Previous studies have successfully predicted overweight status by applying deep learning to 12-lead electrocardiogram (ECG); however, models for predicting underweight status remain unexplored. Here, ...we assessed the feasibility of deep learning in predicting extremely low body weight using 12-lead ECGs, thereby investigating the prediction rationale for highlighting the parts of ECGs that are associated with extremely low body weight. Using records of inpatients predominantly with anorexia nervosa, we trained a convolutional neural network (CNN) that inputs a 12-lead ECG and outputs a binary prediction of whether body mass index is ≤ 12.6 kg/m
. This threshold was identified in a previous study as the optimal cutoff point for predicting the onset of refeeding syndrome. The CNN model achieved an area under the receiver operating characteristic curve of 0.807 (95% confidence interval, 0.745-0.869) on the test dataset. The gradient-weighted class activation map showed that the model focused on QRS waves. A negative correlation with the prediction scores was observed for QRS voltage. These results suggest that deep learning is feasible for predicting extremely low body weight using 12-lead ECGs, and several ECG features, such as lower QRS voltage, may be associated with extremely low body weight in patients with anorexia nervosa.
We aimed to develop action plans for employees' health promotion based on a machine learning model to predict sick leave at a Japanese manufacturing plant.
A random forest model was developed to ...predict sick leave. We developed plans for workers' health promotion based on variable importance and partial dependence plots.
The model showed an area under the receiving operating characteristic curve of 0.882. The higher scores on the Brief Job Stress Questionnaire stress response, younger age, and certain departments were important predictors for sick leave due to mental disorders. We proposed plans to effectively use the Brief Job Stress Questionnaire and provide more support for younger workers and managers of high-risk departments.
We described a process of action plan development using a machine learning model, which may be beneficial for occupational health practitioners.
Background:
Antipsychotics are frequently used to treat delirium but often induce corrected QT (QTc) prolongation, which can be lethal by causing torsade de pointes. Nonetheless, the selection of ...antipsychotics to treat delirium patients with prolonged baseline QTc intervals remains unclear. We aimed to assess the utility of antipsychotics based on their effects on treatment outcomes and QTc intervals.
Methods:
A clinical decision analysis was conducted using data on the effects of antipsychotics on treatment outcomes and QTc intervals from published network meta-analyses. We quantified the utility of six antipsychotics (amisulpride, haloperidol, olanzapine, quetiapine, risperidone, and ziprasidone) using a decision tree and the obtained effect sizes. Subsequently, we conducted sensitivity analyses using multiple utility settings and another dataset. We also performed a probabilistic sensitivity analysis using Monte Carlo simulation, in which the effects of antipsychotics were randomly sampled given the plausible range.
Results:
Amisulpride showed the highest utility when the baseline QTc interval was 420 ms. Quetiapine showed the highest utility when the baseline QTc interval was ≥450 ms. The sensitivity analyses also showed the superiority of quetiapine when the baseline QTc intervals were prolonged.
Conclusions:
Decision analysis suggests that quetiapine is the optimal antipsychotic drug for the treatment of patients with delirium and prolonged baseline QTc intervals.
In Japan, there is a unique clinical department, "Psychosomatic Medicine", while there is not a department of behavioral science or behavioral medicine in medical schools. Although only eight medical ...schools have the department, psychosomatic physicians in the department have been involved with behavioral medicine. In the present manuscript, the author would like to introduce the contribution to behavioral medicine made by psychosomatic physicians in three aspects, education, clinical settings, and research, and propose some strategy for psychosomatic physicians to get more involved with behavioral medicine.
Background Sleep disturbance is a major contributor to future health and occupational issues. Mobile health can provide interventions that address adverse health behaviors for individuals in a ...vulnerable health state in real-world settings (just-in-time adaptive intervention). Objective This study aims to identify a subpopulation with vulnerable sleep state in daily life (study 1) and, immediately afterward, to test whether providing mobile health intervention improved habitual sleep behaviors and psychological wellness in real-world settings by conducting a microrandomized trial (study 2). Methods Japanese workers (n=182) were instructed to collect data on their habitual sleep behaviors and momentary symptoms (including depressive mood, anxiety, and subjective sleep quality) using digital devices in a real-world setting. In study 1, we calculated intraindividual mean and variability of sleep hours, midpoint of sleep, and sleep efficiency to characterize their habitual sleep behaviors. In study 2, we designed and conducted a sleep just-in-time adaptive intervention, which delivered objective push-type sleep feedback messages to improve their sleep hours for a subset of participants in study 1 (n=81). The feedback messages were generated based on their sleep data measured on previous nights and were randomly sent to participants with a 50% chance for each day (microrandomization). Results In study 1, we applied hierarchical clustering to dichotomize the population into 2 clusters (group A and group B) and found that group B was characterized by unstable habitual sleep behaviors (large intraindividual variabilities). In addition, linear mixed-effect models showed that the interindividual variability of sleep hours was significantly associated with depressive mood (β=3.83; P=.004), anxiety (β=5.70; P=.03), and subjective sleep quality (β=−3.37; P=.03). In study 2, we found that providing sleep feedback prolonged subsequent sleep hours (increasing up to 40 min; P=.01), and this effect lasted for up to 7 days. Overall, the stability of sleep hours in study 2 was significantly improved among participants in group B compared with the participants in study 1 (P=.001). Conclusions This is the first study to demonstrate that providing sleep feedback can benefit the modification of habitual sleep behaviors in a microrandomized trial. The findings of this study encourage the use of digitalized health intervention that uses real-time health monitoring and personalized feedback.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
Depressive symptoms are prevalent in cancer patients and are one of the most distressing symptoms in this population. Although mental health professionals such as psychiatrists and psychologists are ...now engaged in cancer care, the management of depressive symptoms in cancer patients needs further improvement. Peer support interventions (PSIs) in cancer care have attracted substantial attention and have several advantages over support by medical professionals, potentially improving depressive symptoms in cancer patients. However, there may be some potential risks. Several strategies using PSIs have been developed to improve depressive symptoms and have been evaluated in randomized controlled trials. The strategies include education on stress management skills, promoting emotional support, counseling on specific topics that are difficult to discuss with others, helping patients navigate the use of resources, and promoting health-related behaviors to decrease depressive symptoms. In this paper, we present recent findings on PSIs in cancer, focusing on randomized controlled trials.
Abstract Context Japanese people's preferred place of end-of-life care may be affected by their experiences, perceptions, and knowledge related to the end of life. Objectives The aims of this study ...were to clarify the Japanese population's preferences for the place of end-of-life care and death and to identify the determinants of each choice of preferred place of end-of-life care within their experiences, perceptions, and knowledge. Methods A total of 2000 Japanese people aged 40–79 years participated in a cross-sectional nationwide survey. Results Fifty-five percent ( n = 1042) responded. Regarding place of end-of-life care, approximately 44% of the general population preferred home, 15% preferred hospital, 19% preferred palliative care unit, 10% preferred public nursing home, 2% preferred private nursing home, and the remaining 11% was unsure. Multinomial logistic regression analysis revealed that the following factors affect people’s preferences regarding place of care: 1) experiences, such as “visiting hospital regularly” and “experiencing home death of relatives,” 2) perceptions, such as “giving due thought to their own death on a daily basis” and “perceiving lower home palliative care costs to be appropriate after comparing hospital admission fees,” and 3) knowledge of “home care nursing” and “24-hour home palliative system by physicians and nurses using insurance.” These factors correlated with preference for hospital, palliative care unit, or public nursing home, when compared with the preference of home. Conclusion The present findings may help to develop an effective end-of-life care system in Japan, in line with people’s various preferred locations for such care.
The advancement of wearable/ambulatory technologies has brought a huge change to data collection frameworks in recent decades. Mobile health (mHealth) care platforms, which utilize ambulatory devices ...to collect naturalistic and often intensively sampled data, produce innovative information of potential clinical relevance. For example, such data can inform clinical study design, recruitment approach, data analysis, and delivery of both "traditional" and novel (e.g., mHealth) interventions. We provide a conceptual overview of how data measured continuously or repeatedly via mobile devices (e.g., smartphone and body sensors) in daily life could be fruitfully used within a mHealth care system. We highlight the potential benefits of integrating ecological momentary assessment (EMA) into mHealth platforms for collecting, processing, and modeling data, and delivering and evaluating novel interventions in everyday life. Although the data obtained from EMA and related approaches may hold great potential benefits for mHealth care system, there are also implementation challenges; we briefly discuss the challenges to integrating EMA into mHealth care system.
Recent findings suggest that patient pre-transplant psychosocial risk factors predict survival after hematopoietic stem cell transplant (HSCT) and importance of comprehensive psychosocial assessment ...during pre-transplant period is increasingly acknowledged. Psychosocial screening process, however, has not been standardized across transplant centers and its predictive value has not yet been confirmed. An observational cohort study was conducted to explore the relationships between psychosocial variables, assessed with the Psychosocial Assessment of Candidates for Transplantation (PACT) scale, and post-transplant overall survival (OS) of patients with hematologic malignancies who received allogeneic HSCT as treatment. Overall, 119 patient medical records were reviewed to determine the PACT score. After controlling for clinical and demographic covariates, lower PACT scores in the domain of compliance with medications and medical advice were significantly associated with poorer OS (HR = 1.75, P = 0.03). Lower PACT ratings in the subscales of personality and psychopathology (HR = 1.35, P = 0.08), lifestyle factors (HR = 1.43, P = 0.08), and relevant disease knowledge and receptiveness to education (HR = 1.32, P = 0.08) tended to be associated with shorter OS. These findings suggested the association between pre-transplant psychosocial factors using PACT and post-transplant OS in patients receiving allogeneic HSCT.
We previously reported a case that led us to hypothesize that decreased production of thrombopoietin (TPO) leads to thrombocytopenia in patients with anorexia nervosa (AN) with severe liver ...dysfunction and that prolonged prothrombin time-international normalized ratio (PT-INR) predicts thrombocytopenia in such cases. To validate this hypothesis, we report another case in which TPO levels were measured. In addition, we examined the association between prolonged PT-INR and thrombocytopenia in such patients.
Similar to the previously reported patient, a patient with AN with severe liver dysfunction showed that TPO levels increased after improvements in liver enzyme levels and PT-INR, followed by recovery of platelet count. In addition, a retrospective study was also conducted to review patients with AN whose liver enzyme levels were > 3 × the upper limit of normal (aspartate aminotransferase > 120 U/L or alanine aminotransferase > 135 U/L). The study included 58 patients and showed a correlation coefficient of -0.486 (95% confidence interval CI, -0.661 to -0.260; P < 0.001) between maximum PT-INR and minimum platelet count. These patients showed higher PT-INR (β, 0.07; 95% CI, 0.02 to 0.13; P = 0.005) and lower platelet count (β, -5.49; 95% CI, -7.47 to -3.52; P < 0.001) than the 58 matched control patients without severe liver dysfunction, even after adjusting for body mass index.
In patients with AN with severe liver dysfunction, prolongation of PT-INR could predict thrombocytopenia, which may be mediated by decreased TPO production due to decreased hepatic synthetic function.