Search

BackgroundThe introduction of natural language processing (NLP) technologies has significantly enhanced the potential of self-administered interventions for treating anxiety and depression by improving human-computer interactions. Although these advances, particularly in complex models such as generative artificial intelligence (AI), are highly promising, robust evidence validating the effectiveness of the interventions remains sparse. ObjectiveThe aim of this study was to determine whether self-administered interventions based on NLP models can reduce depressive and anxiety symptoms. MethodsWe conducted a systematic review and meta-analysis. We searched Web of Science, Scopus, MEDLINE, PsycINFO, IEEE Xplore, Embase, and Cochrane Library from inception to November 3, 2023. We included studies with participants of any age diagnosed with depression or anxiety through professional consultation or validated psychometric instruments. Interventions had to be self-administered and based on NLP models, with passive or active comparators. Outcomes measured included depressive and anxiety symptom scores. We included randomized controlled trials and quasi-experimental studies but excluded narrative, systematic, and scoping reviews. Data extraction was performed independently by pairs of authors using a predefined form. Meta-analysis was conducted using standardized mean differences (SMDs) and random effects models to account for heterogeneity. ResultsIn all, 21 articles were selected for review, of which 76% (16/21) were included in the meta-analysis for each outcome. Most of the studies (16/21, 76%) were recent (2020-2023), with interventions being mostly AI-based NLP models (11/21, 52%); most (19/21, 90%) delivered some form of therapy (primarily cognitive behavioral therapy: 16/19, 84%). The overall meta-analysis showed that self-administered interventions based on NLP models were significantly more effective in reducing both depressive (SMD 0.819, 95% CI 0.389-1.250; P.05). Although the findings were positive, the overall certainty of evidence was very low, mainly due to a high risk of bias, heterogeneity, and potential publication bias. ConclusionsOur findings support the effectiveness of self-administered NLP-based interventions in alleviating depressive and anxiety symptoms, highlighting their potential to increase accessibility to, and reduce costs in, mental health care. Although the results were encouraging, the certainty of evidence was low, underscoring the need for further high-quality randomized controlled trials and studies examining implementation and usability. These interventions could become valuable components of public health strategies to address mental health issues. Trial RegistrationPROSPERO International Prospective Register of Systematic Reviews CRD42023472120; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023472120

BackgroundCancer is a significant public health issue worldwide. Treatments such as surgery, chemotherapy, and radiation therapy often cause psychological and physiological side effects, affecting patients’ ability to function and their quality of life (QoL). Physical activity is crucial to cancer rehabilitation, improving physical function and QoL and reducing cancer-related fatigue. However, many patients face barriers to accessing cancer rehabilitation due to socioeconomic factors, transportation issues, and time constraints. Telerehabilitation can potentially overcome these barriers by delivering rehabilitation remotely. ObjectiveThe aim of the study is to identify how telemedicine is used for the rehabilitation of patients with cancer. MethodsThis scoping review followed recognized frameworks. We conducted an electronic literature search on PubMed for studies published between January 2015 and May 2023. Inclusion criteria were studies reporting physical therapy telerehabilitation interventions for patients with cancer, including randomized and nonrandomized controlled trials, feasibility studies, and usability studies. In total, 21 studies met the criteria and were included in the final review. ResultsOur search yielded 37 papers, with 21 included in the final review. Randomized controlled trials comprised 47% (n=10) of the studies, with feasibility studies at 33% (n=7) and usability studies at 19% (n=4). Sample sizes were typically 50 or fewer participants in 57% (n=12) of the reports. Participants were generally aged 65 years or younger (n=17, 81%), with a balanced gender distribution. Organ-specific cancers were the focus of 66% (n=14) of the papers, while 28% (n=6) included patients who were in the posttreatment period. Web-based systems were the most used technology (n=13, 61%), followed by phone call or SMS text messaging–based systems (n=9, 42%) and mobile apps (n=5, 23%). Exercise programs were mainly home based (n=19, 90%) and included aerobic (n=19, 90%), resistance (n=13, 61%), and flexibility training (n=7, 33%). Outcomes included improvements in functional capacity, cognitive functioning, and QoL (n=10, 47%); reductions in pain and hospital length of stay; and enhancements in fatigue, physical and emotional well-being, and anxiety. Positive effects on feasibility (n=3, 14%), acceptability (n=8, 38%), and cost-effectiveness (n=2, 9%) were also noted. Functional outcomes were frequently assessed (n=19, 71%) with tools like the 6-minute walk test and grip strength tests. ConclusionsTelerehabilitation for patients with cancer is beneficial and feasible, with diverse approaches in study design, technologies, exercises, and outcomes. Future research should focus on developing standardized methodologies, incorporating objective measures, and exploring emerging technologies like virtual reality, wearable or noncontact sensors, and artificial intelligence to optimize telerehabilitation interventions. Addressing these areas can enhance clinical practice and improve outcomes for remote rehabilitation with patients.

BackgroundUnderstanding the multifaceted nature of health outcomes requires a comprehensive examination of the social, economic, and environmental determinants that shape individual well-being. Among these determinants, behavioral factors play a crucial role, particularly the consumption patterns of psychoactive substances, which have important implications on public health. The Global Burden of Disease Study shows a growing impact in disability-adjusted life years due to substance use. The successful identification of patients’ substance use information equips clinical care teams to address substance-related issues more effectively, enabling targeted support and ultimately improving patient outcomes. ObjectiveTraditional natural language processing methods face limitations in accurately parsing diverse clinical language associated with substance use. Large language models offer promise in overcoming these challenges by adapting to diverse language patterns. This study investigates the application of the generative pretrained transformer (GPT) model in specific GPT-3.5 for extracting tobacco, alcohol, and substance use information from patient discharge summaries in zero-shot and few-shot learning settings. This study contributes to the evolving landscape of health care informatics by showcasing the potential of advanced language models in extracting nuanced information critical for enhancing patient care. MethodsThe main data source for analysis in this paper is Medical Information Mart for Intensive Care III data set. Among all notes in this data set, we focused on discharge summaries. Prompt engineering was undertaken, involving an iterative exploration of diverse prompts. Leveraging carefully curated examples and refined prompts, we investigate the model’s proficiency through zero-shot as well as few-shot prompting strategies. ResultsResults show GPT’s varying effectiveness in identifying mentions of tobacco, alcohol, and substance use across learning scenarios. Zero-shot learning showed high accuracy in identifying substance use, whereas few-shot learning reduced accuracy but improved in identifying substance use status, enhancing recall and F1-score at the expense of lower precision. ConclusionsExcellence of zero-shot learning in precisely extracting text span mentioning substance use demonstrates its effectiveness in situations in which comprehensive recall is important. Conversely, few-shot learning offers advantages when accurately determining the status of substance use is the primary focus, even if it involves a trade-off in precision. The results contribute to enhancement of early detection and intervention strategies, tailor treatment plans with greater precision, and ultimately, contribute to a holistic understanding of patient health profiles. By integrating these artificial intelligence–driven methods into electronic health record systems, clinicians can gain immediate, comprehensive insights into substance use that results in shaping interventions that are not only timely but also more personalized and effective.

BackgroundImmersive virtual reality (VR) is a promising therapy to improve the experience of patients with critical illness and may help avoid postdischarge functional impairments. However, the determinants of interest and usability may vary locally and reports of uptake in the literature are variable. ObjectiveThe aim of this mixed methods feasibility study was to assess the acceptability and potential utility of immersive VR in critically ill patients at a single institution. MethodsAdults without delirium who were admitted to 1 of 2 intensive care units were offered the opportunity to participate in 5-15 minutes of immersive VR delivered by a VR headset. Patient vital signs, heart rate variability, mood, and pain were assessed before and after the VR experience. Pre-post comparisons were performed using paired 2-sided t tests. A semistructured interview was administered after the VR experience. Patient descriptions of the experience, issues, and potential uses were summarized with thematic analysis. ResultsOf the 35 patients offered the chance to participate, 20 (57%) agreed to partake in the immersive VR experience, with no difference in participation rate by age. Improvements were observed in overall mood (mean difference 1.8 points, 95% CI 0.6-3.0; P=.002), anxiety (difference of 1.7 points, 95% CI 0.8-2.7; P=.001), and pain (difference of 1.3 points, 95% CI 0.5-2.1; P=.003) assessed on 1-10 scales. The heart rate changed by a mean of –1.1 (95% CI –0.3 to –1.9; P=.008) beats per minute (bpm) from a baseline of 86.1 (SD 11.8) bpm and heart rate variability, assessed by the stress index (SI), changed by a mean of –5.0 (95% CI –1.5 to –8.5; P=.004) seconds–2 from a baseline SI of 40.0 (SD 23) seconds–2. Patients commented on the potential for the therapy to address pain, lessen anxiety, and facilitate calmness. Technical challenges were minimal and there were no adverse effects observed. ConclusionsPatient acceptance of immersive VR was high in a mostly medical intensive care population with little prior VR experience. Patients commented on the potential of immersive VR to ameliorate cognitive and emotional symptoms. Investigators can consider integrating minimally modified commercial VR headsets into the existing intensive care unit workflow to further assess VR’s efficacy for a variety of endpoints.

This study presents an advanced method for predicting symptom escalation in chemotherapy patients using Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNNs). The accurate prediction of symptom escalation is critical in cancer care to enable timely interventions and improve symptom management to enhance patients’ quality of life during treatment. The analytical dataset consists of daily self-reported symptom logs from chemotherapy patients, including a wide range of symptoms, such as nausea, fatigue, and pain. The original dataset was highly imbalanced, with approximately 84% of the data containing no symptom escalation. The data were resampled into varying interval lengths to address this imbalance and improve the model’s ability to detect symptom escalation (n = 3 to n = 7 days). This allowed the model to predict significant changes in symptom severity across these intervals. The results indicate that shorter intervals (n = 3 days) yielded the highest overall performance, with the CNN model achieving an accuracy of 81%, precision of 87%, recall of 80%, and an F1 score of 83%. This was an improvement over the LSTM model, which had an accuracy of 79%, precision of 85%, recall of 79%, and an F1 score of 82%. The model’s accuracy and recall declined as the interval length increased, though precision remained relatively stable. The findings demonstrate that both CNN’s temporospatial feature extraction and LSTM’s temporal modeling effectively capture escalation patterns in symptom progression. By integrating these predictive models into digital health systems, healthcare providers can offer more personalized and proactive care, enabling earlier interventions that may reduce symptom burden and improve treatment adherence. Ultimately, this approach has the potential to significantly enhance the overall quality of life for chemotherapy patients by providing real-time insights into symptom trajectories and guiding clinical decision making.

BackgroundDepression significantly impacts quality of life, affecting approximately 280 million people worldwide. However, only 16.5% of those affected receive treatment, indicating a substantial treatment gap. Immersive technologies (IMTs) such as virtual reality (VR) and augmented reality offer new avenues for treating depression by creating immersive environments for therapeutic interventions. Despite their potential, significant gaps exist in the current evidence regarding the design, implementation, and use of IMTs for depression care. ObjectiveWe aim to map the available evidence on IMT interventions targeting depression treatment. MethodsThis scoping review followed a methodological framework, and we systematically searched databases for studies on IMTs and depression. The focus was on randomized clinical trials involving adults and using IMTs. The selection and charting process involved multiple reviewers to minimize bias. ResultsThe search identified 16 peer-reviewed articles, predominantly from Europe (n=10, 63%), with a notable emphasis on Poland (n=9, 56%), which contributed to more than half of the articles. Most of the studies (9/16, 56%) were conducted between 2020 and 2021. Regarding participant demographics, of the 16 articles, 5 (31%) exclusively involved female participants, and 7 (44%) featured participants whose mean or median age was >60 years. Regarding technical aspects, all studies focused on VR, with most using stand-alone VR headsets (14/16, 88%), and interventions typically ranging from 2 to 8 weeks, predominantly in hospital settings (11/16, 69%). Only 2 (13%) of the 16 studies mentioned using a specific VR design framework in planning their interventions. The most frequently used therapeutic approach was Ericksonian psychotherapy, used in 56% (9/16) of the studies. Notably, none of the articles reported using an implementation framework or identified barriers and enablers to implementation. ConclusionsThis scoping review highlights the growing interest in using IMTs, particularly VR, for depression treatment but emphasizes the need for more inclusive and comprehensive research. Future studies should explore varied therapeutic approaches and cost-effectiveness as well as the inclusion of augmented reality to fully realize the potential of IMTs in mental health care.

In emergency department (ED) settings, rapid and precise diagnostic evaluations are critical to ensure better patient outcomes and efficient healthcare delivery. This study assesses the accuracy of differential diagnosis lists generated by the third-generation ChatGPT (ChatGPT-3.5) and the fourth-generation ChatGPT (ChatGPT-4) based on electronic health record notes recorded within the first 24 h of ED admission. These models process unstructured text to formulate a ranked list of potential diagnoses. The accuracy of these models was benchmarked against actual discharge diagnoses to evaluate their utility as diagnostic aids. Results indicated that both GPT-3.5 and GPT-4 reasonably accurately predicted diagnoses at the body system level, with GPT-4 slightly outperforming its predecessor. However, their performance at the more granular category level was inconsistent, often showing decreased precision. Notably, GPT-4 demonstrated improved accuracy in several critical categories that underscores its advanced capabilities in managing complex clinical scenarios.

BackgroundTelerehabiliation has been shown to have great potential in expanding access to rehabilitation services, enhancing patients’ quality of life, and improving clinical outcomes. Stationary biking exercise can serve as an effective aerobic component of home-based physical rehabilitation programs. Remote monitoring of biking exercise provides necessary safeguards to ensure exercise adherence and safety in patients' homes. The scalability of the current remote monitoring of biking exercise solutions is impeded by the high cost that limits patient access to these services, especially among older adults with chronic health conditions. ObjectiveThe aim of this project was to design and test two low-cost wireless interfaces for the telemonitoring of home-based biking exercise. MethodsWe designed an interactive biking system (iBikE) that comprises a tablet PC and a low-cost bike. Two wireless interfaces to monitor the revolutions per minute (RPM) were built and tested. The first version of the iBikE system uses Bluetooth Low Energy (BLE) to send information from the iBikE to the PC tablet, and the second version uses a Wi-Fi network for communication. Both systems provide patients and their clinical teams the capability to monitor exercise progress in real time using a simple graphical representation. The bike can be used for upper or lower limb rehabilitation. We developed two tablet applications with the same graphical user interfaces between the application and the bike sensors but with different communication protocols (BLE and Wi-Fi). For testing purposes, healthy adults were asked to use an arm bike for three separate subsessions (1 minute each at a slow, medium, and fast pace) with a 1-minute resting gap. While collecting speed values from the iBikE application, we used a tachometer to continuously measure the speed of the bikes during each subsession. Collected data were later used to assess the accuracy of the measured data from the iBikE system. ResultsCollected RPM data in each subsession (slow, medium, and fast) from the iBikE and tachometer were further divided into 4 categories, including RPM in every 10-second bin (6 bins), RPM in every 20-second bin (3 bins), RPM in every 30-second bin (2 bins), and RPM in each 1-minute subsession (60 seconds, 1 bin). For each bin, the mean difference (iBikE and tachometer) was then calculated and averaged for all bins in each subsession. We saw a decreasing trend in the mean RPM difference from the 10-second to the 1-minute measurement. For the 10-second measurements during the slow and fast cycling, the mean discrepancy between the wireless interface and tachometer was 0.67 (SD 0.24) and 1.22 (SD 0.67) for the BLE iBike, and 0.66 (SD 0.48) and 0.87 (SD 0.91) for the Wi-Fi iBike system, respectively. For the 1-minute measurements during the slow and fast cycling, the mean discrepancy between the wireless interface and tachometer was 0.32 (SD 0.26) and 0.66 (SD 0.83) for the BLE iBike, and 0.21 (SD 0.21) and 0.47 (SD 0.52) for the Wi-Fi iBike system, respectively. ConclusionsWe concluded that a low-cost wireless interface provides the necessary accuracy for the telemonitoring of home-based biking exercise.

Objective: We sought to determine if a computer delivered brief alcohol intervention (CBI) with or without interactive voice response counseling and text messages (CBI-IVR-TM), reduced alcohol use and sexual risk behaviors compared to attention control. Methods: We conducted a 3-arm RCT among women (n = 439) recruited from Baltimore City Sexually Transmitted Infection (STI) Clinics. Eligibility included: 1) consumption of >7 drinks per week or 2) ≥2 episodes of heavy episodic drinking or ≥2 episodes of sex under the influence of alcohol in the prior three months. Research assessments conducted at baseline, 3, 6 and 12 months included a 30-day Timeline Followback querying daily alcohol use, drug use, and sexual activity. We used the MINI International Neuropsychiatric Interview-DSM-IV to ascertain drinking severity. Primary alcohol outcomes included: drinking days, heavy drinking days, drinks per drinking day. Secondary sexual risk outcomes included number of sexual partners, days of condomless sex, and days of condomless sex under the influence of drugs and alcohol. Results: Median age was 31 (IQR 25–44 years), 88% were African American, 65% reported current recreational drug use, and 26% endorsed depressive symptoms. On the MINI 66% met criteria for alcohol use disorder (49% alcohol dependence, 18% abuse). At follow-up, all three groups reduced drinking days, heavy drinking days, drinks per drinking day and drinks per week with no significant differences between study arms. There was no difference in sexual risk outcomes among the groups. Conclusions: Among women attending an urban STI clinic single session CBI with or without IVR and text message boosters was insufficient to reduce unhealthy alcohol use or sexual risk behaviors beyond control. The high severity of alcohol use and the prevalence of mental health symptoms and other substance use comorbidity underscores the importance of developing programs that address not only alcohol use but other determinants of STI risk among women.

Objective The COVID-19 pandemic is a global public health crisis, with over 33 million cases and 999 000 deaths worldwide. Data are needed regarding the clinical course of hospitalised patients, particularly in the USA. We aimed to compare clinical characteristic of patients with COVID-19 who had in-hospital mortality with those who were discharged alive.Design Demographic, clinical and outcomes data for patients admitted to five Mount Sinai Health System hospitals with confirmed COVID-19 between 27 February and 2 April 2020 were identified through institutional electronic health records. We performed a retrospective comparative analysis of patients who had in-hospital mortality or were discharged alive.Setting All patients were admitted to the Mount Sinai Health System, a large quaternary care urban hospital system.Participants Participants over the age of 18 years were included.Primary outcomes We investigated in-hospital mortality during the study period.Results A total of 2199 patients with COVID-19 were hospitalised during the study period. As of 2 April, 1121 (51%) patients remained hospitalised, and 1078 (49%) completed their hospital course. Of the latter, the overall mortality was 29%, and 36% required intensive care. The median age was 65 years overall and 75 years in those who died. Pre-existing conditions were present in 65% of those who died and 46% of those discharged. In those who died, the admission median lymphocyte percentage was 11.7%, D-dimer was 2.4 μg/mL, C reactive protein was 162 mg/L and procalcitonin was 0.44 ng/mL. In those discharged, the admission median lymphocyte percentage was 16.6%, D-dimer was 0.93 μg/mL, C reactive protein was 79 mg/L and procalcitonin was 0.09 ng/mL.Conclusions In our cohort of hospitalised patients, requirement of intensive care and mortality were high. Patients who died typically had more pre-existing conditions and greater perturbations in inflammatory markers as compared with those who were discharged.

Existing telemonitoring systems provide limited support in implementing personalized treatment plans. We developed a Home Automated Telemanagement (HAT) system for patients with congestive heart failure (CHF) to provide support in following individualized treatment plans as well as to monitor symptoms, weight changes, and quality of life, while educating the patient on their disease. The system was developed for both a laptop computer and a Nintendo Wii. The system is designed to be placed in the patient's home and to communicate all patient data to a central server implementing real-time clinical decision support. The system questions the patient daily on their condition, monitors their weight, and provides the patient with instant feedback on their condition in the form of a 3-zone CHF action plan. Their medication regimen and suggested actions are determined by their care management team and integrated into the system, keeping a personalized approach to disease management while taking advantage of the technology available. The systems are designed to be as simple as possible, making it usable by patients with no prior computer or videogame experience. A feasibility assessment in African American patients with CHF and without prior computer or videogame experience demonstrated high level of acceptance of the CHF HAT laptop and Wii systems. Keywords: telem

Joseph Finkelstein1, Eunme Cha1, Steven M Scharf 21Welch Center for Prevention, Epidemiology and Clinical Research, Johns Hopkins University, Baltimore, MD, USA; 2Division of Pulmonary and Critical Care Medicine at the Department of Medicine, University of Maryland School of Medicine, Baltimore, MD, USARationale: Recent studies described association between chronic obstructive pulmonary disease (COPD) and increased risk of cardiovascular diseases (CVD). In their analysis none of these studies accounted for sociodemographic factors, health behaviors, and patient comorbidities simultaneously.Objective: To study whether COPD diagnosis is an independent risk factor for CVD. Methods: Subjects aged 40 years and older (N = 18,342) from the sample adult file of the 2002 National Health Interview Survey (NHIS) were included in the analysis. Chi-squared tests and odds ratios (OR) were utilized to compare the data. Multiple logistic regression was employed to analyze the association between COPD and CVD with simultaneous control for sociodemographic factors (age, gender, race, marital status, education, income), health behaviors (tobacco use, alcohol consumption, physical activity), and patient comorbidities (diabetes, hypertension, high cholesterol, and obesity). The analysis employed NHIS sampling weights to generate data representative of the entire US population.Results: The COPD population had increased prevalence of CVD (56.5% vs 25.6%; P < 0.0001). Adjusted logistic regression showed that COPD patients (N = 958) were at higher risk of having coronary heart disease (OR = 2.0, 95% CI: 1.5–2.5), angina (OR = 2.1, 95% CI: 1.6–2.7), myocardial infarction (OR = 2.2, 95% CI: 1.7–2.8), stroke (OR = 1.5, 95% CI: 1.1–2.1), congestive heart failure (OR = 3.9, 95% CI: 2.8–5.5), poor circulation in lower extremities (OR = 2.5, 95% CI: 2.0–3.0), and arrhythmia (OR = 2.4, 95% CI: 2.0–2.8). Overall, the presence of COPD increased the odds of having CVD by a factor of 2.7 (95% CI: 2.3–3.2).Conclusions: These findings support the conclusion that COPD is an independent risk factor for CVD.Keywords: chronic obstructive pulmonary disease, cardiovascular disease, risk factors, population-based analysis, case-control study

The goals of this project were: (1) development of an interactive multimedia medical education tool (CO-ED) utilizing modern features of handheld computing (PDA) and major constructs of adult learning theories, and (2) pilot testing of the computer-assisted education in residents and clinicians. Comparison of the knowledge scores using paired t-test demonstrated statistically significant increase in subject knowledge (p

The aim of this project was construction of a universal platform for rapid development and implementation of interactive computer-based collection of clinical data. A TabletPC was used to pilot-test the platform and to implement two self-administered questionnaires: SF-12 Health Survey (SF-12) and Health Utilities Index (HUI). Qualitative analysis of the system acceptance in 12 patients showed that computer-assisted data collection in elderly patients with no previous computer experience can be successfully implemented using a TabletPC.

Successful patient self-management requires a multidisciplinary approach that includes regular patient assessment, disease-specific education, control of medication adherence, implementation of health behavior change models and social support. Existing systems for computer-assisted disease management do not provide this multidisciplinary patient support and do not address treatment compliance issues. We developed the Home Automated Telemanagement (HAT) system for patients with different chronic health conditions to facilitate their self-care. The HAT system consists of a home unit, HAT server, and clinician units. Patients at home use a palmtop or a laptop connected with a disease monitor on a regular basis. Each HAT session consists of self-testing, feedback, and educational components. The self-reported symptom data and objective results obtained from disease-specific sensors are automatically sent from patient homes to the HAT server in the hospital. Any web-enabled device can serve as a clinician unit to review patient results. The HAT system monitors self-testing results and patient compliance. The HAT system has been implemented and tested in patients receiving anticoagulation therapy, patients with asthma, COPD and other health conditions. Evaluation results indicated high level of acceptance of the HAT system by the patients and that the system has a positive impact on main clinical outcomes and patient satisfaction with medical care.