RESUMEN

PROBLEM: Existing quantitative data is conflicting concerning whether multiparous birthing parents (individuals with an older child(ren)) experience an easier postpartum transition compared to primiparous birthing parents (first time parents). AIM: This convergent mixed methods study leverages the depth of qualitative inquiry to seek a clearer understanding of the way in which acquired parenting experience contributes to observed quantitative differences in outcomes between parity groups. This work can serve as a first step in planning for supportive interventions that effectively address the postpartum needs of both parity groups. METHODS: Thirty birthing parents (43.3% multiparous; 46.7% racial minorities) completed measures of postpartum functioning, perceived stress, anxiety symptoms, and depression symptoms as well as an interview inquiring about factors impacting postpartum functioning. Scores on postpartum functioning and emotional wellbeing were compared between parity groups, and these findings were merged with the qualitative data on firsthand parenting experience to clarify how acquired experience impacts functioning and emotional wellbeing during the postpartum transition. FINDINGS: Primiparous parents reported significantly: worse postpartum functioning, higher perceived stress, higher levels of depression symptoms, and higher levels of anxiety symptoms. Participants' qualitative report of how acquired parenting experience impacts wellbeing suggests that experience grants parents skills, knowledge, and the opportunity to disconfirm maladaptive cognitions about parenting which allows for increased comfort and confidence in the parental role. CONCLUSIONS: The practical and psychological resources gained from acquiring parenting experience during one's first postpartum period appear to be brought forward into subsequent pregnancies and protect against threats to functioning and emotional wellbeing.

Asunto(s)

RESUMEN

BACKGROUND: Usage of medication brand names in electronic health records may introduce conflicts of interest, perpetuate false perceptions of brand superiority, alter prescribing practices, and cause confusion leading to errors. OBJECTIVE: We sought to identify the frequency of brand name medication usage in clinical documentation, as well as factors associated with increased usage. DESIGNS, SETTINGS, AND PARTICIPANTS: We conducted a retrospective analysis of all clinical documentation written at our healthcare system (a multifacility academic urban healthcare system) between 2015 and 2020. MAIN OUTCOMES AND MEASURES: We used string-matching and regular expressions to identify medication mentions. We conducted bivariate analyses to identify associations between brand name usage and author-, note-, and medication-level factors, and a multivariate Poisson regression to clarify independent associations between individual factors and brand usage. RESULTS: A total of 104,456,653 notes from 37,285 unique authors were included in our analysis. A total of 162,906,009 medication mentions were identified, of which 36.0% were brand name mentions with a steady year-over-year decrease. Factors associated with the usage of a brand name include: author role, years since release, length and syllabic complexity of the generic name, service type, and encounter context. Over-the-counter availability did not affect usage. There was sizable individual variation between note writers.

Asunto(s)

RESUMEN

OBJECTIVE: To develop an automated deidentification pipeline for radiology reports that detect protected health information (PHI) entities and replaces them with realistic surrogates "hiding in plain sight." MATERIALS AND METHODS: In this retrospective study, 999 chest X-ray and CT reports collected between November 2019 and November 2020 were annotated for PHI at the token level and combined with 3001 X-rays and 2193 medical notes previously labeled, forming a large multi-institutional and cross-domain dataset of 6193 documents. Two radiology test sets, from a known and a new institution, as well as i2b2 2006 and 2014 test sets, served as an evaluation set to estimate model performance and to compare it with previously released deidentification tools. Several PHI detection models were developed based on different training datasets, fine-tuning approaches and data augmentation techniques, and a synthetic PHI generation algorithm. These models were compared using metrics such as precision, recall and F1 score, as well as paired samples Wilcoxon tests. RESULTS: Our best PHI detection model achieves 97.9 F1 score on radiology reports from a known institution, 99.6 from a new institution, 99.5 on i2b2 2006, and 98.9 on i2b2 2014. On reports from a known institution, it achieves 99.1 recall of detecting the core of each PHI span. DISCUSSION: Our model outperforms all deidentifiers it was compared to on all test sets as well as human labelers on i2b2 2014 data. It enables accurate and automatic deidentification of radiology reports. CONCLUSIONS: A transformer-based deidentification pipeline can achieve state-of-the-art performance for deidentifying radiology reports and other medical documents.

Asunto(s)

RESUMEN

Importance: Duplicated text is a well-documented hazard in electronic medical records (EMRs), leading to wasted clinician time, medical error, and burnout. This study hypothesizes that text duplication is prevalent and increases with time and EMR size and that duplicate information is shared across authors. Objective: To examine the prevalence and scope of duplication behavior in clinical notes from a large academic health system and the factors associated with duplication. Design, Setting, and Participants: This retrospective, cross-sectional analysis of note length and content duplication rates used a set of 10 adjacent word tokens (ie, a 10-gram) sliding-window approach to identify spans of text duplicated exactly from earlier notes in a patient's record for all inpatient and outpatient notes written within the University of Pennsylvania Health System from January 1, 2015, through December 31, 2020. Text duplicated from a different author vs text duplicated from the same author was quantified. Furthermore, novel text and duplicated text per author for various note types and author types, as well as per patient record by number of notes in the record, were quantified. Information scatter, another documentation hazard, was defined as the inverse of novel text per note, and the association between information duplication and information scatter was graphed. Data analysis was performed from January to March 2022. Main Outcomes and Measures: Total, novel, and duplicate text by note type and note author were determined, as were the mean intra-author and inter-author duplication per note by type and author. Results: There were a total of 104 456 653 notes for 1 960 689 unique patients consisting of 32 991 489 889 words; 50.1% of the total text in the record (16 523 851 210 words) was duplicated from prior text written about the same patient. The duplication fraction increased year-over-year, from 33.0% for notes written in 2015 to 54.2% for notes written in 2020. Of the text duplicated, 54.1% came from text written by the same author, whereas 45.9% was duplicated from a different author. Records with more notes had more total duplicate text, approaching 60%. Note types with high information scatter tended to have low information overload, and vice versa, suggesting a trade-off between these 2 hazards under the current documentation paradigm. Conclusions and Relevance: Duplicate text casts doubt on the veracity of all information in the medical record, making it difficult to find and verify information in day-to-day clinical work. The findings of this cross-sectional study suggest that text duplication is a systemic hazard, requiring systemic interventions to fix, and simple solutions such as banning copy-paste may have unintended consequences, such as worsening information scatter. The note paradigm should be further examined as a major cause of duplication and scatter, and alternative paradigms should be evaluated.

Asunto(s)

RESUMEN

Natural language processing (NLP) techniques for electronic health records have shown great potential to improve the quality of medical care. The text of radiology reports frequently constitutes a large fraction of EHR data, and can provide valuable information about patients' diagnoses, medical history, and imaging findings. The lack of a major public repository for radiological reports severely limits the development, testing, and application of new NLP tools. De-identification of protected health information (PHI) presents a major challenge to building such repositories, as many automated tools for de-identification were trained or designed for clinical notes and do not perform sufficiently well to build a public database of radiology reports. We developed and evaluated six ensemble models based on three publically available de-identification tools: MIT de-id, NeuroNER, and Philter. A set of 1023 reports was set aside as the testing partition. Two individuals with medical training annotated the test set for PHI; differences were resolved by consensus. Ensemble methods included simple voting schemes (1-Vote, 2-Votes, and 3-Votes), a decision tree, a naïve Bayesian classifier, and Adaboost boosting. The 1-Vote ensemble achieved recall of 998 / 1043 (95.7%); the 3-Votes ensemble had precision of 1035 / 1043 (99.2%). F1 scores were: 93.4% for the decision tree, 71.2% for the naïve Bayesian classifier, and 87.5% for the boosting method. Basic voting algorithms and machine learning classifiers incorporating the predictions of multiple tools can outperform each tool acting alone in de-identifying radiology reports. Ensemble methods hold substantial potential to improve automated de-identification tools for radiology reports to make such reports more available for research use to improve patient care and outcomes.

Asunto(s)

RESUMEN

During the postpartum period, a birth parent's level of functioning (ability to perform the activities and roles required to maintain wellbeing) is critical in determining the health of parents and their infants. However, existing approaches to support postpartum parents are insufficient, especially in the United States, and these individuals face barriers to care. The utilization of internet-based intervention may be an effective solution allowing access to resources for this population. In this study, we developed a patient-centered online tool to bolster postpartum functioning, and collected data on the feasibility, acceptability, and initial impact of this tool on functioning and emotional wellbeing. Data collection took place between February and June 2021 from a sample of 124 individuals who were within the first ten months postpartum and living in the US. Results suggest that the tool is acceptable, though there are barriers to feasibility of use. Additionally, pilot-efficacy data suggest that this tool may be effective in improving postpartum emotional wellbeing, though further controlled testing is warranted. A future iteration of the tool that incorporates participant feedback to improve feasibility of use could prove an effective means of delivering support to an at-risk population.

RESUMEN

Background: Increasing buprenorphine/naloxone (B/N) access for opioid use disorder (OUD) is essential yet ensuring adherence and preventing diversion remains challenging. This study examines the feasibility, usability, and acceptability of MySafeRx, a mobile platform integrating motivational coaching, adherence monitoring, and electronic dispensing during office-based B/N treatment. Methods: In this multi-site randomized controlled trial, MySafeRx provided coaching and supervised self-administration of B/N by mobile recovery coaches (MRCs) via videoconference. Referred adults (ages 18-65) with OUD were randomized to 1) 42-days of adjunctive MySafeRx treatment (n = 13) or 2) a standard care control group (n = 14). Results: The randomized sample was 63% female and 100% White. Twelve of 13 MySafeRx participants completed at least one MRC session. The mean system usability score reported by MySafeRx participants was 78.4 (n = 12). Participants indicated they would recommend MySafeRx to a friend (mean= 4.1 of 5), and that the dispenser (4.1 of 5) and videoconferencing (4.2 of 5) were easy to use. The MRC component had the highest acceptability (4.4 of 5). MRCs observed B/N self-administration for an average of 64.3% of the required study days (men: 68.9%; women: 57.9%). On average, men (n = 4) met with MRCs on 32±14 days versus 47±6 days for women (n = 8). Exploratory analyses did not show significant differences between intervention and control groups. Conclusions: Despite the small sample, this study supports usability and acceptability of MySafeRx. Increased adherence monitoring, even with remote coaching had limited appeal, which impacted feasibility due to slow recruitment, especially as community prescribing with relaxed monitoring requirements became more widespread.

RESUMEN

BACKGROUND: Clinical workflows require the ability to synthesize and act on existing and emerging patient information. While offering multiple benefits, in many circumstances electronic health records (EHRs) do not adequately support these needs. OBJECTIVES: We sought to design, build, and implement an EHR-connected rounding and handoff tool with real-time data that supports care plan organization and team-based care. This article first describes our process, from ideation and development through implementation; and second, the research findings of objective use, efficacy, and efficiency, along with qualitative assessments of user experience. METHODS: Guided by user-centered design and Agile development methodologies, our interdisciplinary team designed and built Carelign as a responsive web application, accessible from any mobile or desktop device, that gathers and integrates data from a health care institution's information systems. Implementation and iterative improvements spanned January to July 2016. We assessed acceptance via usage metrics, user observations, time-motion studies, and user surveys. RESULTS: By July 2016, Carelign was implemented on 152 of 169 total inpatient services across three hospitals staffing 1,616 hospital beds. Acceptance was near-immediate: in July 2016, 3,275 average unique weekly users generated 26,981 average weekly access sessions; these metrics remained steady over the following 4 years. In 2016 and 2018 surveys, users positively rated Carelign's workflow integration, support of clinical activities, and overall impact on work life. CONCLUSION: User-focused design, multidisciplinary development teams, and rapid iteration enabled creation, adoption, and sustained use of a patient-centered digital workflow tool that supports diverse users' and teams' evolving care plan organization needs.

Asunto(s)

RESUMEN

BACKGROUND: Clinicians spend large amounts of their workday using electronic medical records (EMRs). Poorly designed documentation systems contribute to the proliferation of out-of-date information, increased time spent on medical records, clinician burnout, and medical errors. Beyond software interfaces, examining the underlying paradigms and organizational structures for clinical information may provide insights into ways to improve documentation systems. In particular, our attachment to the note as the major organizational unit for storing unstructured medical data may be a cause of many of the problems with modern clinical documentation. Notes, as currently understood, systematically incentivize information duplication and information scattering, both within a single clinician's notes over time and across multiple clinicians' notes. Therefore, it is worthwhile to explore alternative paradigms for unstructured data organization. OBJECTIVE: The aim of this study is to demonstrate the feasibility of building an EMR that does not use notes as the core organizational unit for unstructured data and which is designed specifically to disincentivize information duplication and information scattering. METHODS: We used specific design principles to minimize the incentive for users to duplicate and scatter information. By default, the majority of a patient's medical history remains the same over time, so users should not have to redocument that information. Clinicians on different teams or services mostly share the same medical information, so all data should be collaboratively shared across teams and services (while still allowing for disagreement and nuance). In all cases where a clinician must state that information has remained the same, they should be able to attest to the information without redocumenting it. We designed and built a web-based EMR based on these design principles. RESULTS: We built a medical documentation system that does not use notes and instead treats the chart as a single, dynamically updating, and fully collaborative workspace. All information is organized by clinical topic or problem. Version history functionality is used to enable granular tracking of changes over time. Our system is highly customizable to individual workflows and enables each individual user to decide which data should be structured and which should be unstructured, enabling individuals to leverage the advantages of structured templating and clinical decision support as desired without requiring programming knowledge. The system is designed to facilitate real-time, fully collaborative documentation and communication among multiple clinicians. CONCLUSIONS: We demonstrated the feasibility of building a non-note-based, fully collaborative EMR system. Our attachment to the note as the only possible atomic unit of unstructured medical data should be reevaluated, and alternative models should be considered.

RESUMEN

Natural language processing (NLP) is a subfield of computer science and linguistics that can be applied to extract meaningful information from radiology reports. Symbolic NLP is rule based and well suited to problems that can be explicitly defined by a set of rules. Statistical NLP is better situated to problems that cannot be well defined and requires annotated or labeled examples from which machine learning algorithms can infer the rules. Both symbolic and statistical NLP have found success in a variety of radiology use cases. More recently, deep learning approaches, including transformers, have gained traction and demonstrated good performance.

Asunto(s)

RESUMEN

Clinicians spend a substantial part of their workday reviewing and writing electronic medical notes. Here we describe how the current, widely accepted paradigm for electronic medical notes represents a poor organizational framework for both the individual clinician and the broader medical team. As described in this viewpoint, the medical chart-including notes, labs, and imaging results-can be reconceptualized as a dynamic, fully collaborative workspace organized by topic rather than time, writer, or data type. This revised framework enables a more accurate and complete assessment of the current state of the patient and easy historical review, saving clinicians substantial time on both data input and retrieval. Collectively, this approach has the potential to improve health care delivery effectiveness and efficiency.

Asunto(s)

RESUMEN

Recommendations are a key component of radiology reports. Automatic extraction of recommendations would facilitate tasks such as recommendation tracking, quality improvement, and large-scale descriptive studies. Existing report-parsing systems are frequently limited to recommendations for follow-up imaging studies, operate at the sentence or document level rather than the individual recommendation level, and do not extract important contextualizing information. We present a neural network architecture capable of extracting fully contextualized recommendations from any type of radiology report. We identified six major "questions" necessary to capture the majority of context associated with a recommendation: recommendation, time period, reason, conditionality, strength, and negation. We developed a unified task representation by allowing questions to refer to answers to other questions. Our representation allows for a single system to perform named entity recognition (NER) and classification tasks. We annotated 2272 radiology reports from all specialties, imaging modalities, and multiple hospitals across our institution. We evaluated the performance of a long short-term memory (LSTM) architecture on the six-question task. The single-task LSTM model achieves a token-level performance of 89.2% at recommendation extraction, and token-level performances between 85 and 95% F1 on extracting modifying features. Our model extracts all types of recommendations, including follow-up imaging, tissue biopsies, and clinical correlation, and can operate in real time. It is feasible to extract complete contextualized recommendations of all types from arbitrary radiology reports. The approach is likely generalizable to other clinical entities referenced in radiology reports, such as radiologic findings or diagnoses.

Asunto(s)

RESUMEN

BACKGROUND: Incidental radiographic findings, such as adrenal nodules, are commonly identified in imaging studies and documented in radiology reports. However, patients with such findings frequently do not receive appropriate follow-up, partially due to the lack of tools for the management of such findings and the time required to maintain up-to-date lists. Natural language processing (NLP) is capable of extracting information from free-text clinical documents and could provide the basis for software solutions that do not require changes to clinical workflows. OBJECTIVES: In this manuscript we present (1) a machine learning algorithm we trained to identify radiology reports documenting the presence of a newly discovered adrenal incidentaloma, and (2) the web application and results database we developed to manage these clinical findings. METHODS: We manually annotated a training corpus of 4,090 radiology reports from across our institution with a binary label indicating whether or not a report contains a newly discovered adrenal incidentaloma. We trained a convolutional neural network to perform this text classification task. Over the NLP backbone we built a web application that allows users to coordinate clinical management of adrenal incidentalomas in real time. RESULTS: The annotated dataset included 404 positive (9.9%) and 3,686 (90.1%) negative reports. Our model achieved a sensitivity of 92.9% (95% confidence interval: 80.9-97.5%), a positive predictive value of 83.0% (69.9-91.1)%, a specificity of 97.8% (95.8-98.9)%, and an F1 score of 87.6%. We developed a front-end web application based on the model's output. CONCLUSION: Developing an NLP-enabled custom web application for tracking and management of high-risk adrenal incidentalomas is feasible in a resource constrained, safety net hospital. Such applications can be used by an institution's quality department or its primary care providers and can easily be generalized to other types of clinical findings.

Asunto(s)

RESUMEN

During the first twelve months postpartum, infants require intensive care and mothers are susceptible to physical and mental health concerns as they undergo a period of tremendous psychological and physiological adjustment. The mother's level of postpartum functioning not only impacts her experience as a mother but also the infant and family unit. However, efforts to bolster functioning are lacking, and previous literature has identified a gap between what experts recommend and what mothers desire during the postpartum period. To address this, we conducted structured interviews with a diverse sample of 30 postpartum mothers to identify factors that mothers report are most influential to their postpartum functioning. In total, we identified 23 clinically actionable factors, all of which are backed by existing literature. In addition to an in-depth presentation of the qualitative findings, we also present a heat map to visualize the relevance of these factors to each of seven established domains of maternal functioning. Lastly, based on our findings, we offer a taxonomy of interventional strategies that could bolster maternal functioning during this critical period.

Asunto(s)

RESUMEN

INTRODUCTION: Machine learning (ML) and natural language processing have great potential to improve information extraction (IE) within electronic medical records (EMRs) for a wide variety of clinical search and summarization tools. Despite ML advancements, clinical adoption of real time IE tools for patient care remains low. Clinically motivated IE task definitions, publicly available annotated clinical datasets, and inclusion of subtasks such as coreference resolution and named entity normalization are critical for the development of useful clinical tools. MATERIALS AND METHODS: We provide a task definition and comprehensive annotation requirements for a clinically motivated symptom extraction task. Four annotators labeled symptom mentions within 1108 discharge summaries from two public clinical note datasets for the tasks of named entity recognition, coreference resolution, and named entity normalization; these annotations will be released to the public. Baseline human performance was assessed and two ML models were evaluated on the symptom extraction task. RESULTS: 16,922 symptom mentions were identified within the discharge summaries, with 11,944 symptom instances after coreference resolution and 1255 unique normalized answer forms. Human annotator performance averaged 92.2% F1. Recurrent network model performance was 85.6% F1 (recall 85.8%, precision 85.4%), and Transformer-based model performance was 86.3% F1 (recall 86.6%, precision 86.1%). Our models extracted vague symptoms, acronyms, typographical errors, and grouping statements. The models generalized effectively to a separate clinical note corpus and can run in real time. CONCLUSION: To our knowledge, this dataset will be the largest and most comprehensive publicly released, annotated dataset for clinically motivated symptom extraction, as it includes annotations for named entity recognition, coreference, and normalization for more than 1000 clinical documents. Our neural network models extracted symptoms from unstructured clinical free text at near human performance in real time. In this paper, we present a clinically motivated task definition, dataset, and simple supervised natural language processing models to demonstrate the feasibility of building clinically applicable information extraction tools.

Asunto(s)

RESUMEN

PURPOSE: To evaluate publicly available de-identification tools on a large corpus of narrative-text radiology reports. MATERIALS AND METHODS: In this retrospective study, 21 categories of protected health information (PHI) in 2503 radiology reports were annotated from a large multihospital academic health system, collected between January 1, 2012 and January 8, 2019. A subset consisting of 1023 reports served as a test set; the remainder were used as domain-specific training data. The types and frequencies of PHI present within the reports were tallied. Five public de-identification tools were evaluated: MITRE Identification Scrubber Toolkit, U.S. National Library of Medicine‒Scrubber, Massachusetts Institute of Technology de-identification software, Emory Health Information DE-identification (HIDE) software, and Neuro named-entity recognition (NeuroNER). The tools were compared using metrics including recall, precision, and F1 score (the harmonic mean of recall and precision) for each category of PHI. RESULTS: The annotators identified 3528 spans of PHI text within the 2503 reports. Cohen κ for interrater agreement was 0.938. Dates accounted for the majority of PHI found in the dataset of radiology reports (n = 2755 [78%]). The two best-performing tools both used machine learning methods-NeuroNER (precision, 94.5%; recall, 92.6%; microaveraged F1 score [F1], 93.6%) and Emory HIDE (precision, 96.6%; recall, 88.2%; F1, 92.2%)-but none exceeded 50% F1 on the important patient names category. CONCLUSION: PHI appeared infrequently within the corpus of reports studied, which created difficulties for training machine learning systems. Out-of-the-box de-identification tools achieved limited performance on the corpus of radiology reports, suggesting the need for further advancements in public datasets and trained models.Supplemental material is available for this article.See also the commentary by Tenenholtz and Wood in this issue.© RSNA, 2020.

RESUMEN

Unstructured and semi-structured radiology reports represent an underutilized trove of information for machine learning (ML)-based clinical informatics applications, including abnormality tracking systems, research cohort identification, point-of-care summarization, semi-automated report writing, and as a source of weak data labels for training image processing systems. Clinical ML systems must be interpretable to ensure user trust. To create interpretable models applicable to all of these tasks, we can build general-purpose systems which extract all relevant human-level assertions or "facts" documented in reports; identifying these facts is an information extraction (IE) task. Previous IE work in radiology has focused on a limited set of information, and extracts isolated entities (i.e., single words such as "lesion" or "cyst") rather than complete facts, which require the linking of multiple entities and modifiers. Here, we develop a prototype system to extract all useful information in abdominopelvic radiology reports (findings, recommendations, clinical history, procedures, imaging indications and limitations, etc.), in the form of complete, contextualized facts. We construct an information schema to capture the bulk of information in reports, develop real-time ML models to extract this information, and demonstrate the feasibility and performance of the system.

Asunto(s)

RESUMEN

BACKGROUND: Medication adherence is critical to the effectiveness of psychopharmacologic therapy. Psychiatric disorders present special adherence considerations, notably an altered capacity for decision making and the increased street value of controlled substances. A wide range of interventions designed to improve adherence in mental health and substance use disorders have been studied; recently, many have incorporated information technology (eg, mobile phone apps, electronic pill dispensers, and telehealth). Many intervention components have been studied across different disorders. Furthermore, many interventions incorporate multiple components, making it difficult to evaluate the effect of individual components in isolation. OBJECTIVE: The aim of this study was to conduct a systematic scoping review to develop a literature-driven, transdiagnostic taxonomic framework of technology-based medication adherence intervention and measurement components used in mental health and substance use disorders. METHODS: This review was conducted based on a published protocol (PROSPERO: CRD42018067902) in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses systematic review guidelines. We searched 7 electronic databases: MEDLINE, EMBASE, PsycINFO, the Cochrane Central Register of Controlled Trials, Web of Science, Engineering Village, and ClinicalTrials.gov from January 2000 to September 2018. Overall, 2 reviewers independently conducted title and abstract screens, full-text screens, and data extraction. We included all studies that evaluate populations or individuals with a mental health or substance use disorder and contain at least 1 technology-delivered component (eg, website, mobile phone app, biosensor, or algorithm) designed to improve medication adherence or the measurement thereof. Given the wide variety of studied interventions, populations, and outcomes, we did not conduct a risk of bias assessment or quantitative meta-analysis. We developed a taxonomic framework for intervention classification and applied it to multicomponent interventions across mental health disorders. RESULTS: The initial search identified 21,749 results; after screening, 127 included studies remained (Cohen kappa: 0.8, 95% CI 0.72-0.87). Major intervention component categories include reminders, support messages, social support engagement, care team contact capabilities, data feedback, psychoeducation, adherence-based psychotherapy, remote care delivery, secure medication storage, and contingency management. Adherence measurement components include self-reports, remote direct visualization, fully automated computer vision algorithms, biosensors, smart pill bottles, ingestible sensors, pill counts, and utilization measures. Intervention modalities include short messaging service, mobile phone apps, websites, and interactive voice response. We provide graphical representations of intervention component categories and an element-wise breakdown of multicomponent interventions. CONCLUSIONS: Many technology-based medication adherence and monitoring interventions have been studied across psychiatric disease contexts. Interventions that are useful in one psychiatric disorder may be useful in other disorders, and further research is necessary to elucidate the specific effects of individual intervention components. Our framework is directly developed from the substance use disorder and mental health treatment literature and allows for transdiagnostic comparisons and an organized conceptual mapping of interventions.

RESUMEN

PURPOSE: To evaluate the performance of machine learning algorithms on organ-level classification of semistructured pathology reports, to incorporate surgical pathology monitoring into an automated imaging recommendation follow-up engine. MATERIALS AND METHODS: This retrospective study included 2013 pathology reports from patients who underwent abdominal imaging at a large tertiary care center between 2012 and 2018. The reports were labeled by two annotators as relevant to four abdominal organs: liver, kidneys, pancreas and/or adrenal glands, or none. Automated classification methods were compared: simple string matching, random forests, extreme gradient boosting, support vector machines, and two neural network architectures-convolutional neural networks and long short-term memory networks. Three methods from the literature were used to provide interpretability and qualitative validation of the learned network features. RESULTS: The neural networks performed well on the four-organ classification task (F1 score: 96.3% for convolutional neural network and 96.7% for long short-term memory vs 89.9% for support vector machines, 93.9% for extreme gradient boosting, 82.8% for random forests, and 75.2% for simple string matching). Multiple methods were used to visualize the decision-making process of the network, verifying that the networks used similar heuristics to a human annotator. The neural networks were able to classify, with a high degree of accuracy, pathology reports written in unseen formats, suggesting the networks had learned a generalizable encoding of the salient features. CONCLUSION: Neural network-based approaches achieve high performance on organ-level pathology report classification, suggesting that it is feasible to use them within automated tracking systems.© RSNA, 2019Supplemental material is available for this article.See also the commentary by Liu in this issue.

RESUMEN

BACKGROUND: While buprenorphine/naloxone (B/N) is approved for opioid use disorder treatment, effective delivery of B/N comes with significant challenges. Most notably, many patients do not take medication daily as prescribed; this non-adherence worsens treatment outcomes, increases healthcare costs, and leads to persistent worries of diversion among providers and policymakers. The present study examines the feasibility, usability, and acceptability of MySafeRx-a mobile technology platform integrating motivational coaching, adherence monitoring, and electronic pill dispensing designed to address the challenges of office-based opioid treatment (OBOT) with B/N. METHODS: The MySafeRx platform integrates electronic pill dispensers, text-messaging, and videoconferencing to provide supervised self-administration of medication and daily motivational coaching through an Android app interface. High-risk early adults (18-39 years old) who were enrolled in OBOT with B/N and had documented illicit opioid use in the past month during opioid agonist therapy (n = 12) participated in a 28-day single-arm observational study of the MySafeRx platform in addition to standard care. RESULTS: Two-thirds of participants who completed the study achieved an average of > 5 days per week of supervised B/N self-administration. Visual confirmation of medication adherence was demonstrated for an average of 72% of study days among all participants. All participants achieved platform technical proficiency within 60 min, reporting good levels of usability and acceptability. Illicit opioid abstinence rates confirmed by urine toxicology increased by 53% during MySafeRx but fell 43% within 3 weeks post-intervention. CONCLUSION: The MySafeRx medication adherence and remote coaching mobile platform is acceptable and can be feasibly implemented in real-world opioid use disorder treatment settings during high-risk periods (i.e., initial stabilization, after illicit opioid lapse), resulting in reduced illicit opioid use; however, the effect did not last after intervention completion, suggesting longer duration or extended taper of program may be needed. ClinicalTrials.Gov NCT02942199 10/24/16 https://clinicaltrials.gov/ct2/show/NCT02942199.

Asunto(s)