital literacy had a significantly positive influence on the intention to use telepharamcy. Digital literacy had a more significant prediction power than others. The results could be useful in terms of designing emerging systems and understanding users' computer skills.

Ensuring reliability of Large Language Models (LLMs) in clinical tasks is crucial. Our study assesses two state-of-the-art LLMs (ChatGPT and LlaMA-2) for extracting clinical information, focusing on cognitive tests like MMSE and CDR. Our data consisted of 135,307 clinical notes (Jan 12th, 2010 to May 24th, 2023) mentioning MMSE, CDR, or MoCA. After applying inclusion criteria 34,465 notes remained, of which 765 underwent ChatGPT (GPT-4) and LlaMA-2, and 22 experts reviewed the responses. ChatGPT successfully extracted MMSE and CDR instances with dates from 742 notes. We used 20 notes for fine-tuning and training the reviewers. The remaining 722 were assigned to reviewers, with 309 each assigned to two reviewers simultaneously. Inter-rater-agreement (Fleiss' Kappa), precision, recall, true/false negative rates, and accuracy were calculated. Our study follows TRIPOD reporting guidelines for model validation. For MMSE information extraction, ChatGPT (vs. LlaMA-2) achieved accuracy of 83% (vs. 66.4%), sensitivity of 89.7% (vs. 69.9%), true-negative rates of 96% (vs 60.0%), and precision of 82.7% (vs 62.2%). For CDR the results were lower overall, with accuracy of 87.1% (vs. 74.5%), sensitivity of 84.3% (vs. 39.7%), true-negative rates of 99.8% (98.4%), and precision of 48.3% (vs. 16.1%). We qualitatively evaluated the MMSE errors of ChatGPT and LlaMA-2 on double-reviewed notes. LlaMA-2 errors included 27 cases of total hallucination, 19 cases of reporting other scores instead of MMSE, 25 missed scores, and 23 cases of reporting only the wrong date. In comparison, ChatGPT's errors included only 3 cases of total hallucination, 17 cases of wrong test reported instead of MMSE, and 19 cases of reporting a wrong date. In this diagnostic/prognostic study of ChatGPT and LlaMA-2 for extracting cognitive exam dates and scores from clinical notes, ChatGPT exhibited high accuracy, with better performance compared to LlaMA-2. The use of LLMs could benefit dementia research and clinical care, by identifying eligible patients for treatments initialization or clinical trial enrollments. Rigorous evaluation of LLMs is crucial to understanding their capabilities and limitations.

Objectives: Although several brief cognitive behavior therapy (CBT)-based treatments for dental fear have proven efficacious, these interventions remain largely unavailable outside of the specialty clinics in which they were developed. Leveraging technology, we sought to increase access to treatment for individuals with dental fear through the development of a mobile application (Dental FearLess).

Materials and methods: To assess the resonance of our app as an avenue for dental fear treatment, we conducted a study assessing the usability, feasibility, and acceptability of the beta app. Participants with moderate to severe dental fear (N = 80) completed the app and reported on the perceived usability of the mobile interface (Systems Usability Scale, SUS; α = .82) and credibility of the intervention (Credibility and Expectancy Questionnaire, CEQ; α = .88). A sub-sample of participants naïve to the app (n = 10) completed the app during a think-aloud procedure, sharing their candid thoughts and reactions while using the app, prior to reporting on usability and credibility metrics.

Results: Overall usability (M = 78.5, SD = 17.7) and credibility (M = 21.7, SD = 5.5) of the beta version of the app were good. The think-aloud data further corroborated the app's acceptability, while highlighting several areas for user improvement (i.e., aesthetics, navigation, engagement).

Conclusions: Usability and acceptability results are promising for the viability of an accessible, feasible, self-administered intervention for dental fear. Refinements made based on user feedback have produced a clinical-trial-ready mobile application. App refinement decisions, informed by user feedback, are representative of the larger literature-that is, of the ubiquitous negotiations m-health developers must make across treatment fidelity, usability, and engagement. Implications for future research are discussed.

Symptom-only case definitions are insufficient to discriminate COVID-like illness from acute respiratory infection (ARI) or influenza-like illness (ILI), due to the overlap in case definitions. Our objective was to develop a statistical method that does not rely on case definitions to determine the contribution of influenza virus and SARS-CoV-2 to the ARI burden during periods when both viruses are circulating. Data sources used for testing the approach were weekly ARI syndrome reports from the Infectieradar participatory syndromic surveillance system during the analysis period (the first 25 weeks of 2022, in which SARS-CoV-2 and influenza virus co-circulated in the Netherlands) and data from virologically tested ARI (including ILI) patients who consulted a general practitioner in the same period. Estimation of the proportions of ARI attributable to influenza virus, SARS-CoV-2, or another cause was framed as an inference problem, through which all data sources are combined within a Bayesian framework to infer the weekly numbers of ARI reports attributable to each cause. Posterior distributions for the attribution proportions were obtained using Markov Chain Monte-Carlo methods. Application of the approach to the example data sources indicated that, of the total ARI reports (total of 11,312; weekly mean of 452) during the analysis period, the model attributed 35.4% (95% CrI: 29.2-40.0%) and 27.0% (95% CrI: 19.3-35.2%) to influenza virus and SARS-CoV-2, respectively. The proposed statistical model allows the attribution of respiratory syndrome reports from participatory surveillance to either influenza virus or SARS-CoV-2 infection in periods when both viruses are circulating, but comparability of the participatory surveillance and virologically tested populations is important. Portability for use by other countries with established participatory respiratory surveillance systems is an asset.

It is widely assumed that telehealth tools like mHealth (mobile health), telemedicine, and tele-education can supplement the efficiency of Healthcare Providers (HCPs). We conducted a systematic review of evidence on the barriers and facilitators associated with the use of telehealth by HCPs in India. A systematic literature search following a pre-registered protocol (https://doi.org/10.17605/OSF.IO/KQ3U9 [PROTOCOL DOI]) was conducted on PubMed. The search strategy, inclusion, and exclusion criteria were based on the World Health Organization's action framework on Human Resources for Health (HRH) and Universal Health Coverage (UHC) in India with a specific focus on telehealth tools. Eligible articles published in English from 1st January 2001 to 17th February 2022 were included. One hundred and six studies were included in the review. Of these, 53 studies (50%) involved mHealth interventions, 25 (23.6%) involved telemedicine interventions whereas the remaining 28 (26.4%) involved the use of tele-education interventions by HCPs in India. In each category, most of the studies followed a quantitative study design and were mostly published in the last 5 years. The study sites were more commonly present in states in south India. The facilitators and barriers related to each type of intervention were analyzed under the following sub-headings- 1) Human resource related, 2) Application related 3) Technical, and 4) Others. The interventions were most commonly used for improving the management of mental health, non-communicable diseases, and maternal and child health. The use of telehealth has not been uniformly studied in India. The facilitators and barriers to telehealth use need to be kept in mind while designing the intervention. Future studies should focus on looking at region-specific, intervention-specific, and health cadre-specific barriers and facilitators for the use of telehealth.

Lifestyle-related diseases, such as diabetes, are mostly caused by poor lifestyle habits; therefore, modifying these habits is important. In Japan, a system of specific health checkups (SHC) and specific health guidance (SHG) was introduced in 2008. The challenges faced include low retention rates and difficulty in maintaining results. Digital technologies can support self-management and increase patient convenience, although evidence of the usefulness of this technology for SHG is limited. This study evaluated the usefulness of nutritional guidance using a smartphone application (app) added to conventional SHG. We recruited eligible participants for SHG in Japan from November 2018 to March 2020. We assigned them to "Intervention Group: Application-Supported Nutrition Therapy" or "Control Group: Human Nutrition Therapy" based on their desire to use the app. The primary outcome was a change in non-high-density lipoprotein cholesterol (non-HDL-C) levels post-intervention. The secondary outcomes were a change in lipid profile, metabolic indices, and frequency of logins to the app. We assessed 109 participants in two cohorts: 3-month (short-term) and 6-month (long-term). The short-term cohort had 23 intervention and 29 control participants, while the long-term cohort had 35 and 22, respectively. There was a significant improvement in non-HDL-C levels in the short-term intervention group compared to the control group. There was no significant difference in non-HDL-C levels in the long-term groups or at 1 year. There were significant improvements in body weight (BW) in the short-term cohort until 1 year compared within the groups. The retention rate remained high in the short-term cohort (92%) but decreased to 57.8% at 6 months in the long-term cohort. Using an app system to facilitate dietary recordings and guidance for patients at risk of lifestyle-related diseases led to improved lipid levels and BW. These benefits persisted to some extent after 1 year. This app may partially supplement conventional SHG.

We present Clinical Prediction with Large Language Models (CPLLM), a method that involves fine-tuning a pre-trained Large Language Model (LLM) for predicting clinical disease and readmission. We utilized quantization and fine-tuned the LLM using prompts. For diagnostic predictions, we predicted whether patients would be diagnosed with a target disease during their next visit or in the subsequent diagnosis, leveraging their historical medical records. We compared our results to various baselines, including Retain and Med-BERT, the latter of which is the current state-of-the-art model for disease prediction using temporal structured EHR data. In addition, we also evaluated CPLLM's utility in predicting hospital readmission and compared our method's performance with benchmark baselines. Our experiments ultimately revealed that our proposed method, CPLLM, surpasses all the tested models in terms of PR-AUC and ROC-AUC metrics, providing state-of-the-art performance as a tool for predicting disease diagnosis and patient hospital readmission without requiring pre-training on medical data. Such a method can be easily implemented and integrated into the clinical workflow to help care providers plan next steps for their patients.