Economic analysis of digital motor rehabilitation technologies: a systematic review.

Rehabilitation technologies offer promising opportunities for interventions for patients with motor disabilities. However, their use in routine care remains limited due to their high cost and persistent doubts about their cost-effectiveness. Providing solid evidence of the economic efficiency of rehabilitation technologies would help dispel these doubts in order to better take advantage of these technologies. In this context, this systematic review aimed to examine the cost-effectiveness of rehabilitation interventions based on the use of digital technologies. In total, 660 articles published between 2011 and 2021 were identified, of which eleven studies met all the inclusion criteria. Of these eleven studies, seven proved to be cost-effective, while four were not. Four studies used cost-utility analyses (CUAs) and seven used cost-minimization analyses (CMAs). The majority (ten studies) focused on the rehabilitation of the upper and/or lower limbs after a stroke, while only one study examined the rehabilitation of the lower limbs after knee arthroplasty. Regarding the evaluated devices, seven studies analyzed the cost-effectiveness of robotic rehabilitation and four analyzed rehabilitation with virtual reality.The assessment of the quality of the included studies using the CHEERS (Consolidated Health Economic Evaluation Reporting Standards) suggested that the quality was related to the economic analysis method: all studies that adopted a cost-utility analysis obtained a high quality score (above 80%), while the quality scores of the cost-minimization analyses were average, with the highest score obtained by a CMA being 72%. The average quality score of all the articles was 75%, ranging between 52 and 100. Of the four studies with a considering score, two concluded that there was equivalence between the intervention and conventional care in terms of cost-effectiveness, one concluded that the intervention dominated, while the last one concluded that usual care dominated. This suggests that even considering the quality of the included studies, rehabilitation interventions based on digital technologies remain cost-effective, they improved health outcomes and quality of life for patients with motor disorders while also allowing cost savings.

Machine Learning and Natural Language Processing in Mental Health: Systematic Review.

BACKGROUND: Machine learning systems are part of the field of artificial intelligence that automatically learn models from data to make better decisions. Natural language processing (NLP), by using corpora and learning approaches, provides good performance in statistical tasks, such as text classification or sentiment mining. OBJECTIVE: The primary aim of this systematic review was to summarize and characterize, in methodological and technical terms, studies that used machine learning and NLP techniques for mental health. The secondary aim was to consider the potential use of these methods in mental health clinical practice. METHODS: This systematic review follows the PRISMA (Preferred Reporting Items for Systematic Review and Meta-analysis) guidelines and is registered with PROSPERO (Prospective Register of Systematic Reviews; number CRD42019107376). The search was conducted using 4 medical databases (PubMed, Scopus, ScienceDirect, and PsycINFO) with the following keywords: machine learning, data mining, psychiatry, mental health, and mental disorder. The exclusion criteria were as follows: languages other than English, anonymization process, case studies, conference papers, and reviews. No limitations on publication dates were imposed. RESULTS: A total of 327 articles were identified, of which 269 (82.3%) were excluded and 58 (17.7%) were included in the review. The results were organized through a qualitative perspective. Although studies had heterogeneous topics and methods, some themes emerged. Population studies could be grouped into 3 categories: patients included in medical databases, patients who came to the emergency room, and social media users. The main objectives were to extract symptoms, classify severity of illness, compare therapy effectiveness, provide psychopathological clues, and challenge the current nosography. Medical records and social media were the 2 major data sources. With regard to the methods used, preprocessing used the standard methods of NLP and unique identifier extraction dedicated to medical texts. Efficient classifiers were preferred rather than transparent functioning classifiers. Python was the most frequently used platform. CONCLUSIONS: Machine learning and NLP models have been highly topical issues in medicine in recent years and may be considered a new paradigm in medical research. However, these processes tend to confirm clinical hypotheses rather than developing entirely new information, and only one major category of the population (ie, social media users) is an imprecise cohort. Moreover, some language-specific features can improve the performance of NLP methods, and their extension to other languages should be more closely investigated. However, machine learning and NLP techniques provide useful information from unexplored data (ie, patients' daily habits that are usually inaccessible to care providers). Before considering It as an additional tool of mental health care, ethical issues remain and should be discussed in a timely manner. Machine learning and NLP methods may offer multiple perspectives in mental health research but should also be considered as tools to support clinical practice.

An Approach for Data Mining of Electronic Health Record Data for Suicide Risk Management: Database Analysis for Clinical Decision Support.

BACKGROUND: In an electronic health context, combining traditional structured clinical assessment methods and routine electronic health-based data capture may be a reliable method to build a dynamic clinical decision-support system (CDSS) for suicide prevention. OBJECTIVE: The aim of this study was to describe the data mining module of a Web-based CDSS and to identify suicide repetition risk in a sample of suicide attempters. METHODS: We analyzed a database of 2802 suicide attempters. Clustering methods were used to identify groups of similar patients, and regression trees were applied to estimate the number of suicide attempts among these patients. RESULTS: We identified 3 groups of patients using clustering methods. In addition, relevant risk factors explaining the number of suicide attempts were highlighted by regression trees. CONCLUSIONS: Data mining techniques can help to identify different groups of patients at risk of suicide reattempt. The findings of this study can be combined with Web-based and smartphone-based data to improve dynamic decision making for clinicians.

Clinicians' Concerns About Mobile Ecological Momentary Assessment Tools Designed for Emerging Psychiatric Problems: Prospective Acceptability Assessment of the MEmind App.

BACKGROUND: Many mental disorders are preceded by a prodromal phase consisting of various attenuated and unspecific symptoms and functional impairment. Electronic health records are generally used to capture these symptoms during medical consultation. Internet and mobile technologies provide the opportunity to monitor symptoms emerging in patients' environments using ecological momentary assessment techniques to support preventive therapeutic decision making. OBJECTIVE: The objective of this study was to assess the acceptability of a Web-based app designed to collect medical data during appointments and provide ecological momentary assessment features. METHODS: We recruited clinicians at 4 community psychiatry departments in France to participate. They used the app to assess patients and to collect data after viewing a video of a young patient's emerging psychiatric consultation. We then asked them to answer a short anonymous self-administered questionnaire that evaluated their experience, the acceptability of the app, and their habit of using new technologies. RESULTS: Of 24 practitioners invited, 21 (88%) agreed to participate. Most of them were between 25 and 45 years old, and greater age was not associated with poorer acceptability. Most of the practitioners regularly used new technologies, and 95% (20/21) connected daily to the internet, with 70% (15/21) connecting 3 times a day or more. However, only 57% (12/21) reported feeling comfortable with computers. Of the clinicians, 86% (18/21) would recommend the tool to their colleagues and 67% (14/21) stated that they would be interested in daily use of the app. Most of the clinicians (16/21, 76%) found the interface easy to use and useful. However, several clinicians noted the lack of readability (8/21, 38%) and the need to improve ergonometric features (4/21, 19%), in particular to facilitate browsing through various subsections. Some participants (5/21, 24%) were concerned about the storage of medical data and most of them (11/21, 52%) seemed to be uncomfortable with this. CONCLUSIONS: We describe the first step of the development of a Web app combining an electronic health record and ecological momentary assessment features. This online tool offers the possibility to assess patients and to integrate medical data easily into face-to-face conditions. The acceptability of this app supports the feasibility of its broader implementation. This app could help to standardize assessment and to build up a strong database. Used in conjunction with robust data mining analytic techniques, such a database would allow exploration of risk factors, patterns of symptom evolution, and identification of distinct risk subgroups.

[Suicide prevention and eHealth: towards personalized follow-up strategies?] / Prévention du suicide et santé connectée - Vers la personnalisation des soins ?

Suicide risk assessment usually rely on brief medical visit and does not report the evolution of this risk after the patient discharge. However, the reattempt risk is still high several months after the initial attempt. In these setting, long term suicide prevention of at risk subjects are challenging. Thanks to recent technological advances, electronic health (eHealth) data collection strategies now can provide access to real-time patient self-report data during the interval between visits. The extension of the clinical assessment to the patient environment and data processing using data mining will support medical decision making.

Toward mHealth Brief Contact Interventions in Suicide Prevention: Case Series From the Suicide Intervention Assisted by Messages (SIAM) Randomized Controlled Trial.

BACKGROUND: Research indicates that maintaining contact either via letter or postcard with at-risk adults following discharge from care services after a suicide attempt (SA) can reduce reattempt risk. Pilot studies have demonstrated that interventions using mobile health (mHealth) technologies are feasible in a suicide prevention setting. OBJECTIVE: The aim of this study was to report three cases of patients recruited in the Suicide Intervention Assisted by Messages (SIAM) study to describe how a mobile intervention may influence follow-up. METHODS: SIAM is a 2-year, multicenter randomized controlled trial conducted by the Brest University Hospital, France. Participants in the intervention group receive SIAM text messages 48 hours after discharge, then at day 8 and day 15, and months 1, 2, 3, 4, 5, and 6. The study includes participants aged 18 years or older, who have attended a participating hospital for an SA, and have been discharged from the emergency department (ED) or a psychiatric unit (PU) for a stay of less than 7 days. Eligible participants are randomized between the SIAM intervention messages and a control group. In this study, we present three cases from the ongoing SIAM study that demonstrate the capability of a mobile-based brief contact intervention for triggering patient-initiated contact with a crisis support team at various time points throughout the mobile-based follow-up period. RESULTS: Out of the 244 patients recruited in the SIAM randomized controlled trial, three cases were selected to illustrate the impact of mHealth on suicide risk management. Participants initiated contact with the emergency crisis support service after receiving text messages up to 6 months following discharge from the hospital. Contact was initiated immediately following receipt of a text message or up to 6 days following a message. CONCLUSIONS: This text message-based brief contact intervention has demonstrated the potential to reconnect suicidal individuals with crisis support services while they are experiencing suicidal ideation as well as in a period after receiving messages. As follow-up phone calls over an extended period of time may not be feasible, this intervention has the potential to offer simple technological support for individuals following discharge from the ED. TRIAL REGISTRATION: ClinicalTrials.gov NCT02106949; https://clinicaltrials.gov/ct2/show/NCT02106949 (Archived by WebCite at http://www.webcitation.org/6wMtAFL49).

Ecological Assessment of Clinicians' Antipsychotic Prescription Habits in Psychiatric Inpatients: A Novel Web- and Mobile Phone-Based Prototype for a Dynamic Clinical Decision Support System.

BACKGROUND: Electronic prescribing devices with clinical decision support systems (CDSSs) hold the potential to significantly improve pharmacological treatment management. OBJECTIVE: The aim of our study was to develop a novel Web- and mobile phone-based application to provide a dynamic CDSS by monitoring and analyzing practitioners' antipsychotic prescription habits and simultaneously linking these data to inpatients' symptom changes. METHODS: We recruited 353 psychiatric inpatients whose symptom levels and prescribed medications were inputted into the MEmind application. We standardized all medications in the MEmind database using the Anatomical Therapeutic Chemical (ATC) classification system and the defined daily dose (DDD). For each patient, MEmind calculated an average for the daily dose prescribed for antipsychotics (using the N05A ATC code), prescribed daily dose (PDD), and the PDD to DDD ratio. RESULTS: MEmind results found that antipsychotics were used by 61.5% (217/353) of inpatients, with the largest proportion being patients with schizophrenia spectrum disorders (33.4%, 118/353). Of the 217 patients, 137 (63.2%, 137/217) were administered pharmacological monotherapy and 80 (36.8%, 80/217) were administered polytherapy. Antipsychotics were used mostly in schizophrenia spectrum and related psychotic disorders, but they were also prescribed in other nonpsychotic diagnoses. Notably, we observed polypharmacy going against current antipsychotics guidelines. CONCLUSIONS: MEmind data indicated that antipsychotic polypharmacy and off-label use in inpatient units is commonly practiced. MEmind holds the potential to create a dynamic CDSS that provides real-time tracking of prescription practices and symptom change. Such feedback can help practitioners determine a maximally therapeutic drug treatment while avoiding unproductive overprescription and off-label use.

Development of a Web-Based Clinical Decision Support System for Drug Prescription: Non-Interventional Naturalistic Description of the Antipsychotic Prescription Patterns in 4345 Outpatients and Future Applications.

PURPOSE: The emergence of electronic prescribing devices with clinical decision support systems (CDSS) is able to significantly improve management pharmacological treatments. We developed a web application available on smartphones in order to help clinicians monitor prescription and further propose CDSS. METHOD: A web application (www.MEmind.net) was developed to assess patients and collect data regarding gender, age, diagnosis and treatment. We analyzed antipsychotic prescriptions in 4345 patients attended in five Psychiatric Community Mental Health Centers from June 2014 to October 2014. The web-application reported average daily dose prescribed for antipsychotics, prescribed daily dose (PDD), and the PDD to defined daily dose (DDD) ratio. RESULTS: The MEmind web-application reported that antipsychotics were used in 1116 patients out of the total sample, mostly in 486 (44%) patients with schizophrenia related disorders but also in other diagnoses. Second generation antipsychotics (quetiapine, aripiprazole and long-acting paliperidone) were preferably employed. Low doses were more frequently used than high doses. Long acting paliperidone and ziprasidone however, were the only two antipsychotics used at excessive dosing. Antipsychotic polypharmacy was used in 287 (26%) patients with classic depot drugs, clotiapine, amisulpride and clozapine. CONCLUSIONS: In this study we describe the first step of the development of a web application that is able to make polypharmacy, high dose usage and off label usage of antipsychotics visible to clinicians. Current development of the MEmind web application may help to improve prescription security via momentary feedback of prescription and clinical decision support system.