Search

Background Pancreatic cancer is the third leading cause of cancer-related deaths, and although pancreatectomy is currently the only curative treatment, it is associated with significant morbidity. Objective The objective of this study was to evaluate the utility of wearable telemonitoring technologies to predict treatment outcomes using patient activity metrics and machine learning. Methods In this prospective, single-center, single-cohort study, patients scheduled for pancreatectomy were provided with a wearable telemonitoring device to be worn prior to surgery. Patient clinical data were collected and all patients were evaluated using the American College of Surgeons National Surgical Quality Improvement Program surgical risk calculator (ACS-NSQIP SRC). Machine learning models were developed to predict whether patients would have a textbook outcome and compared with the ACS-NSQIP SRC using area under the receiver operating characteristic (AUROC) curves. Results Between February 2019 and February 2020, 48 patients completed the study. Patient activity metrics were collected over an average of 27.8 days before surgery. Patients took an average of 4162.1 (SD 4052.6) steps per day and had an average heart rate of 75.6 (SD 14.8) beats per minute. Twenty-eight (58%) patients had a textbook outcome after pancreatectomy. The group of 20 (42%) patients who did not have a textbook outcome included 14 patients with severe complications and 11 patients requiring readmission. The ACS-NSQIP SRC had an AUROC curve of 0.6333 to predict failure to achieve a textbook outcome, while our model combining patient clinical characteristics and patient activity data achieved the highest performance with an AUROC curve of 0.7875. Conclusions Machine learning models outperformed ACS-NSQIP SRC estimates in predicting textbook outcomes after pancreatectomy. The highest performance was observed when machine learning models incorporated patient clinical characteristics and activity metrics.

Background Digital therapeutics are evidence-based therapeutic interventions driven by high-quality software programs for the treatment, prevention, or management of a medical disorder or disease. Many studies in the western population have shown the effectiveness of mobile app–based digital therapeutics for improving glycemic control in patients with type 2 diabetes (T2D). However, few studies have assessed similar outcomes in the South Asian population. Objective This study aims to investigate the real-world effectiveness of the Wellthy CARE digital therapeutic for improving glycemic control among the South Asian population of Indian origin. Methods We analyzed deidentified data from 102 patients with T2D from India enrolled in a 16-week structured self-management program delivered using the Wellthy CARE mobile app. Patients recorded their meals, weight, physical activity, and blood sugar in the app, and they received lessons on self-care behaviors (healthy eating, being active, monitoring, medication adherence, problem solving, healthy coping, and reducing risks); feedback provided by an artificial intelligence–powered chatbot; and periodic interactions with certified diabetes educators via voice calls and chats. The primary outcome of the program was a change in glycated hemoglobin A1c (HbA1c). Secondary outcomes included the difference between preintervention and postintervention fasting blood glucose (FBG) and postprandial blood glucose (PPBG) levels; changes in BMI and weight at the completion of 16 weeks; and the association between program engagement and the changes in HbA1c, FBG, and PPBG levels. Results At the end of 16 weeks, the average change in HbA1c was –0.49% (n=102; 95% CI −0.73 to 0.25; P Conclusions The use of the Wellthy CARE digital therapeutic for patients with T2D showed a significant reduction in the levels of HbA1c, FBG, and PPBG after 16 weeks. A higher level of participation showed improved glycemic control, suggesting the potential of the Wellthy CARE platform for better management of the disease.

Background Hypertension is a long-term medical condition. Electronic and mobile health care services can help patients to self-manage this condition. However, not all management is effective, possibly due to different levels of patient engagement (PE) with health care services. Health care provider follow-up is an intervention to promote PE and blood pressure (BP) control. Objective This study aimed to discover and characterize patterns of PE with a hypertension self-management app, investigate the effects of health care provider follow-up on PE, and identify the follow-up effects on BP in each PE pattern. Methods PE was represented as the number of days that a patient recorded self-measured BP per week. The study period was the first 4 weeks for a patient to engage in the hypertension management service. K-means algorithm was used to group patients by PE. There was compliance follow-up, regular follow-up, and abnormal follow-up in management. The follow-up effect was calculated by the change in PE (CPE) and the change in systolic blood pressure (CSBP, SBP) before and after each follow-up. Chi-square tests and z scores were used to ascertain the distribution of gender, age, education level, SBP, and the number of follow-ups in each cluster. The follow-up effect was identified by analysis of variances. Once a significant effect was detected, Bonferroni multiple comparisons were further conducted to identify the difference between 2 clusters. Results Patients were grouped into 4 clusters according to PE: (1) PE started low and dropped even lower (PELL), (2) PE started high and remained high (PEHH), (3) PE started high and dropped to low (PEHL), and (4) PE started low and rose to high (PELH). Significantly more patients over 60 years old were found in the PEHH cluster (P≤.05). Abnormal follow-up was significantly less frequent (P≤.05) in the PELL cluster. Compliance follow-up and regular follow-up can improve PE. In the clusters of PEHH and PELH, the improvement in PE in the first 3 weeks and the decrease in SBP in all 4 weeks were significant after follow-up. The SBP of the clusters of PELL and PELH decreased more (–6.1 mmHg and –8.4 mmHg) after follow-up in the first week. Conclusions Four distinct PE patterns were identified for patients engaging in the hypertension self-management app. Patients aged over 60 years had higher PE in terms of recording self-measured BP using the app. Once SBP reduced, patients with low PE tended to stop using the app, and a continued decline in PE occurred simultaneously with the increase in SBP. The duration and depth of the effect of health care provider follow-up were more significant in patients with high or increased engagement after follow-up.

Background Hypertension is associated with a large global disease burden with variable control rates across different regions and races. Telehealth has recently emerged as a health care strategy for managing chronic diseases, but there are few reports regarding the effects of synchronous telehealth services on home blood pressure (BP) control and variability. Objective The objective of this study is to investigate the effect of synchronous telehealth services with a digital platform on home BP. Methods This retrospective study was conducted by the Taiwan ELEctroHEALTH study group at the Telehealth Center of the National Taiwan University Hospital. We analyzed home BP data taken from 2888 patients with cardiovascular disease (CVD) enrolled in our telehealth program between 2009 to 2017. Of the 2888 patients with CVD, 348 (12.05%) patients who received home BP surveillance for ≥56 days were selected for BP analysis. Patients were stratified into three groups: (1) poorly controlled hypertension, (2) well-controlled hypertension, and (3) nonhypertension. The mean, SD, coefficient of variation (CV), and average real variability were calculated. Results Telehealth interventions significantly and steadily reduced systolic blood pressure (SBP) in the poorly controlled hypertension group from 144.8.2±9.2 to 133.7±10.2 mmHg after 2 months (P Conclusions Synchronous telehealth intervention may improve home BP control and decrease day-by-day home BP variability in patients with CVD.

Background Online physician reviews are an important source of information for prospective patients. In addition, they represent an untapped resource for studying the effects of gender on the doctor-patient relationship. Understanding gender differences in online reviews is important because it may impact the value of those reviews to patients. Documenting gender differences in patient experience may also help to improve the doctor-patient relationship. This is the first large-scale study of physician reviews to extensively investigate gender bias in online reviews or offer recommendations for improvements to online review systems to correct for gender bias and aid patients in selecting a physician. Objective This study examines 154,305 reviews from across the United States for all medical specialties. Our analysis includes a qualitative and quantitative examination of review content and physician rating with regard to doctor and reviewer gender. Methods A total of 154,305 reviews were sampled from Google Place reviews. Reviewer and doctor gender were inferred from names. Reviews were coded for overall patient experience (negative or positive) by collapsing a 5-star scale and coded for general categories (process, positive/negative soft skills), which were further subdivided into themes. Computational text processing methods were employed to apply this codebook to the entire data set, rendering it tractable to quantitative methods. Specifically, we estimated binary regression models to examine relationships between physician rating, patient experience themes, physician gender, and reviewer gender). Results Female reviewers wrote 60% more reviews than men. Male reviewers were more likely to give negative reviews (odds ratio [OR] 1.15, 95% CI 1.10-1.19; P Conclusions This work reinforces findings in the extensive literature on gender differences and gender bias in patient-physician interaction. Its novel contribution lies in highlighting gender differences in online reviews. These reviews inform patients’ choice of doctor and thus affect both patients and physicians. The evidence of gender bias documented here suggests review sites may be improved by providing information about gender differences, controlling for gender when presenting composite ratings for physicians, and helping users write less biased reviews.

Background The use of patient portals for presenting health-related patient data, such as blood test results, is becoming increasingly important in health practices. Patient portals have the potential to enhance patient health engagement, but content might be misinterpreted. Objective This study aimed to discover whether the way of presenting blood test outcomes in an electronic patient portal is associated with patient health engagement and whether this varies across different blood test outcomes. Methods A 2x3 between-subjects experiment was conducted among members of the Nivel Dutch Health Care Consumer Panel. All participants read a scenario in which they were asked to imagine themselves receiving blood test results. These results differed in terms of the presented blood values (ie, normal vs partially abnormal vs all abnormal) as well as in terms of whether the results were accompanied with explanatory text and visualization. Patient health engagement was measured both before (T0) and after (T1) participants were exposed to their fictive blood test results. Results A total 487 of 900 invited members responded (response rate 54%), of whom 50.3% (245/487) were female. The average age of the participants was 52.82 years (SD 15.41 years). Patient health engagement saw either a significant decrease or a nonsignificant difference in the experimental groups after viewing the blood test results. The mean difference was smaller in the groups that received blood test results with additional text and visualization (meanT0 5.33, SE 0.08; meanT1 5.14, SE 0.09; mean difference 0.19, SE 0.08, P=.02) compared with groups that received blood test results without explanatory text and visualization (meanT0 5.19, SE 0.08; meanT1 4.55, SE 0.09; mean difference 0.64, SE 0.08, P Conclusions Adding text and visualization features can attenuate the decrease in patient health engagement in participants who receive outcomes of a blood test via a patient portal, particularly when blood test results are (partly) normal. This suggests that explanatory text and visualization can be reassuring. Future research is warranted to determine whether these results can be generalized to a patient population who receive their actual blood test results.

Background Digital pain mapping allows for remote and ecological momentary assessment in patients over multiple time points spanning days to months. Frequent ecological assessments may reveal tendencies and fluctuations more clearly and provide insights into the trajectory of a patient’s pain. Objective The primary aim of this study is to remotely map and track the intensity and distribution of pain and discomfort (eg, burning, aching, and tingling) in patients with nonmalignant spinal referred pain over 12 weeks using a web-based app for digital pain mapping. The secondary aim is to explore the barriers of use by determining the differences in clinical and user characteristics between patients with good (regular users) and poor (nonregular users) reporting compliance. Methods Patients (N=91; n=53 women) with spinal referred pain were recruited using web-based and traditional in-house strategies. Patients were asked to submit weekly digital pain reports for 12 weeks. Each pain report consisted of digital pain drawings on a pseudo–three-dimensional body chart and pain intensity ratings. The pain drawings captured the distribution of pain and discomfort (pain quality descriptors) expressed as the total extent and location. Differences in weekly pain reports were explored using the total extent (pixels), current and usual pain intensity ratings, frequency of quality descriptor selection, and Jaccard similarity index. Validated e-questionnaires were completed at baseline to determine the patients’ characteristics (adapted Danish National Spine Register), disability (Oswestry Disability Index and Neck Disability Index), and pain catastrophizing (Pain Catastrophizing Scale) profiles. Barriers of use were assessed at 6 weeks using a health care–related usability and acceptance e-questionnaire and a self-developed technology-specific e-questionnaire to assess the accessibility and ease of access of the pain mapping app. Associations between total extent, pain intensity, disability, and catastrophizing were explored to further understand pain. Differences between regular and nonregular users were assessed to understand the pain mapping app reporting compliance. Results Fluctuations were identified in pain reports for total extent and pain intensity ratings (P Conclusions This is the first study to examine digital reports of pain intensity and distribution in patients with nonmalignant spinal referred pain remotely for a sustained period and barriers of use and compliance using a digital pain mapping app. Differences in age, pain distribution, and current pain intensity may influence reporting behavior and compliance.

Background The benefits of telemedicine include cost savings and decentralized care. Video consultation is one form that enables early detection of deteriorating patients and promotion of self-efficacy in patients who are well but anxious. Abdominal pain is a common symptom presented by patients in emergency departments. These patients could benefit from video consultation, as it enables remote follow-up of patients who do not require admission and facilitates early discharge of patients from overcrowded hospitals. Objective The study aimed to evaluate the safety and efficacy of the use of digital telereview in patients presenting with undifferentiated acute abdominal pain. Methods The SAVED study was a prospective randomized controlled trial in which follow-up using existing telephone-based telereview (control) was compared with digital telereview (intervention). Patients with undifferentiated acute abdominal pain discharged from the emergency department observation ward were studied based on intention-to-treat. The control arm received routine, provider-scheduled telereview with missed reviews actively coordinated and rescheduled by emergency department staff. The intervention arm received access to a platform for digital telereview (asynchronous and synchronous format) that enabled patient-led appointment rescheduling. Patients were followed-up for 2 weeks for outcomes of service utilization, efficacy (compliance with their disposition plan), and safety (re-presentation for the same condition). Results A total of 70 patients participated, with patients randomly assigned to each arm (1:1 ratio). Patients were a mean age of 40.0 (SD 13.8; range 22-71) years, predominantly female (47/70, 67%), and predominantly of Chinese ethnicity (39/70, 56%). The telereview service was used by 32 patients in the control arm (32/35, 91%) and 18 patients in the intervention arm (18/35, 51%). Most patients in control (33/35, 94%; 95% CI 79.5%-99.0%) and intervention (34/35, 97%; 95% CI 83.4%-99.9%) arms were compliant with their final disposition. There was a low rate of re-presentation at 72 hours and 2 weeks for both control (72 hours: 2/35, 6%; 95% CI 1.0%-20.5%; 2 weeks: 2/35, 6%, 95% CI 1.0%-20.5%) and intervention (72 hours: 2/35, 6%; 95% CI 1.0%-20.5%; 2 weeks: 3/35, 9%, 95% CI 2.2%-24.2%) arms. There were no significant differences in safety (P>.99) and efficacy (P>.99) between the two groups. Conclusions The application of digital telereview for the follow-up of patients with abdominal pain may be safe and effective. Future studies are needed to evaluate its cost-effectiveness and usefulness for broader clinical application. Trial Registration ISRCTN Registry ISRCTN28468556; http://www.isrctn.com/ISRCTN28468556.

Background Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity. Objective We aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems. Methods Sequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k–nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points—at admission, on Day 7, and at discharge—to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k–nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison. Results With all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission. Conclusions For patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance.

Background Attempts to use virtual reality (VR) as a treatment for various psychiatric disorders have been made recently, and many researchers have identified the effects of VR in psychiatric disorders. Studies have reported that VR therapy is effective in social anxiety disorder (SAD). However, there is no prior study on the neural correlates of VR therapy in patients with SAD. Objective The aim of this study is to find the neural correlates of VR therapy by evaluating the treatment effectiveness of VR in patients with SAD using portable functional near-infrared spectroscopy (fNIRS). Methods Patients with SAD (n=28) were provided with 6 sessions of VR treatment that was developed for exposure to social situations with a recording system of each participant’s self-introduction in VR. After each VR treatment session, the first-person view (video 1) and third-person view (video 2) clips of the participant’s self-introduction were automatically generated. The functional activities of prefrontal regions were measured by fNIRS while watching videos 1 and 2 with a cognitive task, before and after whole VR treatment sessions, and after the first session of VR treatment. We compared the data of fNIRS between patients with SAD and healthy controls (HCs; n=27). Results We found that reduction in activities of the right frontopolar prefrontal cortex (FPPFC) in HCs was greater than in the SAD group at baseline (t=–2.01, P=.049). Comparing the frontal cortex activation before and after VR treatment sessions in the SAD group showed significant differences in activities of the FPPFC (right: t=–2.93, P Conclusions Activities of the FPPFC and OFC were associated with symptom reduction after VR treatment for SAD. Our study findings might provide a clue to understanding the mechanisms underlying VR treatment for SAD. Trial Registration Clinical Research Information Service (CRIS) KCT0003854; https://tinyurl.com/559jp2kp

Background: Breast cancer patients have to face a high-risk state during chemotherapy, which involves deterioration of their health including extensive physical deterioration. Face-to-face physical exercise programs have presented low adherence rates during medical treatment, and telehealth systems could improve these adherence rates. Objective: This study aimed to evaluate the effectiveness of a Web-based exercise program (e-CuidateChemo) to mitigate the side effects of chemotherapy on the physical being, anthropometric aspects, and body composition. Results: Functional capacity improved significantly in the e-CuidateChemo group compared to the control group (6-minute walk test: 62.07 [SD 130.09] m versus –26.34 [SD 82.21] m; 6-minute walk test % distance predicted: 10.81% [SD 22.69%] m versus –4.60% [SD 14.58%]; between-group effect: P=.015 for both). The intervention group also showed significantly improved secondary outcomes such as between-group effects for abdominal (24.93 [SD 26.83] s vs –18.59 [SD 38.69] s), back (12.45 [SD 10.20] kg vs 1.39 [10.72] kg), and lower body (–2.82 [SD 3.75] s vs 1.26 [SD 2.84] s) strength; all P, The study was funded by a research project grant from the Andalusian Health Service, Junta de Andalucia, call for subsidies for the financing of biomedical research and health sciences in Andalusia (SAS-0457-2010) and by the Spanish Ministry of Education (FPU14/01069 and FPU17/00939).

Background: Decreased ambient temperature significantly increases office blood pressure, but few studies have evaluated the effect of ambient temperature on home blood pressure. Objective: We aimed to investigate the relationship between short-term ambient temperature exposure and home blood pressure. Methods: We recruited patients with chronic cardiovascular diseases from a telehealth care program at a university-affiliated hospital. Blood pressure was measured at home by patients or their caregivers. We obtained hourly meteorological data for Taipei (temperature, relative humidity, and wind speed) for the same time period from the Central Weather Bureau, Taiwan. Results: From 2009 to 2013, we enrolled a total of 253 patients. Mean patient age was 70.28 (SD 13.79) years, and 66.0% (167/253) of patients were male. We collected a total of 110,715 home blood pressure measurements. Ambient temperature had a negative linear effect on all 3 home blood pressure parameters after adjusting for demographic and clinical factors and antihypertensive agents. A 1°C decrease was associated with a 0.5492-mm Hg increase in mean blood pressure, a 0.6841-mm Hg increase in systolic blood pressure, and a 0.2709-mm Hg increase in diastolic blood pressure. This temperature effect on home blood pressure was less prominent in patients with diabetes or hypertension. Antihypertensive agents modified this negative effect of temperature on home blood pressure to some extent, and angiotensin receptor blockers had the most favorable results. Conclusions: Short-term exposure to low ambient temperature significantly increased home blood pressure in patients with chronic cardiovascular diseases. Antihypertensive agents may modify this effect.

Background The use of digital therapeutic solutions for rehabilitation of conditions such as osteoarthritis provides scalable access to rehabilitation. Few validated technological solutions exist to ensure supervision of users while they exercise at home. Motion Coach (Kaia Health GmbH) provides audiovisual feedback on exercise execution in real time on conventional smartphones. Objective We hypothesized that the interrater agreement between physiotherapists and Motion Coach would be noninferior to physiotherapists’ interrater agreement for exercise evaluations in a cohort with osteoarthritis. Methods Patients diagnosed with osteoarthritis of the knee or hip were recruited at a university hospital to perform a set of 6 exercises. Agreement between Motion Coach and 2 physiotherapists’ corrections for segments of the exercises were compared using Cohen κ and percent agreement. Results Participants (n=24) were enrolled and evaluated. There were no significant differences between interrater agreements (Motion Coach app vs physiotherapists: percent agreement 0.828; physiotherapist 1 vs physiotherapist 2: percent agreement 0.833; P Conclusions The results demonstrated that Motion Coach is noninferior to physiotherapist evaluations. Interrater agreement did not differ between 2 physiotherapists or between physiotherapists and the Motion Coach app. This finding was valid for all investigated exercises and subgroups. These results confirm the ability of Motion Coach to detect user form during exercise and provide valid feedback to users with musculoskeletal disorders.

Background Adherence to core type 2 diabetes mellitus (T2DM) treatment behaviors is suboptimal, and nonadherence is generally not limited to one treatment behavior. The internet holds promise for programs that aim to improve adherence. We developed a computer-tailored eHealth program for patients with T2DM to improve their treatment adherence, that is, adherence to both a healthy lifestyle and medical behaviors. Objective The objective of this study is to examine the effectiveness of the eHealth program in a randomized controlled trial. Methods Patients with T2DM were recruited by their health professionals and randomized into either the intervention group, that is, access to the eHealth program for 6 months, or a waiting-list control group. In total, 478 participants completed the baseline questionnaire, of which 234 gained access to the eHealth program. Of the 478 participants, 323 were male and 155 were female, the mean age was 60 years, and the participants had unfavorable BMI and HbA1c levels on average. Outcome data were collected through web-based assessments on physical activity (PA) levels, caloric intake from unhealthy snacks, and adherence to oral hypoglycemic agents (OHAs) and insulin therapy. Changes to separate behaviors were standardized and summed into a composite change score representing changes in the overall treatment adherence. Further standardization of this composite change score yielded the primary outcome, which can be interpreted as Cohen d (effect size). Standardized change scores observed in separate behaviors acted as secondary outcomes. Mixed linear regression analyses were conducted to examine the effectiveness of the intervention on overall and separate treatment behavior adherence, accommodating relevant covariates and patient nesting. Results After the 6-month follow-up assessment, 47.4% (111/234) of participants in the intervention group and 72.5% (177/244) of participants in the control group were retained. The overall treatment adherence improved significantly in the intervention group compared with the control group, reflected by a small effect size (d=0.27; 95% CI 0.032 to 0.509; P=.03). When considering changes in separate treatment behaviors, a significant decrease was observed only in caloric intake from unhealthy snacks in comparison with the control group (d=0.36; 95% CI 0.136 to 0.584; P=.002). For adherence to PA (d=−0.14; 95% CI −0.388 to 0.109; P=.27), OHAs (d=0.27; 95% CI −0.027 to 0.457; P=.08), and insulin therapy (d=0.35; 95% CI −0.066 to 0.773; P=.10), no significant changes were observed. These results from the unadjusted analyses were comparable with the results of the adjusted analyses, the per-protocol analyses, and the sensitivity analyses. Conclusions Our multibehavior program significantly improved the overall treatment adherence compared with the control group. To further enhance the impact of the intervention in the personal, societal, and economic areas, a wide-scale implementation of our eHealth intervention is suggested. Trial Registration Netherlands Trial Register NL664; https://www.trialregister.nl/trial/6664

Background Artificial intelligence (AI) is gaining increasing importance in many medical specialties, yet data on patients’ opinions on the use of AI in medicine are scarce. Objective This study aimed to investigate patients’ opinions on the use of AI in different aspects of the medical workflow and the level of control and supervision under which they would deem the application of AI in medicine acceptable. Methods Patients scheduled for computed tomography or magnetic resonance imaging voluntarily participated in an anonymized questionnaire between February 10, 2020, and May 24, 2020. Patient information, confidence in physicians vs AI in different clinical tasks, opinions on the control of AI, preference in cases of disagreement between AI and physicians, and acceptance of the use of AI for diagnosing and treating diseases of different severity were recorded. Results In total, 229 patients participated. Patients favored physicians over AI for all clinical tasks except for treatment planning based on current scientific evidence. In case of disagreement between physicians and AI regarding diagnosis and treatment planning, most patients preferred the physician’s opinion to AI (96.2% [153/159] vs 3.8% [6/159] and 94.8% [146/154] vs 5.2% [8/154], respectively; P=.001). AI supervised by a physician was considered more acceptable than AI without physician supervision at diagnosis (confidence rating 3.90 [SD 1.20] vs 1.64 [SD 1.03], respectively; P=.001) and therapy (3.77 [SD 1.18] vs 1.57 [SD 0.96], respectively; P=.001). Conclusions Patients favored physicians over AI in most clinical tasks and strongly preferred an application of AI with physician supervision. However, patients acknowledged that AI could help physicians integrate the most recent scientific evidence into medical care. Application of AI in medicine should be disclosed and controlled to protect patient interests and meet ethical standards.

Background Fatalities rarely occur in dental offices. Implications for clinicians may be deduced from scientific publications and internet reports about deaths in dental offices. Objective Data involving deaths in dental facilities were analyzed using Google as well as the PubMed database. By comparing both sources, we examined how internet data may enhance knowledge about deaths in dental offices obtained from scientific medical publications, which causes of death are published online, and how associated life-threatening emergencies may be prevented. Methods To retrieve relevant information, we searched Google for country-specific incidents of death in dental practices using the following keywords: “death at the dentist,” “death in dental practice,” and “dying at the dentist.” For PubMed searches, the following keywords were used: “dentistry and mortality,” “death and dental treatment,” “dentistry and fatal outcome,” and “death and dentistry.” Deaths associated with dental treatment in a dental facility, attributable causes of death, and documented ages of the deceased were included in our analysis. Deaths occurring in maxillofacial surgery or pre-existing diseases involved in the death (eg, cancer and abscesses) were excluded. A total of 128 cases from online publications and 71 cases from PubMed publications that met the inclusion criteria were analyzed using chi-square statistics after exclusion of duplicates. Results The comparison between the fatalities from internet (n=117) and PubMed (n=71) publications revealed that more casualties affecting minors appeared online than in PubMed literature (online 68/117, 58.1%; PubMed 20/71, 28%; P Conclusions Online and PubMed databases may increase awareness of life-threatening risks for patients during dental treatment. Negative aspects of anesthesia and sedation, as well as the number of deaths of young patients, were underestimated when reviewing PubMed literature only. Medical history of patients, medication dosages, and vital function monitoring are significant issues for practitioners. A high-impact finding from online reports was the underestimation of risks when performing sedation and even general anesthesia. Detailed knowledge of the definition and understanding of deep sedation and general anesthesia by dentists is of major concern. By avoiding potentially hazardous procedures, such as sedation-aided treatments performed solely by dentists, the risk of treatment-induced life-threatening emergencies may be reduced.

Background: Patients with hypothyroidism report poor health-related quality of life despite having undergone thyroid hormone replacement therapy (THRT). Understanding patient concerns regarding levothyroxine can help improve the treatment outcomes of THRT. Objective: This study aimed to (1) identify the distinctive themes in patient concerns regarding THRT, (2) determine whether patients have unique primary medication concerns specific to their demographics, and (3) determine the predictability of primary medication concerns on patient treatment satisfaction. Methods: We collected patient reviews from WebMD in the United States (1037 reviews about generic levothyroxine and 1075 reviews about the brand version) posted between September 1, 2007, and January 30, 2017. We used natural language processing to identify the themes of medication concerns. Multiple regression analyses were conducted in order to examine the predictability of the primary medication concerns on patient treatment satisfaction. Results: Natural language processing of the patient reviews of levothyroxine posted on a social networking site produced 6 distinctive themes of patient medication concerns related to levothyroxine treatment: how to take the drug, treatment initiation, dose adjustment, symptoms of pain, generic substitutability, and appearance. Patients had different primary medication concerns unique to their gender, age, and treatment duration. Furthermore, treatment satisfaction on levothyroxine depended on what primary medication concerns the patient had. Conclusions: Natural language processing of text content available on social media could identify different themes of patient medication concerns that can be validated in future studies to inform the design of tailored medication counseling for improved patient treatment satisfaction.

Background: Over 30 million people in the United States (over 9%) have been diagnosed with diabetes. About 25% of people with diabetes will experience a diabetic foot ulcer (DFU) in their lifetime. Unresolved DFUs may lead to sepsis and are the leading cause of lower-limb amputations. DFU rates can be reduced by screening patients with diabetes to enable risk-based interventions. Skin temperature assessment has been shown to reduce the risk of foot ulceration. While several tools have been developed to measure plantar temperatures, they only measure temperature once a day or are designed for clinic use only. In this report, wireless sensor-embedded socks designed for daily wear are introduced, which perform continuous temperature monitoring of the feet of persons with diabetes in the home environment. Combined with a mobile app, this wearable device informs the wearer about temperature increases in one foot relative to the other, to facilitate early detection of ulcers and timely intervention. Objective: A pilot study was conducted to assess the accuracy of sensors used in daily wear socks, obtain user feedback on how comfortable sensor-embedded socks were for home use, and examine whether observed temperatures correlated with clinical observations. Methods: Temperature accuracy of sensors was assessed both prior to incorporation in the socks, as well as in the completed design. The measured temperatures were compared to the reference standard, a high-precision thermostatic water bath in the range 20°C-40°C. A total of 35 patients, 18 years of age and older, with diabetic peripheral neuropathy were enrolled in a single-site study conducted under an Institutional Review Board–approved protocol. This study evaluated the usability of the sensor-embedded socks and correlated the observed temperatures with clinical findings. Results: The temperatures measured by the stand-alone sensors were within 0.2°C of the reference standard. In the sensor-embedded socks, across multiple measurements for each of the six sensors, a high agreement (R2=1) between temperatures measured and the reference standard was observed. Patients reported that the socks were easy to use and comfortable, ranking them at a median score of 9 or 10 for comfort and ease of use on a 10-point scale. Case studies are presented showing that the temperature differences observed between the feet were consistent with clinical observations. Conclusions: We report the first use of wireless continuous temperature monitoring for daily wear and home use in patients with diabetes and neuropathy. The wearers found the socks to be no different from standard socks. The temperature studies conducted show that the sensors used in the socks are reliable and accurate at detecting temperature and the findings matched clinical observations. Continuous temperature monitoring is a promising approach as an early warning system for foot ulcers, Charcot foot, and reulceration.

Background: Electronic patient portals provide a new method for sharing personal medical information with individual patients. Objective: Our aim was to review utilization patterns of the largest online patient portal in Canada's largest city. Methods: We conducted a 4-year time-trend analysis of aggregated anonymous utilization data of the MyChart patient portal at Sunnybrook Health Sciences Centre in Ontario, Canada, from January 1, 2012, through December 31, 2015. Prespecified analyses examined trends related to day (weekend vs weekday), season (July vs January), year (2012 vs 2015), and an extreme adverse weather event (ice storm of December 20-26, 2013). Primary endpoints included three measures of patient portal activity: registrations, logins, and pageviews. Results: We identified 32,325 patients who registered for a MyChart account during the study interval. Time-trend analysis showed no sign of attenuating registrations over time. Logins were frequent, averaged 734 total per day, and showed an increasing trend over time. Pageviews mirrored logins, averaged about 3029 total per day, and equated to about 5 pageviews during the average login. The most popular pageviews were clinical notes, followed by laboratory results and medical imaging reports. All measures of patient activity were lower on weekends compared to weekdays (P

Patient portals have emerged as a recognized digital health strategy. To date, research on patient portals has grown rapidly. However, there has been limited evaluation of the growing body of evidence on portal availability, use, clinical or health behavior and outcomes, and portal adoption over time.This paper aims to comprehensively consolidate the current state of evidence on patient portals using the umbrella review methodology, introduce our approach for evaluating evidence for quantitative and qualitative findings presented in included systematic reviews, and present a knowledge translation tool that can be used to inform all stages of patient portal adoption.For this study, a modified version of the Joanna Briggs Institute umbrella review method was used. Multiple databases were searched for systematic reviews focused on patient portals, and the final sample included 14 reviews. We conducted a meta-level synthesis of findings from quantitative, qualitative, and mixed methods primary studies reported in systematic reviews. We organized the umbrella review findings according to the Clinical Adoption Meta-Model (CAMM). Vote-counting, GRADE (Grading of Recommendations, Assessment, Development, and Evaluations), and CERQual (Confidence in the Evidence from Review of Qualitative Research) were used to assess the umbrella review evidence.Our knowledge translation tool summarizes the findings in the form of an evidence map. Organized by the CAMM categories, the map describes the following factors that influence portal adoption and effects over time: patient contexts, patient's interest and satisfaction, portal design, facilitators and barriers, providers' attitudes, service utilization, behavioral effects, clinical outcomes, and patient-reported outcomes. The map lists the theories and mechanisms recognized in the included portal research while identifying the need for business models and organizational theories that can inform all stages of portal adoption. Our GRADE and CERQual umbrella review evaluation resulted in the majority of evidence being rated as moderate to low, which reflects methodological issues in portal research, insufficient number of studies, or mixed results in specific focus areas. The 2 findings with a high rating of evidence were patients' interest in using portals for communication and the importance of a simple display of information in the portals. Over 40 portal features were identified in the umbrella review, with communication through secure messaging and appointment booking mentioned in all systematic reviews.Our umbrella review provides a meta-level synthesis to make sense of the evidence on patient portals from published systematic reviews. Unsystematic and variable reporting of portal features undermines the ability to evaluate and compare portal effects and overlooks the specific context of portal use. Research designs sensitive to the social, organizational, policy, and temporal dimensions are needed to better understand the underlying mechanisms and context that leverage the identified factors to improve portal use and effects.

Background An understanding of the technology acceptance of home-based cardiac telerehabilitation programs is paramount if they are to be designed and delivered to target the needs and preferences of patients with coronary heart disease; however, the current state of technology acceptance of home-based cardiac telerehabilitation has not been systematically evaluated in the literature. Objective We aimed to provide a comprehensive summary of home-based cardiac telerehabilitation technology acceptance in terms of (1) the timing and approaches used and (2) patients’ perspectives on its usability, utility, acceptability, acceptance, and external variables. Methods We searched PubMed, CENTRAL, Embase, CINAHL, PsycINFO, and Scopus (inception to July 2021) for English-language papers that reported empirical evidence on the technology acceptance of early-phase home-based cardiac telerehabilitation in patients with coronary heart disease. Content analysis was undertaken. Results The search identified 1798 studies, of which 18 studies, with 14 unique home-based cardiac telerehabilitation programs, met eligibility criteria. Technology acceptance (of the home-based cardiac telerehabilitation programs) was mostly evaluated at intra- and posttrial stages using questionnaires (n=10) and usage data (n=11). The least used approach was evaluation through qualitative interviews (n=3). Usability, utility, acceptability, and acceptance were generally favored. External variables that influenced home-based cardiac telerehabilitation usage included component quality, system quality, facilitating conditions, and intrinsic factors. Conclusions Home-based cardiac telerehabilitation usability, utility, acceptability, and acceptance were high; yet, a number of external variables influenced acceptance. Findings and recommendations from this review can provide guidance for developing and evaluating patient-centered home-based cardiac telerehabilitation programs to stakeholders and clinicians.