The Proposition for Bipolar Depression Forecasting Based on Wearable Data Collection

Abstract

Bipolar depression is treated wrongly as unipolar depression, on average, for 8 years. It is shown that this mismedication affects the occurrence of a manic episode and aggravates the overall condition of patients with bipolar depression. Significant effort was invested in early detection of depression and forecasting of responses to certain therapeutic approaches using a combination of features extracted from standard and online testing, wearables monitoring, and machine learning. In the case of unipolar depression, this approach yielded evidence that this data-based computational psychiatry approach would be helpful in clinical practice. Following a similar pipeline, we examined the usefulness of this approach to foresee a manic episode in bipolar depression, so that clinicians and family of the patient can help patient navigate through the time of crisis. Our projects combined the results from self-reported daily questionnaires, the data obtained from smart watches, and the data from regular reports from standard psychiatric interviews to feed various machine learning models to predict a crisis in bipolar depression. Contrary to satisfactory predictions in unipolar depression, we found that bipolar depression, having more complex dynamics, requires personalized approach. A previous work on physiological complexity (complex variability) suggests that an inclusion of electrophysiological data, properly quantified, might lead to better solutions, as shown in other projects of our group concerning unipolar depression. Here, we make a comparison of previously performed research in a methodological sense, revisiting and additionally interpreting our own results showing that the methodological approach to mania forecasting may be modified to provide an accurate prediction in bipolar depression.

possible scalable solution for Early detection of prodromal phase of dementia based on EEG complexity

“…SVM and its variants are obviously popular, but the use of embedded regularization frameworks is recommended instead (at least with the absolute shrinkage and selection operator) 126 . LOOCV and k-fold cross-validation are also popular procedures for validation (for model evaluation), and model generalization capability is typically untested on independent samples 126 . Furthermore, a Vapnik-Chevronenkis dimension 127 should be required as a standard for model evaluation or reduction -hence, very early when researchers make a decision on the methodology to be applied.…”

“…Sometimes during the development of a model, the model 'learns' some dependencies, and recognizes exactly that in unseen data, although it was not the intended task. That happens when "a developed model perfectly describes the overall aspects of the training data (including all underlying relationships and associated noise), resulting in fitting error to asymptotically become zero" 126 . It basically seeks the known dataset in a new one.…”

Automated recognition of major depressive disorder from cardiovascular and respiratory physiological signals

“…Seven classifiers were considered, and the results indicated that good classification was achievable with a small number of principal components, where Sample Entropy had the better performance. Llamocca et al (29) combined the data from regular reports from standard psychiatric interviews, self-reported daily questionnaires, and data obtained from smart watches to train machine learning models for crisis in bipolar depression prediction. Since bipolar depression have more complex dynamics, it was concluded that a personalized approach is needed.…”

Progress in Objective Detection of Depression and Online Monitoring of Patients Based on Physiological Complexity

“…Our group focused mainly on data-driven computational psychiatry research ( 9 – 14 ). We also became aware of so-called unwarranted optimism ( 15 – 17 ) and reported on it ( 10 , 12 ).…”

“…A recent publication demonstrated that ML's purely reliance on patient's medical history, medication, epidemiological data, and scales/questionaries data ( 18 ) are simply not capable of providing practically useful results. We also explored the possibilities of this methodology in forecasting mania in bipolar depression disorder-BDD ( 13 , 14 , 19 , 20 ). In this research we collected daily self-reports (via mobile phone applications), clinical assessment (standard clinical interviews and scales/questionaries), medical histories (including medication, and other important variables), several sleep variables, smartwatch variables (173 variables per person in total) in attempt to construct an accurate dynamical model of transition between five clinically defined states and in order to forecast mania phase.…”