Use of digital patient decision-support tools for atrial fibrillation treatments: a systematic review and meta-analysis.

OBJECTIVES: To assess the effects of digital patient decision-support tools for atrial fibrillation (AF) treatment decisions in adults with AF. STUDY DESIGN: Systematic review and meta-analysis. ELIGIBILITY CRITERIA: Eligible randomised controlled trials (RCTs) evaluated digital patient decision-support tools for AF treatment decisions in adults with AF. INFORMATION SOURCES: We searched MEDLINE, EMBASE and Scopus from 2005 to 2023.Risk-of-bias (RoB) assessment: We assessed RoB using the Cochrane Risk of Bias Tool 2 for RCTs and cluster RCT and the ROBINS-I tool for quasi-experimental studies. SYNTHESIS OF RESULTS: We used random effects meta-analysis to synthesise decisional conflict and patient knowledge outcomes reported in RCTs. We performed narrative synthesis for all outcomes. The main outcomes of interest were decisional conflict and patient knowledge. RESULTS: 13 articles, reporting on 11 studies (4 RCTs, 1 cluster RCT and 6 quasi-experimental) met the inclusion criteria. There were 2714 participants across all studies (2372 in RCTs), of which 26% were women and the mean age was 71 years. Socioeconomically disadvantaged groups were poorly represented in the included studies. Seven studies (n=2508) focused on non-valvular AF and the mean CHAD2DS2-VASc across studies was 3.2 and for HAS-BLED 1.9. All tools focused on decisions regarding thromboembolic stroke prevention and most enabled calculation of individualised stroke risk. Tools were heterogeneous in features and functions; four tools were patient decision aids. The readability of content was reported in one study. Meta-analyses showed a reduction in decisional conflict (4 RCTs (n=2167); standardised mean difference -0.19; 95% CI -0.30 to -0.08; p=0.001; I2=26.5%; moderate certainty evidence) corresponding to a decrease in 12.4 units on a scale of 0 to 100 (95% CI -19.5 to -5.2) and improvement in patient knowledge (2 RCTs (n=1057); risk difference 0.72, 95% CI 0.68, 0.76, p<0.001; I2=0%; low certainty evidence) favouring digital patient decision-support tools compared with usual care. Four of the 11 tools were publicly available and 3 had been implemented in healthcare delivery. CONCLUSIONS: In the context of stroke prevention in AF, digital patient decision-support tools likely reduce decisional conflict and may result in little to no change in patient knowledge, compared with usual care. Future studies should leverage digital capabilities for increased personalisation and interactivity of the tools, with better consideration of health literacy and equity aspects. Additional robust trials and implementation studies are warranted. PROSPERO REGISTRATION NUMBER: CRD42020218025.

Predicting Adverse Outcomes Following Catheter Ablation Treatment for Atrial Flutter/Fibrillation.

BACKGROUND & AIM: To develop prognostic survival models for predicting adverse outcomes after catheter ablation treatment for non-valvular atrial fibrillation (AF) and/or atrial flutter (AFL). METHODS: We used a linked dataset including hospital administrative data, prescription medicine claims, emergency department presentations, and death registrations of patients in New South Wales, Australia. The cohort included patients who received catheter ablation for AF and/or AFL. Traditional and deep survival models were trained to predict major bleeding events and a composite of heart failure, stroke, cardiac arrest, and death. RESULTS: Out of a total of 3,285 patients in the cohort, 177 (5.3%) experienced the composite outcome-heart failure, stroke, cardiac arrest, death-and 167 (5.1%) experienced major bleeding events after catheter ablation treatment. Models predicting the composite outcome had high-risk discrimination accuracy, with the best model having a concordance index >0.79 at the evaluated time horizons. Models for predicting major bleeding events had poor risk discrimination performance, with all models having a concordance index <0.66. The most impactful features for the models predicting higher risk were comorbidities indicative of poor health, older age, and therapies commonly used in sicker patients to treat heart failure and AF and AFL. DISCUSSION: Diagnosis and medication history did not contain sufficient information for precise risk prediction of experiencing major bleeding events. Predicting the composite outcome yielded promising results, but future research is needed to validate the usefulness of these models in clinical practice. CONCLUSIONS: Machine learning models for predicting the composite outcome have the potential to enable clinicians to identify and manage high-risk patients following catheter ablation for AF and AFL proactively.

Machine-learning versus traditional approaches for atherosclerotic cardiovascular risk prognostication in primary prevention cohorts: a systematic review and meta-analysis.

BACKGROUND: Cardiovascular disease (CVD) risk prediction is important for guiding the intensity of therapy in CVD prevention. Whilst current risk prediction algorithms use traditional statistical approaches, machine learning (ML) presents an alternative method that may improve risk prediction accuracy. This systematic review and meta-analysis aimed to investigate whether ML algorithms demonstrate greater performance compared with traditional risk scores in CVD risk prognostication. METHODS AND RESULTS: MEDLINE, EMBASE, CENTRAL, and SCOPUS Web of Science Core collections were searched for studies comparing ML models to traditional risk scores for CVD risk prediction between the years 2000 and 2021. We included studies that assessed both ML and traditional risk scores in adult (≥18 year old) primary prevention populations. We assessed the risk of bias using the Prediction Model Risk of Bias Assessment Tool (PROBAST) tool. Only studies that provided a measure of discrimination [i.e. C-statistics with 95% confidence intervals (CIs)] were included in the meta-analysis. A total of 16 studies were included in the review and meta-analysis (3302 515 individuals). All study designs were retrospective cohort studies. Out of 16 studies, 3 externally validated their models, and 11 reported calibration metrics. A total of 11 studies demonstrated a high risk of bias. The summary C-statistics (95% CI) of the top-performing ML models and traditional risk scores were 0.773 (95% CI: 0.740-0.806) and 0.759 (95% CI: 0.726-0.792), respectively. The difference in C-statistic was 0.0139 (95% CI: 0.0139-0.140), P < 0.0001. CONCLUSION: ML models outperformed traditional risk scores in the discrimination of CVD risk prognostication. Integration of ML algorithms into electronic healthcare systems in primary care could improve identification of patients at high risk of subsequent CVD events and hence increase opportunities for CVD prevention. It is uncertain whether they can be implemented in clinical settings. Future implementation research is needed to examine how ML models may be utilized for primary prevention.This review was registered with PROSPERO (CRD42020220811).

The performance of machine learning models in predicting suicidal ideation, attempts, and deaths: A meta-analysis and systematic review.

Research has posited that machine learning could improve suicide risk prediction models, which have traditionally performed poorly. This systematic review and meta-analysis evaluated the performance of machine learning models in predicting longitudinal outcomes of suicide-related outcomes of ideation, attempt, and death and examines outcome, data, and model types as potential covariates of model performance. Studies were extracted from PubMed, Web of Science, Embase, and PsycINFO. A bivariate mixed effects meta-analysis and meta-regression analyses were performed for studies using machine learning to predict future events of suicidal ideation, attempts, and/or deaths. Risk of bias was assessed for each study using an adaptation of the Prediction model Risk Of Bias Assessment Tool. Narrative review included 56 studies, and analyses examined 54 models from 35 studies. The models achieved a very good pooled AUC of 0.86, sensitivity of 0.66 (95% CI [0.60, 0.72)], and specificity of 0.87 (95% CI [0.84, 0.90]). Pooled AUCs for ideation, attempt, and death were similar at 0.88, 0.87, and 0.84 respectively. Model performance was highly varied; however, meta-regressions did not provide evidence that performance varied by outcome, data, or model types. Findings suggest that machine learning has the potential to improve suicide risk detection, with pooled estimates of machine learning performance comparing favourably to performance of traditional suicide prediction models. However, more studies with lower risk of bias are necessary to improve the application of machine learning in suicidology.

A personalized mobile app for physical activity: An experimental mixed-methods study.

Objectives: To investigate the feasibility of the be.well app and its personalization approach which regularly considers users' preferences, amongst university students. Methods: We conducted a mixed-methods, pre-post experiment, where participants used the app for 2 months. Eligibility criteria included: age 18-34 years; owning an iPhone with Internet access; and fluency in English. Usability was assessed by a validated questionnaire; engagement metrics were reported. Changes in physical activity were assessed by comparing the difference in daily step count between baseline and 2 months. Interviews were conducted to assess acceptability; thematic analysis was conducted. Results: Twenty-three participants were enrolled in the study (mean age = 21.9 years, 71.4% women). The mean usability score was 5.6 ± 0.8 out of 7. The median daily engagement time was 2 minutes. Eighteen out of 23 participants used the app in the last month of the study. Qualitative data revealed that people liked the personalized activity suggestion feature as it was actionable and promoted user autonomy. Some users also expressed privacy concerns if they had to provide a lot of personal data to receive highly personalized features. Daily step count increased after 2 months of the intervention (median difference = 1953 steps/day, p-value <.001, 95% CI 782 to 3112). Conclusions: Incorporating users' preferences in personalized advice provided by a physical activity app was considered feasible and acceptable, with preliminary support for its positive effects on daily step count. Future randomized studies with longer follow up are warranted to determine the effectiveness of personalized mobile apps in promoting physical activity.

Assessing the effectiveness of empirical calibration under different bias scenarios.

BACKGROUND: Estimations of causal effects from observational data are subject to various sources of bias. One method for adjusting for the residual biases in the estimation of treatment effects is through the use of negative control outcomes, which are outcomes not believed to be affected by the treatment of interest. The empirical calibration procedure is a technique that uses negative control outcomes to calibrate p-values. An extension of this technique calibrates the coverage of the 95% confidence interval of a treatment effect estimate by using negative control outcomes as well as positive control outcomes, which are outcomes for which the treatment of interest has known effects. Although empirical calibration has been used in several large observational studies, there is no systematic examination of its effect under different bias scenarios. METHODS: The effect of empirical calibration of confidence intervals was analyzed using simulated datasets with known treatment effects. The simulations consisted of binary treatment and binary outcome, with biases resulting from unmeasured confounder, model misspecification, measurement error, and lack of positivity. The performance of the empirical calibration was evaluated by determining the change in the coverage of the confidence interval and the bias in the treatment effect estimate. RESULTS: Empirical calibration increased coverage of the 95% confidence interval of the treatment effect estimate under most bias scenarios but was inconsistent in adjusting the bias in the treatment effect estimate. Empirical calibration of confidence intervals was most effective when adjusting for the unmeasured confounding bias. Suitable negative controls had a large impact on the adjustment made by empirical calibration, but small improvements in the coverage of the outcome of interest were also observable when using unsuitable negative controls. CONCLUSIONS: This work adds evidence to the efficacy of empirical calibration of the confidence intervals in observational studies. Calibration of confidence intervals is most effective where there are biases due to unmeasured confounding. Further research is needed on the selection of suitable negative controls.

An Observational Study of Clinical and Health System Factors Associated With Catheter Ablation and Early Ablation Treatment for Atrial Fibrillation in Australia.

OBJECTIVE: To investigate clinical and health system factors associated with receiving catheter ablation (CA) and earlier ablation for non-valvular atrial fibrillation (AF). METHODS: We used hospital administrative data linked with death registrations in New South Wales, Australia for patients with a primary diagnosis of AF between 2009 and 2017. Outcome measures included receipt of CA versus not receiving CA during follow-up (using Cox regression) and receipt of early ablation (using logistic regression). RESULTS: Cardioversion during index admission (hazard ratio [HR] 1.96; 95% CI 1.75-2.19), year of index admission (HR 1.07; 95% CI 1.05-1.10), private patient status (HR 2.65; 95% CI 2.35-2.97), and living in more advantaged areas (HR 1.18; 95% CI 1.13-1.22) were associated with a higher likelihood of receiving CA. A history of congestive heart failure, hypertension, diabetes, and myocardial infarction were associated with a lower likelihood of receiving CA. Private patient status (odds ratio [OR] 2.04; 95% CI 1.59-2.61), cardioversion during index admission (OR 1.25; 95% CI 1.0-1.57), and history of diabetes (OR 1.6; 95% CI 1.06-2.41) were associated with receiving early ablation. CONCLUSIONS: Beyond clinical factors, private patients are more likely to receive CA and earlier ablation than their public counterparts. Whether the earlier access to ablation procedures in private patients is leading to differences in outcomes among patients with atrial fibrillation remains to be explored.

Extract, transform, load framework for the conversion of health databases to OMOP.

Common data models standardize the structures and semantics of health datasets, enabling reproducibility and large-scale studies that leverage the data from multiple locations and settings. The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) is one of the leading common data models. While there is a strong incentive to convert datasets to OMOP, the conversion is time and resource-intensive, leaving the research community in need of tools for mapping data to OMOP. We propose an extract, transform, load (ETL) framework that is metadata-driven and generic across source datasets. The ETL framework uses a new data manipulation language (DML) that organizes SQL snippets in YAML. Our framework includes a compiler that converts YAML files with mapping logic into an ETL script. Access to the ETL framework is available via a web application, allowing users to upload and edit YAML files via web editor and obtain an ETL SQL script for use in development environments. The structure of the DML maximizes readability, refactoring, and maintainability, while minimizing technical debt and standardizing the writing of ETL operations for mapping to OMOP. Our framework also supports transparency of the mapping process and reuse by different institutions.

The use of mobile apps and fitness trackers to promote healthy behaviors during COVID-19: A cross-sectional survey.

OBJECTIVES: To examine i) the use of mobile apps and fitness trackers in adults during the COVID-19 pandemic to support health behaviors; ii) the use of COVID-19 apps; iii) associations between using mobile apps and fitness trackers, and health behaviors; iv) differences in usage amongst population subgroups. METHODS: An online cross-sectional survey was conducted during June-September 2020. The survey was developed and reviewed independently by co-authors to establish face validity. Associations between using mobile apps and fitness trackers and health behaviors were examined using multivariate logistic regression models. Subgroup analyses were conducted using Chi-square and Fisher's exact tests. Three open-ended questions were included to elicit participants' views; thematic analysis was conducted. RESULTS: Participants included 552 adults (76.7% women; mean age: 38±13.6 years); 59.9% used mobile apps for health, 38.2% used fitness trackers, and 46.3% used COVID-19 apps. Users of mobile apps or fitness trackers had almost two times the odds of meeting aerobic physical activity guidelines compared to non-users (odds ratio = 1.91, 95% confidence interval 1.07 to 3.46, P = .03). More women used health apps than men (64.0% vs 46.8%, P = .004). Compared to people aged 18-44 (46.1%), more people aged 60+ (74.5%) and more people aged 45-60 (57.6%) used a COVID-19 related app (P < .001). Qualitative data suggest people viewed technologies (especially social media) as a 'double-edged sword': helping with maintaining a sense of normalcy and staying active and socially connected, but also having a negative emotional effect stemming from seeing COVID-related news. People also found that mobile apps did not adapt quickly enough to the circumstances caused by COVID-19. CONCLUSIONS: Use of mobile apps and fitness trackers during the pandemic was associated with higher levels of physical activity, in a sample of educated and likely health-conscious individuals. Future research is needed to understand whether the association between using mobile devices and physical activity is maintained in the long-term.

Efecto de la temperatura y concentración de microplásticos en la tasa de filtración del mejillón Semimytilus algosus (Mytiloida: Mytilidae) / Effect of temperature and microplastic concentration on the filtration rate of the mussel Semimytilus algosus (Myiloida: Mytilidae)

Resumen Introducción: La presencia de microplásticos (MPs, partículas menores a 5 mm) y el incremento de la temperatura en los océanos, vienen generando perturbaciones en la vida marina, que se pueden relacionar con alteraciones en el metabolismo de organismos filtradores, como los mitílidos. Objetivo: Se evalúa el efecto de diferentes temperaturas y concentraciones de MPs sobre la tasa de filtración (TF) de Semimytilus algosus. Métodos: Una muestra de organismos (N = 72) fue expuesta a cuatro temperaturas (17, 20, 23 y 26 °C), y un testigo sin microplásticos (MPs0) y dos concentraciones de MPs (< 125 µm) de 0.125 mg/l (MPs1) y 0.250 mg/l (MPs2), todos en combinación con la microalga Isochrysis galbana (1x106 cel/ml/día) por 21 días. Resultados: A medida que aumentó la concentración de MPs, se redujo la TF de S. algosus. Respecto a la temperatura, durante el día 7 se observó una mayor TF a 23 °C en todos los tratamientos, y para los días 14 y 21 se obtuvieron los menores valores de TF a 23 y 26 °C. La acción conjunta del incremento de temperatura y MPs, afectó negativamente la TF de S. algosus, donde ambos factores ocasionaron el descenso de la TF para todos los tiempos de evaluación. No se registró mortalidad a 17 °C para ningún tratamiento, y en el caso de mitílidos expuestos a MPs1 y temperaturas de 20 y 26 °C se presentó la mayor mortalidad (67 %). Conclusiones: El estudio demuestra el efecto adverso del incremento de temperatura y MPs sobre la TF de S. algosus.

Abstract Introduction: The presence of microplastics (MPs, particles smaller than 5 mm) and the increase in temperature in the oceans, have been generating disturbances in marine life, which can be related to alterations in the metabolism of filter-feeders, such as Mythilids. Objective: The effect of different temperatures and concentrations of MPs on the filtration rate (TF) of Semimytilus algosus is evaluated. Methods: A sample of organisms (N = 72) was exposed to four temperatures (17, 20, 23 and 26 °C), and a control without microplastics (MPs0) and two concentrations of MPs (< 125 µm) of 0.125 mg/l (MPs1) and 0.250 mg/l (MPs2), all in combination with Isochrysis galbana microalgae (1x106 cells/ml/day) for 21 days. Results: As the concentration of MPs increased, the TF of S. algosus decreased. Regarding temperature, during day 7 a higher TF was observed at 23 °C in all treatments, and during days 14 and 21 the lowest TF values were obtained at 23 and 26 °C. The joint action of the increase in temperature and MPs, negatively affected the TF of S. algosus, where both factors caused the decrease in TF for all evaluation times. No mortality was recorded at 17 °C for any treatment, and in the case of mytylids exposed to MPs1 at 20 °C and 26 °C, the highest mortality (67 %) occurred. Conclusions: The study demonstrates the adverse effect of the increase in temperature and MPs on the TF of S. algosus.

Personalized mobile technologies for lifestyle behavior change: A systematic review, meta-analysis, and meta-regression.

Given that the one-size-fits-all approach to mobile health interventions have limited effects, a personalized approach might be necessary to promote healthy behaviors and prevent chronic conditions. Our systematic review aims to evaluate the effectiveness of personalized mobile interventions on lifestyle behaviors (i.e., physical activity, diet, smoking and alcohol consumption), and identify the effective key features of such interventions. We included any experimental trials that tested a personalized mobile app or fitness tracker and reported any lifestyle behavior measures. We conducted a narrative synthesis for all studies, and a meta-analysis of randomized controlled trials. Thirty-nine articles describing 31 interventions were included (n = 77,243, 64% women). All interventions personalized content and rarely personalized other features. Source of data included system-captured (12 interventions), user-reported (11 interventions) or both (8 interventions). The meta-analysis showed a moderate positive effect on lifestyle behavior outcomes (standardized difference in means [SDM] 0.663, 95% CI 0.228 to 1.10). A meta-regression model including source of data found that interventions that used system-captured data for personalization were associated with higher effectiveness than those that used user-reported data (SDM 1.48, 95% CI 0.76 to 2.19). In summary, the field is in its infancy, with preliminary evidence of the potential efficacy of personalization in improving lifestyle behaviors. Source of data for personalization might be important in determining intervention effectiveness. To fully exploit the potential of personalization, future high-quality studies should investigate the integration of multiple data from different sources and include personalized features other than content.

Do smartphone applications and activity trackers increase physical activity in adults? Systematic review, meta-analysis and metaregression.

OBJECTIVE: To determine the effectiveness of physical activity interventions involving mobile applications (apps) or trackers with automated and continuous self-monitoring and feedback. DESIGN: Systematic review and meta-analysis. DATA SOURCES: PubMed and seven additional databases, from 2007 to 2020. STUDY SELECTION: Randomised controlled trials in adults (18-65 years old) without chronic illness, testing a mobile app or an activity tracker, with any comparison, where the main outcome was a physical activity measure. Independent screening was conducted. DATA EXTRACTION AND SYNTHESIS: We conducted random effects meta-analysis and all effect sizes were transformed into standardised difference in means (SDM). We conducted exploratory metaregression with continuous and discrete moderators identified as statistically significant in subgroup analyses. MAIN OUTCOME MEASURES: Physical activity: daily step counts, min/week of moderate-to-vigorous physical activity, weekly days exercised, min/week of total physical activity, metabolic equivalents. RESULTS: Thirty-five studies met inclusion criteria and 28 were included in the meta-analysis (n=7454 participants, 28% women). The meta-analysis showed a small-to-moderate positive effect on physical activity measures (SDM 0.350, 95% CI 0.236 to 0.465, I2=69%, T 2=0.051) corresponding to 1850 steps per day (95% CI 1247 to 2457). Interventions including text-messaging and personalisation features were significantly more effective in subgroup analyses and metaregression. CONCLUSION: Interventions using apps or trackers seem to be effective in promoting physical activity. Longer studies are needed to assess the impact of different intervention components on long-term engagement and effectiveness.

Empirical analysis of Zipf's law, power law, and lognormal distributions in medical discharge reports.

BACKGROUND: Bayesian modelling and statistical text analysis rely on informed probability priors to encourage good solutions. OBJECTIVE: This paper empirically analyses whether text in medical discharge reports follow Zipf's law, a commonly assumed statistical property of language where word frequency follows a discrete power-law distribution. METHOD: We examined 20,000 medical discharge reports from the MIMIC-III dataset. Methods included splitting the discharge reports into tokens, counting token frequency, fitting power-law distributions to the data, and testing whether alternative distributions-lognormal, exponential, stretched exponential, and truncated power-law-provided superior fits to the data. RESULT: Discharge reports are best fit by the truncated power-law and lognormal distributions. Discharge reports appear to be near-Zipfian by having the truncated power-law provide superior fits over a pure power-law. CONCLUSION: Our findings suggest that Bayesian modelling and statistical text analysis of discharge report text would benefit from using truncated power-law and lognormal probability priors and non-parametric models that capture power-law behavior.

A Mobile Social Networking App for Weight Management and Physical Activity Promotion: Results From an Experimental Mixed Methods Study.

BACKGROUND: Smartphone apps, fitness trackers, and online social networks have shown promise in weight management and physical activity interventions. However, there are knowledge gaps in identifying the most effective and engaging interventions and intervention features preferred by their users. OBJECTIVE: This 6-month pilot study on a social networking mobile app connected to wireless weight and activity tracking devices has 2 main aims: to evaluate changes in BMI, weight, and physical activity levels in users from different BMI categories and to assess user perspectives on the intervention, particularly on social comparison and automated self-monitoring and feedback features. METHODS: This was a mixed methods study involving a one-arm, pre-post quasi-experimental pilot with postintervention interviews and focus groups. Healthy young adults used a social networking mobile app intervention integrated with wireless tracking devices (a weight scale and a physical activity tracker) for 6 months. Quantitative results were analyzed separately for 2 groups-underweight-normal and overweight-obese BMI-using t tests and Wilcoxon sum rank, Wilcoxon signed rank, and chi-square tests. Weekly BMI change in participants was explored using linear mixed effects analysis. Interviews and focus groups were analyzed inductively using thematic analysis. RESULTS: In total, 55 participants were recruited (mean age of 23.6, SD 4.6 years; 28 women) and 45 returned for the final session (n=45, 82% retention rate). There were no differences in BMI from baseline to postintervention (6 months) and between the 2 BMI groups. However, at 4 weeks, participants' BMI decreased by 0.34 kg/m2 (P<.001), with a loss of 0.86 kg/m2 in the overweight-obese group (P=.01). Participants in the overweight-obese group used the app significantly less compared with individuals in the underweight-normal BMI group, as they mentioned negative feelings and demotivation from social comparison, particularly from upward comparison with fitter people. Participants in the underweight-normal BMI group were avid users of the app's self-monitoring and feedback (P=.02) and social (P=.04) features compared with those in the overweight-obese group, and they significantly increased their daily step count over the 6-month study duration by an average of 2292 steps (95% CI 898-3370; P<.001). Most participants mentioned a desire for a more personalized intervention. CONCLUSIONS: This study shows the effects of different interventions on participants from higher and lower BMI groups and different perspectives regarding the intervention, particularly with respect to its social features. Participants in the overweight-obese group did not sustain a short-term decrease in their BMI and mentioned negative emotions from app use, while participants in the underweight-normal BMI group used the app more frequently and significantly increased their daily step count. These differences highlight the importance of intervention personalization. Future research should explore the role of personalized features to help overcome personal barriers and better match individual preferences and needs.

Identifying relevant information in medical conversations to summarize a clinician-patient encounter.

To inform the development of automated summarization of clinical conversations, this study sought to estimate the proportion of doctor-patient communication in general practice (GP) consultations used for generating a consultation summary. Two researchers with a medical degree read the transcripts of 44 GP consultations and highlighted the phrases to be used for generating a summary of the consultation. For all consultations, less than 20% of all words in the transcripts were needed for inclusion in the summary. On average, 9.1% of all words in the transcripts, 26.6% of all medical terms, and 27.3% of all speaker turns were highlighted. The results indicate that communication content used for generating a consultation summary makes up a small portion of GP consultations, and automated summarization solutions-such as digital scribes-must focus on identifying the 20% relevant information for automatically generating consultation summaries.

Envisioning an artificial intelligence documentation assistant for future primary care consultations: A co-design study with general practitioners.

OBJECTIVE: The study sought to understand the potential roles of a future artificial intelligence (AI) documentation assistant in primary care consultations and to identify implications for doctors, patients, healthcare system, and technology design from the perspective of general practitioners. MATERIALS AND METHODS: Co-design workshops with general practitioners were conducted. The workshops focused on (1) understanding the current consultation context and identifying existing problems, (2) ideating future solutions to these problems, and (3) discussing future roles for AI in primary care. The workshop activities included affinity diagramming, brainwriting, and video prototyping methods. The workshops were audio-recorded and transcribed verbatim. Inductive thematic analysis of the transcripts of conversations was performed. RESULTS: Two researchers facilitated 3 co-design workshops with 16 general practitioners. Three main themes emerged: professional autonomy, human-AI collaboration, and new models of care. Major implications identified within these themes included (1) concerns with medico-legal aspects arising from constant recording and accessibility of full consultation records, (2) future consultations taking place out of the exam rooms in a distributed system involving empowered patients, (3) human conversation and empathy remaining the core tasks of doctors in any future AI-enabled consultations, and (4) questioning the current focus of AI initiatives on improved efficiency as opposed to patient care. CONCLUSIONS: AI documentation assistants will likely to be integral to the future primary care consultations. However, these technologies will still need to be supervised by a human until strong evidence for reliable autonomous performance is available. Therefore, different human-AI collaboration models will need to be designed and evaluated to ensure patient safety, quality of care, doctor safety, and doctor autonomy.

Responses of Conversational Agents to Health and Lifestyle Prompts: Investigation of Appropriateness and Presentation Structures.

BACKGROUND: Conversational agents (CAs) are systems that mimic human conversations using text or spoken language. Their widely used examples include voice-activated systems such as Apple Siri, Google Assistant, Amazon Alexa, and Microsoft Cortana. The use of CAs in health care has been on the rise, but concerns about their potential safety risks often remain understudied. OBJECTIVE: This study aimed to analyze how commonly available, general-purpose CAs on smartphones and smart speakers respond to health and lifestyle prompts (questions and open-ended statements) by examining their responses in terms of content and structure alike. METHODS: We followed a piloted script to present health- and lifestyle-related prompts to 8 CAs. The CAs' responses were assessed for their appropriateness on the basis of the prompt type: responses to safety-critical prompts were deemed appropriate if they included a referral to a health professional or service, whereas responses to lifestyle prompts were deemed appropriate if they provided relevant information to address the problem prompted. The response structure was also examined according to information sources (Web search-based or precoded), response content style (informative and/or directive), confirmation of prompt recognition, and empathy. RESULTS: The 8 studied CAs provided in total 240 responses to 30 prompts. They collectively responded appropriately to 41% (46/112) of the safety-critical and 39% (37/96) of the lifestyle prompts. The ratio of appropriate responses deteriorated when safety-critical prompts were rephrased or when the agent used a voice-only interface. The appropriate responses included mostly directive content and empathy statements for the safety-critical prompts and a mix of informative and directive content for the lifestyle prompts. CONCLUSIONS: Our results suggest that the commonly available, general-purpose CAs on smartphones and smart speakers with unconstrained natural language interfaces are limited in their ability to advise on both the safety-critical health prompts and lifestyle prompts. Our study also identified some response structures the CAs employed to present their appropriate responses. Further investigation is needed to establish guidelines for designing suitable response structures for different prompt types.

Challenges of developing a digital scribe to reduce clinical documentation burden.

Clinicians spend a large amount of time on clinical documentation of patient encounters, often impacting quality of care and clinician satisfaction, and causing physician burnout. Advances in artificial intelligence (AI) and machine learning (ML) open the possibility of automating clinical documentation with digital scribes, using speech recognition to eliminate manual documentation by clinicians or medical scribes. However, developing a digital scribe is fraught with problems due to the complex nature of clinical environments and clinical conversations. This paper identifies and discusses major challenges associated with developing automated speech-based documentation in clinical settings: recording high-quality audio, converting audio to transcripts using speech recognition, inducing topic structure from conversation data, extracting medical concepts, generating clinically meaningful summaries of conversations, and obtaining clinical data for AI and ML algorithms.

The Personalization of Conversational Agents in Health Care: Systematic Review.

BACKGROUND: The personalization of conversational agents with natural language user interfaces is seeing increasing use in health care applications, shaping the content, structure, or purpose of the dialogue between humans and conversational agents. OBJECTIVE: The goal of this systematic review was to understand the ways in which personalization has been used with conversational agents in health care and characterize the methods of its implementation. METHODS: We searched on PubMed, Embase, CINAHL, PsycInfo, and ACM Digital Library using a predefined search strategy. The studies were included if they: (1) were primary research studies that focused on consumers, caregivers, or health care professionals; (2) involved a conversational agent with an unconstrained natural language interface; (3) tested the system with human subjects; and (4) implemented personalization features. RESULTS: The search found 1958 publications. After abstract and full-text screening, 13 studies were included in the review. Common examples of personalized content included feedback, daily health reports, alerts, warnings, and recommendations. The personalization features were implemented without a theoretical framework of customization and with limited evaluation of its impact. While conversational agents with personalization features were reported to improve user satisfaction, user engagement and dialogue quality, the role of personalization in improving health outcomes was not assessed directly. CONCLUSIONS: Most of the studies in our review implemented the personalization features without theoretical or evidence-based support for them and did not leverage the recent developments in other domains of personalization. Future research could incorporate personalization as a distinct design factor with a more careful consideration of its impact on health outcomes and its implications on patient safety, privacy, and decision-making.

A network model of activities in primary care consultations.

OBJECTIVE: The objective of this study is to characterize the dynamic structure of primary care consultations by identifying typical activities and their inter-relationships to inform the design of automated approaches to clinical documentation using natural language processing and summarization methods. MATERIALS AND METHODS: This is an observational study in Australian general practice involving 31 consultations with 4 primary care physicians. Consultations were audio-recorded, and computer interactions were recorded using screen capture. Physical interactions in consultation rooms were noted by observers. Brief interviews were conducted after consultations. Conversational transcripts were analyzed to identify different activities and their speech content as well as verbal cues signaling activity transitions. An activity transition analysis was then undertaken to generate a network of activities and transitions. RESULTS: Observed activity classes followed those described in well-known primary care consultation models. Activities were often fragmented across consultations, did not flow necessarily in a defined order, and the flow between activities was nonlinear. Modeling activities as a network revealed that discussing a patient's present complaint was the most central activity and was highly connected to medical history taking, physical examination, and assessment, forming a highly interrelated bundle. Family history, allergy, and investigation discussions were less connected suggesting less dependency on other activities. Clear verbal signs were often identifiable at transitions between activities. DISCUSSION: Primary care consultations do not appear to follow a classic linear model of defined information seeking activities; rather, they are fragmented, highly interdependent, and can be reactively triggered. CONCLUSION: The nonlinearity of activities has significant implications for the design of automated information capture. Whereas dictation systems generate literal translation of speech into text, speech-based clinical summary systems will need to link disparate information fragments, merge their content, and abstract coherent information summaries.