Dataset Information

Utilizing Machine Learning on Internet Search Activity to Support the Diagnostic Process and Relapse Detection in Young Individuals With Early Psychosis: Feasibility Study.

ABSTRACT: BACKGROUND:Psychiatry is nearly entirely reliant on patient self-reporting, and there are few objective and reliable tests or sources of collateral information available to help diagnostic and assessment procedures. Technology offers opportunities to collect objective digital data to complement patient experience and facilitate more informed treatment decisions. OBJECTIVE:We aimed to develop computational algorithms based on internet search activity designed to support diagnostic procedures and relapse identification in individuals with schizophrenia spectrum disorders. METHODS:We extracted 32,733 time-stamped search queries across 42 participants with schizophrenia spectrum disorders and 74 healthy volunteers between the ages of 15 and 35 (mean 24.4 years, 44.0% male), and built machine-learning diagnostic and relapse classifiers utilizing the timing, frequency, and content of online search activity. RESULTS:Classifiers predicted a diagnosis of schizophrenia spectrum disorders with an area under the curve value of 0.74 and predicted a psychotic relapse in individuals with schizophrenia spectrum disorders with an area under the curve of 0.71. Compared with healthy participants, those with schizophrenia spectrum disorders made fewer searches and their searches consisted of fewer words. Prior to a relapse hospitalization, participants with schizophrenia spectrum disorders were more likely to use words related to hearing, perception, and anger, and were less likely to use words related to health. CONCLUSIONS:Online search activity holds promise for gathering objective and easily accessed indicators of psychiatric symptoms. Utilizing search activity as collateral behavioral health information would represent a major advancement in efforts to capitalize on objective digital data to improve mental health monitoring.

SUBMITTER: Birnbaum ML

PROVIDER: S-EPMC7492982 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Utilizing Machine Learning on Internet Search Activity to Support the Diagnostic Process and Relapse Detection in Young Individuals With Early Psychosis: Feasibility Study.

Birnbaum Michael Leo ML Kulkarni Prathamesh Param PP Van Meter Anna A Chen Victor V Rizvi Asra F AF Arenare Elizabeth E De Choudhury Munmun M Kane John M JM

JMIR mental health 20200901 9

<h4>Background</h4>Psychiatry is nearly entirely reliant on patient self-reporting, and there are few objective and reliable tests or sources of collateral information available to help diagnostic and assessment procedures. Technology offers opportunities to collect objective digital data to complement patient experience and facilitate more informed treatment decisions.<h4>Objective</h4>We aimed to develop computational algorithms based on internet search activity designed to support diagnostic ...[more]

PMID: 32870161

Similar Datasets

Project description:BackgroundAlthough autism is often characterized in literature by the presence of repetitive behavior, in structured decision tasks, individuals with autism spectrum disorder (ASD) have been found to examine more options in a given time period than controls.ObjectiveWe aimed to examine whether this investigative tendency emerges in information searches conducted via the internet.MethodsIn total, 1746 search engine users stated that they had ASD in 2019. This group's naturally occurring responses following 1491 unique general queries and 78 image queries were compared to those of all other users of the search engine. The main dependent measure was scrolled distance, which denoted the extent to which additional results were scanned beyond the initial results presented on-screen. Additionally, we examined the number of clicks on search results as an indicator of the degree of search outcome exploitation and assessed whether there was a trade-off between increased search range and the time invested in viewing initial search results.ResultsAfter issuing general queries, individuals with self-stated ASD scanned more results than controls. The scrolled distance in the results page of general queries was 45% larger for the group of individuals with ASD (P<.001; d=0.45). The group of individuals with ASD also made the first scroll faster than the controls (P<.001; d=0.51). The differences in scrolled distance were larger for popular queries. No group differences in scrolled distance emerged for image queries, suggesting that visual load impeded the investigative behavior of individuals with ASD. No differences emerged in the number of clicks on search results.ConclusionsIndividuals who self-stated that they had ASD scrutinized more general search results and fewer image search results than the controls. Thus, our results at least partially support the notion that individuals with ASD exhibit investigative behaviors and suggest that textual searches are an important context for expressing such tendencies.

Project description:BackgroundInfluenza epidemics pose significant social and economic challenges in China. Internet search query data have been identified as a valuable source for the detection of emerging influenza epidemics. However, the selection of the search queries and the adoption of prediction methods are crucial challenges when it comes to improving predictions. The purpose of this study was to explore the application of the Support Vector Machine (SVM) regression model in merging search engine query data and traditional influenza data.MethodsThe official monthly reported number of influenza cases in Liaoning province in China was acquired from the China National Scientific Data Center for Public Health from January 2011 to December 2015. Based on Baidu Index, a publicly available search engine database, search queries potentially related to influenza over the corresponding period were identified. An SVM regression model was built to be used for predictions, and the choice of three parameters (C, γ, ε) in the SVM regression model was determined by leave-one-out cross-validation (LOOCV) during the model construction process. The model's performance was evaluated by the evaluation metrics including Root Mean Square Error, Root Mean Square Percentage Error and Mean Absolute Percentage Error.ResultsIn total, 17 search queries related to influenza were generated through the initial query selection approach and were adopted to construct the SVM regression model, including nine queries in the same month, three queries at a lag of one month, one query at a lag of two months and four queries at a lag of three months. The SVM model performed well when with the parameters (C = 2, γ = 0.005, ɛ = 0.0001), based on the ensemble data integrating the influenza surveillance data and Baidu search query data.ConclusionsThe results demonstrated the feasibility of using internet search engine query data as the complementary data source for influenza surveillance and the efficiency of SVM regression model in tracking the influenza epidemics in Liaoning.

Project description:Corona Virus Disease 2019 (COVID-19) pandemic has increased the importance of Virtual Learning Environments (VLEs) instigating students to study from their homes. Every day a tremendous amount of data is generated when students interact with VLEs to perform different activities and access learning material. To make the generated data useful, it must be processed and managed by the proper machine learning (ML) algorithm. ML algorithms' applications are many folds with Education Data Mining (EDM) and Learning Analytics (LA) as their major fields. ML algorithms are commonly used to process raw data to discover hidden patterns and construct a model to make future predictions, such as predicting students' performance, dropouts, engagement, etc. However, in VLE, it is important to select the right and most applicable ML algorithm to give the best performance results. In this study, we aim to improve those ML and DL algorithms' performance that give an inferior performance in terms of performance, accuracy, precision, recall, and F1 score. Several ML algorithms were applied on Open University Learning Analytics (OULA) dataset to reveal which one offers the best results in terms of performance, accuracy, precision, recall, and F1 score. Two popular ML algorithms called Decision Tree (DT) and Feed-Forward Neural Network (FFNN) provided unsatisfactory results. They were selected and experimented with various techniques such as grid search cross-validation, adaptive boosting, extreme gradient boosting, early stopping, feature engineering, and dropping inactive neurons to improve their performance scores. Moreover, we also determined the feature weights/importance in predicting the students' study performance, leading to the design and development of the adaptive learning system. The ML techniques and the methods used in this research study can be used by instructors/administrators to optimize learning content and provide informed guidance to students, thus improving their learning experience and making it exciting and adaptive.

Project description:BackgroundRelapse in schizophrenia is a major cause of distress and disability and is predicted by changes in symptoms such as anxiety, depression, and suspiciousness (early warning signs [EWSs]). These can be used as the basis for timely interventions to prevent relapse. However, there is considerable uncertainty regarding the implementation of EWS interventions.ObjectiveThis study was designed to establish the feasibility of conducting a definitive cluster randomized controlled trial comparing Early signs Monitoring to Prevent relapse in psychosis and prOmote Well-being, Engagement, and Recovery (EMPOWER) against treatment as usual (TAU). Our primary outcomes are establishing parameters of feasibility, acceptability, usability, safety, and outcome signals of a digital health intervention as an adjunct to usual care that is deliverable in the UK National Health Service and Australian community mental health service (CMHS) settings. We will assess the feasibility of candidate primary outcomes, candidate secondary outcomes, and candidate mechanisms for a definitive trial.MethodsWe will randomize CMHSs to EMPOWER or TAU. We aim to recruit up to 120 service user participants from 8 CMHSs and follow them for 12 months. Eligible service users will (1) be aged 16 years and above, (2) be in contact with local CMHSs, (3) have either been admitted to a psychiatric inpatient service or received crisis intervention at least once in the previous 2 years for a relapse, and (4) have an International Classification of Diseases-10 diagnosis of a schizophrenia-related disorder. Service users will also be invited to nominate a carer to participate. We will identify the feasibility of the main trial in terms of recruitment and retention to the study and the acceptability, usability, safety, and outcome signals of the EMPOWER intervention. EMPOWER is a mobile phone app that enables the monitoring of well-being and possible EWSs of relapse on a daily basis. An algorithm calculates changes in well-being based on participants' own baseline to enable tailoring of well-being messaging and clinical triage of possible EWSs. Use of the app is blended with ongoing peer support.ResultsRecruitment to the trial began September 2018, and follow-up of participants was completed in July 2019. Data collection is continuing. The database was locked in July 2019, followed by analysis and disclosing of group allocation.ConclusionsThe knowledge gained from the study will inform the design of a definitive trial including finalizing the delivery of our digital health intervention, sample size estimation, methods to ensure successful identification, consent, randomization, and follow-up of participants, and the primary and secondary outcomes. The trial will also inform the final health economic model to be applied in the main trial.Trial registrationInternational Standard Randomized Controlled Trial Number (ISRCTN): 99559262; http://isrctn.com/ISRCTN99559262.International registered report identifier (irrid)DERR1-10.2196/15058.

Dataset Information

Utilizing Machine Learning on Internet Search Activity to Support the Diagnostic Process and Relapse Detection in Young Individuals With Early Psychosis: Feasibility Study.

Publications

Utilizing Machine Learning on Internet Search Activity to Support the Diagnostic Process and Relapse Detection in Young Individuals With Early Psychosis: Feasibility Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets