More Like this

1. Patient-Independent Schizophrenia Relapse Prediction Using Mobile Sensor Based Daily Behavioral Rhythm Changes.

   Lamichhane, Bishal ; Ben-Zeev, Dror ; Campbell, Andrew ; Choudhury, Tanzeem ; Hauser, Marta ; Kane, John ; Obuchi, Mikio ; Scherer, Emily ; Walsh, Megan ; Wang, Rui ; et al ( February 2021 , Wireless Mobile Communication and Healthcare. MobiHealth 2020. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering)

   null (Ed.)

   A schizophrenia relapse has severe consequences for a patient’s health, work, and sometimes even life safety. If an oncoming relapse can be predicted on time, for example by detecting early behavioral changes in patients, then interventions could be provided to prevent the relapse. In this work, we investigated a machine learning based schizophrenia relapse prediction model using mobile sensing data to characterize behavioral features. A patient-independent model providing sequential predictions, closely representing the clinical deployment scenario for relapse prediction, was evaluated. The model uses the mobile sensing data from the recent four weeks to predict an oncoming relapse in the next week. We used the behavioral rhythm features extracted from daily templates of mobile sensing data, self-reported symptoms collected via EMA (Ecological Momentary Assessment), and demographics to compare different classifiers for the relapse prediction. Naive Bayes based model gave the best results with an F2 score of 0.083 when evaluated in a dataset consisting of 63 schizophrenia patients, each monitored for up to a year. The obtained F2 score, though low, is better than the baseline performance of random classification (F2 score of 0.02 ± 0.024). Thus, mobile sensing has predictive value for detecting an oncoming relapse and needs further investigation to improve the current performance. Towards that end, further feature engineering and model personalization based on the behavioral idiosyncrasies of a patient could be helpful. 

   more » « less
2. Prediction of short-term antidepressant response using probabilistic graphical models with replication across multiple drugs and treatment settings

   https://doi.org/10.1038/s41386-020-00943-x  

   Athreya, Arjun P. ; Brückl, Tanja ; Binder, Elisabeth B. ; John Rush, A. ; Biernacka, Joanna ; Frye, Mark A. ; Neavin, Drew ; Skime, Michelle ; Monrad, Ditlev ; Iyer, Ravishankar K. ; et al ( June 2021 , Neuropsychopharmacology)

   null (Ed.)

   Abstract Heterogeneity in the clinical presentation of major depressive disorder and response to antidepressants limits clinicians’ ability to accurately predict a specific patient’s eventual response to therapy. Validated depressive symptom profiles may be an important tool for identifying poor outcomes early in the course of treatment. To derive these symptom profiles, we first examined data from 947 depressed subjects treated with selective serotonin reuptake inhibitors (SSRIs) to delineate the heterogeneity of antidepressant response using probabilistic graphical models (PGMs). We then used unsupervised machine learning to identify specific depressive symptoms and thresholds of improvement that were predictive of antidepressant response by 4 weeks for a patient to achieve remission, response, or nonresponse by 8 weeks. Four depressive symptoms (depressed mood, guilt feelings and delusion, work and activities and psychic anxiety) and specific thresholds of change in each at 4 weeks predicted eventual outcome at 8 weeks to SSRI therapy with an average accuracy of 77% ( p  = 5.5E-08). The same four symptoms and prognostic thresholds derived from patients treated with SSRIs correctly predicted outcomes in 72% ( p  = 1.25E-05) of 1996 patients treated with other antidepressants in both inpatient and outpatient settings in independent publicly-available datasets. These predictive accuracies were higher than the accuracy of 53% for predicting SSRI response achieved using approaches that (i) incorporated only baseline clinical and sociodemographic factors, or (ii) used 4-week nonresponse status to predict likely outcomes at 8 weeks. The present findings suggest that PGMs providing interpretable predictions have the potential to enhance clinical treatment of depression and reduce the time burden associated with trials of ineffective antidepressants. Prospective trials examining this approach are forthcoming. 

   more » « less
3. Early prediction of patient discharge disposition in acute neurological care using machine learning

   https://doi.org/10.1186/s12913-022-08615-w  

   Mickle, Charles F. ; Deb, Debzani ( October 2022 , BMC Health Services Research)

   Acute neurological complications are some of the leading causes of death and disability in the U.S. The medical professionals that treat patients in this setting are tasked with deciding where (e.g., home or facility), how, and when to discharge these patients. It is important to be able to predict potential patient discharge outcomes as early as possible during the patient’s hospital stay and to know what factors influence the development of discharge planning. This study carried out two parallel experiments: A multi-class outcome (patient discharge targets of ‘home’, ‘nursing facility’, ‘rehab’, ‘death’) and binary class outcome (‘home’ vs. ‘non-home’). The goal of this study is to develop early predictive models for each experiment exploring which patient characteristics and clinical variables significantly influence discharge planning of patients based on the data that are available only within 24 h of their hospital admission. 

   Our methodology centers around building and training five different machine learning models followed by testing and tuning those models to find the best-suited predictor for each experiment with a dataset of 5,245 adult patients with neurological conditions taken from the eICU-CRD database.

   The results of this study show XGBoost to be the most effective model for predicting between four common discharge outcomes of ‘home’, ‘nursing facility’, ‘rehab’, and ‘death’, with 71% average c-statistic. The XGBoost model was also the best-performer in the binary outcome experiment with a c-statistic of 76%. This article also explores the accuracy, reliability, and interpretability of the best performing models in each experiment by identifying and analyzing the features that are most impactful to the predictions.

   The acceptable accuracy and interpretability of the predictive models based on early admission data suggests that the models can be used in a suggestive context to help guide healthcare providers in efforts of planning effective and equitable discharge recommendations.

    

   more » « less
4. Acquisition of visual priors and induced hallucinations in chronic schizophrenia

   https://doi.org/10.1093/brain/awz171  

   Valton, Vincent ; Karvelis, Povilas ; Richards, Katie L. ; Seitz, Aaron R. ; Lawrie, Stephen M. ; Seriès, Peggy ( June 2019 , Brain)

   Prominent theories suggest that symptoms of schizophrenia stem from learning deficiencies resulting in distorted internal models of the world. To test these theories further, we used a visual statistical learning task known to induce rapid implicit learning of the stimulus statistics. In this task, participants are presented with a field of coherently moving dots and are asked to report the presented direction of the dots (estimation task), and whether they saw any dots or not (detection task). Two of the directions were more frequently presented than the others. In controls, the implicit acquisition of the stimuli statistics influences their perception in two ways: (i) motion directions are perceived as being more similar to the most frequently presented directions than they really are (estimation biases); and (ii) in the absence of stimuli, participants sometimes report perceiving the most frequently presented directions (a form of hallucinations). Such behaviour is consistent with probabilistic inference, i.e. combining learnt perceptual priors with sensory evidence. We investigated whether patients with chronic, stable, treated schizophrenia (n = 20) differ from controls (n = 23) in the acquisition of the perceptual priors and/or their influence on perception. We found that although patients were slower than controls, they showed comparable acquisition of perceptual priors, approximating the stimulus statistics. This suggests that patients have no statistical learning deficits in our task. This may reflect our patients’ relative wellbeing on antipsychotic medication. Intriguingly, however, patients experienced significantly fewer (P = 0.016) hallucinations of the most frequently presented directions than controls when the stimulus was absent or when it was very weak (prior-based lapse estimations). This suggests that prior expectations had less influence on patients’ perception than on controls when stimuli were absent or below perceptual threshold.

    

   more » « less
5. Machine learning for passive mental health symptom prediction: Generalization across different longitudinal mobile sensing studies

   https://doi.org/10.1371/journal.pone.0266516  

   Adler, Daniel A. ; Wang, Fei ; Mohr, David C. ; Choudhury, Tanzeem ( April 2022 , PLOS ONE)

   Chen, Chi-Hua (Ed.)

   Mobile sensing data processed using machine learning models can passively and remotely assess mental health symptoms from the context of patients’ lives. Prior work has trained models using data from single longitudinal studies, collected from demographically homogeneous populations, over short time periods, using a single data collection platform or mobile application. The generalizability of model performance across studies has not been assessed. This study presents a first analysis to understand if models trained using combined longitudinal study data to predict mental health symptoms generalize across current publicly available data. We combined data from the CrossCheck (individuals living with schizophrenia) and StudentLife (university students) studies. In addition to assessing generalizability, we explored if personalizing models to align mobile sensing data, and oversampling less-represented severe symptoms, improved model performance. Leave-one-subject-out cross-validation (LOSO-CV) results were reported. Two symptoms (sleep quality and stress) had similar question-response structures across studies and were used as outcomes to explore cross-dataset prediction. Models trained with combined data were more likely to be predictive (significant improvement over predicting training data mean) than models trained with single-study data. Expected model performance improved if the distance between training and validation feature distributions decreased using combined versus single-study data. Personalization aligned each LOSO-CV participant with training data, but only improved predicting CrossCheck stress. Oversampling significantly improved severe symptom classification sensitivity and positive predictive value, but decreased model specificity. Taken together, these results show that machine learning models trained on combined longitudinal study data may generalize across heterogeneous datasets. We encourage researchers to disseminate collected de-identified mobile sensing and mental health symptom data, and further standardize data types collected across studies to enable better assessment of model generalizability. 

   more » « less