Search

BackgroundSuicide is an important public health concern in the United States and around the world. There has been significant work examining machine learning approaches to identify and predict intentional self-harm and suicide using existing data sets. With recent advances in computing, deep learning applications in health care are gaining momentum. ObjectiveThis study aimed to leverage the information in clinical notes using deep neural networks (DNNs) to (1) improve the identification of patients treated for intentional self-harm and (2) predict future self-harm events. MethodsWe extracted clinical text notes from electronic health records (EHRs) of 835 patients with International Classification of Diseases (ICD) codes for intentional self-harm and 1670 matched controls who never had any intentional self-harm ICD codes. The data were divided into training and holdout test sets. We tested a number of algorithms on clinical notes associated with the intentional self-harm codes using the training set, including several traditional bag-of-words–based models and 2 DNN models: a convolutional neural network (CNN) and a long short-term memory model. We also evaluated the predictive performance of the DNNs on a subset of patients who had clinical notes 1 to 6 months before the first intentional self-harm event. Finally, we evaluated the impact of a pretrained model using Word2vec (W2V) on performance. ResultsThe area under the receiver operating characteristic curve (AUC) for the CNN on the phenotyping task, that is, the detection of intentional self-harm in clinical notes concurrent with the events was 0.999, with an F1 score of 0.985. In the predictive task, the CNN achieved the highest performance with an AUC of 0.882 and an F1 score of 0.769. Although pretraining with W2V shortened the DNN training time, it did not improve performance. ConclusionsThe strong performance on the first task, namely, phenotyping based on clinical notes, suggests that such models could be used effectively for surveillance of intentional self-harm in clinical text in an EHR. The modest performance on the predictive task notwithstanding, the results using DNN models on clinical text alone are competitive with other reports in the literature using risk factors from structured EHR data.

Background: Depression is prevalent among individuals who smoke cigarettes and increases risk for relapse. A previous clinical trial suggests that Goal2Quit, a behavioral activation-based smoking cessation mobile app, effectively increases smoking abstinence and reduces depressive symptoms. Objective: Secondary analyses were conducted on these trial data to identify predictors of success in depression-specific digitalized cessation interventions. Methods: Adult who smoked cigarettes (age = 38.4 ± 10.3, 53% women) were randomized to either use Goal2Quit for 12 weeks (N = 103), paired with a 2-week sample of nicotine replacement therapy (patch and lozenge) or to a Treatment-As-Usual (TAU) control (N = 47). The least absolute shrinkage and selection operator was utilized to identify a subset of baseline variables predicting either smoking or depression intervention outcomes. The retained predictors were then fitted via linear regression models to determine relations to each intervention outcome. Results: Relative to TAU, only individuals who spent significant time using Goal2Quit (56 ± 46 min) were more likely to reduce cigarette use by at least 50% after 12 weeks, whereas those who spent minimal time using Goal2Quit (10 ± 2 min) did not exhibit significant changes. An interaction between educational attainment and treatment group revealed that, as compared to TAU, only app users with an educational degree beyond high school exhibited significant reductions in depression. Conclusions: The findings highlight the importance of tailoring depression-specific digital cessation interventions to individuals' unique engagement needs and educational level. This study provides a potential methodological template for future research aimed at personalizing technology-based treatments for cigarette users with depressive symptoms. [ABSTRACT FROM AUTHOR]

Objectives: Cigarette smoking negatively affects oral health. Nicotine replacement therapies (NRT; e.g. nicotine patch or lozenge) and brief interventions (e.g. Ask‐Advise‐Refer; AAR) can improve cessation outcomes but are underutilized. NRT sampling (NRTS) increases NRT utilization by providing patients with samples of NRT as part of routine healthcare. Ask‐Advise‐Refer is a brief intervention where practitioners: ask patients about tobacco use, advise those using tobacco to quit and refer to the state quit line. The objective of this qualitative study was to explore dental care practitioners' and patients' attitudes and experiences regarding tobacco cessation treatment and perceptions of two brief intervention models, assessed separately: NRTS and AAR. Methods: Twenty‐four dental care practitioners and nine patients, recruited through the National Dental Practice‐Based Research Network, participated in semi‐structured telephone interviews. Interviews assessed experiences with tobacco use intervention and attitudes towards NRTS and AAR. Thematic analysis identified emergent themes related to feasibility and acceptability of NRTS and AAR. Results: Practitioners varied on how they address tobacco use, from systematically to idiosyncratically. Some practitioners recommend NRT; few had prescribed it. Practitioners had favourable attitudes towards AAR and NRTS, with most believing that both interventions would be acceptable and feasible to implement. Concerns regarding AAR were time and patient resistance to discussing tobacco use. Concerns regarding NRTS were patient resistance to using NRT, side effects or medication interactions, and capacity to provide follow‐up. Patients reported that oral health practitioners generally ask about tobacco use but do not provide interventions. Patients were open to discussing their tobacco use with practitioners and had favourable attitudes about NRTS. Conclusions: This formative work suggests that NRTS and AAR may be feasible to implement in dental care settings. Future studies are needed to assess the effectiveness and implementation potential of NRTS in dental care settings. [ABSTRACT FROM AUTHOR]

Introduction To improve the feasibility of remote biochemical verification of smoking status, our team developed "COast," a mobile app integrated with REDCap that allows a research participant to complete self-report research assessments and provide a breath sample via the iCOQuit Smokerlyzer for the purposes of carbon monoxide (CO) testing. The aims of the present study were to examine (1) the validity of remote CO data capture using COast as compared to gold-standard approaches (salivary cotinine, stand-alone CO monitor) and (2) the feasibility of remote CO data capture using COast as applied to both daily and weekly CO collection schedules. Methods Participants (N  = 143, 59% Female), including recently quit (n  = 36) and current (n  = 107) smokers, completed a baseline video session to capture validity data, and then were randomized to daily or weekly CO monitoring for a period of 1 month. Results Balancing both sensitivity and specificity, optimal cut-points for defining abstinence using the COast system were <4 parts per million (ppm) with salivary cotinine as the referent (Sensitivity = 100%, Specificity = 92.8%) and <8 ppm with the stand-alone CO monitor as the referent (Sensitivity = 100%, Specificity = 88.9%). Compliance across groups with CO monitoring was high with average compliance of 74% for the daily group and 84% for the weekly group. Self-reported feasibility and acceptability of using the system were strong. Conclusions Pairing the iCOQuit with REDCap via the COast app was both valid and feasible among a sample of adults who smoke cigarettes enrolled remotely. This integration may help to improve the rigor of decentralized smoking cessation trials. Implications With increasing prevalence of decentralized trial designs, innovative methods are needed to remotely capture biomarkers. Methods that leverage existing widely available research data capture platforms may be particularly useful for promoting adoption. The COast app, which integrates a Bluetooth-enabled CO monitor with REDCap, is a fitting, valid, and feasible solution to remotely biochemically verify smoking status. [ABSTRACT FROM AUTHOR]