Search

BackgroundChatbots are artificial intelligence–driven programs that interact with people. The applications of this technology include the collection and delivery of information, generation of and responding to inquiries, collection of end user feedback, and the delivery of personalized health and medical information to patients through cellphone- and web-based platforms. However, no chatbots have been developed for patients with lung cancer and their caregivers. ObjectiveThis study aimed to develop and evaluate the early feasibility of a chatbot designed to improve the knowledge of symptom management among patients with lung cancer in Japan and their caregivers. MethodsWe conducted a sequential mixed methods study that included a web-based anonymized questionnaire survey administered to physicians and paramedics from June to July 2019 (phase 1). Two physicians conducted a content analysis of the questionnaire to curate frequently asked questions (FAQs; phase 2). Based on these FAQs, we developed and integrated a chatbot into a social network service (phase 3). The physicians and paramedics involved in phase I then tested this chatbot (α test; phase 4). Thereafter, patients with lung cancer and their caregivers tested this chatbot (β test; phase 5). ResultsWe obtained 246 questions from 15 health care providers in phase 1. We curated 91 FAQs and their corresponding responses in phase 2. In total, 11 patients and 1 caregiver participated in the β test in phase 5. The participants were asked 60 questions, 8 (13%) of which did not match the appropriate categories. After the β test, 7 (64%) participants responded to the postexperimental questionnaire. The mean satisfaction score was 2.7 (SD 0.5) points out of 5. ConclusionsMedical staff providing care to patients with lung cancer can use the categories specified in this chatbot to educate patients on how they can manage their symptoms. Further studies are required to improve chatbots in terms of interaction with patients.

There are currently no abstract classifiers, which can be used for new diagnostic test accuracy (DTA) systematic reviews to select primary DTA study abstracts from database searches. Our goal was to develop machine-learning-based abstract classifiers for new DTA systematic reviews through an open competition. We prepared a dataset of abstracts obtained through database searches from 11 reviews in different clinical areas. As the reference standard, we used the abstract lists that required manual full-text review. We randomly splitted the datasets into a train set, a public test set, and a private test set. Competition participants used the training set to develop classifiers and validated their classifiers using the public test set. The classifiers were refined based on the performance of the public test set. They could submit as many times as they wanted during the competition. Finally, we used the private test set to rank the submitted classifiers. To reduce false exclusions, we used the Fbeta measure with a beta set to seven for evaluating classifiers. After the competition, we conducted the external validation using a dataset from a cardiology DTA review. We received 13,774 submissions from 1429 teams or persons over 4 months. The top-honored classifier achieved a Fbeta score of 0.4036 and a recall of 0.2352 in the external validation. In conclusion, we were unable to develop an abstract classifier with sufficient recall for immediate application to new DTA systematic reviews. Further studies are needed to update and validate classifiers with datasets from other clinical areas.

It is often challenging to present the available evidence in a timely and comprehensible manner. We aimed to visualize the evolution of evidence about antidepressants for depression by conducting cumulative network meta-analyses (NMAs) and to examine whether it could have helped the selection of optimal drugs. We built a Shiny web application that performs and presents cumulative NMAs based on R netmeta. We used a comprehensive dataset of double-blind randomized controlled trials of 21 antidepressants in the acute treatment of major depression. The primary outcomes were efficacy (treatment response) and acceptability (all-cause discontinuation), and treatment effects were summarized via odds ratios. We evaluated the confidence in evidence using the CINeMA (Confidence in Network Meta-Analysis) framework for a series of consecutive NMAs. Users can change several conditions for the analysis, such as the period of synthesis, among the others. We present the league tables and two-dimensional plots that combine efficacy, acceptability and level of confidence in the evidence together, for NMAs conducted in 1990, 1995, 2000, 2005, 2010, and 2016. They reveal that through the past four decades, newly approved drugs often showed initially exaggerated results, which tended to diminish and stabilize after approximately a decade. Over the years, the drugs with relative superiority changed dramatically; but as the evidence network grew larger and better connected, the overall confidence improved. The Shiny app visualizes how evidence evolved over years, emphasizing the need for a careful interpretation of relative effects between drugs, especially for the potentially amplified performance of newly approved drugs.

Background: Clinicians' research activities reportedly improve their healthcare performance. Presenting research at conferences may be related to improved patient care outcomes; however, few studies have investigated this relationship. Thus, we examined the association between presenting at conferences and the mortality of patients hospitalized for acute myocardial infarction. Methods: We analyzed an administrative database of acute care hospitals in Japan. The study compared patients admitted to hospitals in which physicians made at least one conference presentation during the patient's admission year (Presentation Group) with those admitted to hospitals with no conference presentations (Control group). We performed multivariable logistic regression analyses to estimate the risk of all-cause in-hospital mortality. Five models were fitted: a Crude model, unadjusted; Model 1, adjusted for personal factors, including sex, age, Killip classification, and so on; Model 2, adjusted for Model 1 plus hospital factors; Model 3 was a multilevel analysis clustered by hospital codes and adjusted for the same variables as Model 1; Model 4 was adjusted for Model 1 plus evidence-based practices through causal mediation analysis. Results: After excluding 3,544 patients with missing Killip classification or ambulance use, data for 56,923 patients in 384 acute care hospitals were analyzed. Drug prescription in accordance with the evidence was significantly greater in the Presentation group than in the Control group. Moreover, conference presentation was significantly associated with lower in-hospital mortality in all models (Odds ratios (OR) = 0.68, 95% Confidence intervals (CIs): 0.65 to 0.72 in the Crude model; OR = 0.73, 95% CIs: 0.68 to 0.79 in Model 1; OR = 0.76, 95% CIs: 0.70 to 0.82 in Model 2; OR = 0.84, 95% CIs: 0.76 to 0.92 in Model 3; OR = 1.00, 95% CIs: 0.92 to 1.09 in Model 4). Conclusion: The promotion of scholarly activities such as conference presentations might improve patient outcomes through increased evidence-based practice. [ABSTRACT FROM AUTHOR]

Background: Physical activity inequalities are an important global concern; nonetheless, few studies have comprehensively examined the association between physical activity inequalities and related factors. We aimed to explore factors associated with regional inequalities in physical activity in Japan. Methods: We investigated the relationship of individual, psychological/behavioral, social, and built‐environmental factors with the proportion of individuals with exercise habits across Japanese prefectures. We sourced data from open databases, including the Japanese National Health Insurance Claims and Nationwide Screening Program Database. We defined exercise habits as engaging in at least 30 min of moderate exercise at least twice a week. We employed multiple regression analysis to identify factors associated with prefectural level physical activity. Results: The median proportion of individuals with exercise habits was 27% (interquartile range, 25–29). Higher frequency of exercise habits was associated with higher frequency of history of exercise (coefficients, 0.60; 95% confidence interval, 0.41–0.80) and lower proportion of female gender (coefficients, −1.74; 95% confidence interval, −2.80 to −0.69). Conclusions: Exercise history and female gender may be related to prefectural level physical activity in Japan. Physical activity interventions should be promoted among women without exercise history. [ABSTRACT FROM AUTHOR]

Meta‐analyses examining dichotomous outcomes often include single‐zero studies, where no events occur in intervention or control groups. These pose challenges, and several methods have been proposed to address them. A fixed continuity correction method has been shown to bias estimates, but it is frequently used because sometimes software (e.g., RevMan software in Cochrane reviews) uses it as a default. We aimed to empirically compare results using the continuity correction with those using alternative models that do not require correction. To this aim, we reanalyzed the original data from 885 meta‐analyses in Cochrane reviews using the following methods: (i) Mantel–Haenszel model with a fixed continuity correction, (ii) random effects inverse variance model with a fixed continuity correction, (iii) Peto method (the three models available in RevMan), (iv) random effects inverse variance model with the treatment arm continuity correction, (v) Mantel–Haenszel model without correction, (vi) logistic regression, and (vii) a Bayesian random effects model with binominal likelihood. For each meta‐analysis we calculated ratios of odds ratios between all methods, to assess how the choice of method may impact results. Ratios of odds ratios <0.8 or <1.25 were seen in ~30% of the existing meta‐analyses when comparing results between Mantel–Haenszel model with a fixed continuity correction and either Mantel–Haenszel model without correction or logistic regression. We concluded that injudicious use of the fixed continuity correction in existing Cochrane reviews may have substantially influenced effect estimates in some cases. Future updates of RevMan should incorporate less biased statistical methods. [ABSTRACT FROM AUTHOR]