Search

An important mobile health (mHealth) task is the use of multimodal data, such as sensor streams and self-report, to construct interpretable time-to-event predictions of, for example, lapse to alcohol or illicit drug use. Interpretability of the prediction model is important for acceptance and adoption by domain scientists, enabling model outputs and parameters to inform theory and guide intervention design. Temporal latent state models are therefore attractive, and so we adopt the continuous time hidden Markov model (CT-HMM) due to its ability to describe irregular arrival times of event data. Standard CT-HMMs, however, are not specialized for predicting the time to a future event, the key variable for mHealth interventions. Also, standard emission models lack a sufficiently rich structure to describe multimodal data and incorporate domain knowledge. We present iSurvive, an extension of classical survival analysis to a CT-HMM. We present a parameter learning method for GLM emissions and survival model fitting, and present promising results on both synthetic data and an mHealth drug use dataset.

Background: Online discussion forums allow those in addiction recovery to seek help through text-based messages, including when facing triggers to drink or use drugs. Trained staff (or “moderators”) may participate within these forums to offer guidance and support when participants are struggling but must expend considerable effort to continually review new content. Demands on moderators limit the scalability of evidence-based digital health interventions. Objective: Automated identification of recovery problems could allow moderators to engage in more timely and efficient ways with participants who are struggling. This paper aimed to investigate whether computational linguistics and supervised machine learning can be applied to successfully flag, in real time, those discussion forum messages that moderators find most concerning. Methods: Training data came from a trial of a mobile phone-based health intervention for individuals in recovery from alcohol use disorder, with human coders labeling discussion forum messages according to whether or not authors mentioned problems in their recovery process. Linguistic features of these messages were extracted via several computational techniques: (1) a Bag-of-Words approach, (2) the dictionary-based Linguistic Inquiry and Word Count program, and (3) a hybrid approach combining the most important features from both Bag-of-Words and Linguistic Inquiry and Word Count. These features were applied within binary classifiers leveraging several methods of supervised machine learning: support vector machines, decision trees, and boosted decision trees. Classifiers were evaluated in data from a later deployment of the recovery support intervention. Results: To distinguish recovery problem disclosures, the Bag-of-Words approach relied on domain-specific language, including words explicitly linked to substance use and mental health (“drink,” “relapse,” “depression,” and so on), whereas the Linguistic Inquiry and Word Count approach relied on language characteristics such as tone, affect, insight, and presence of quantifiers and time references, as well as pronouns. A boosted decision tree classifier, utilizing features from both Bag-of-Words and Linguistic Inquiry and Word Count performed best in identifying problems disclosed within the discussion forum, achieving 88% sensitivity and 82% specificity in a separate cohort of patients in recovery. Conclusions: Differences in language use can distinguish messages disclosing recovery problems from other message types. Incorporating machine learning models based on language use allows real-time flagging of concerning content such that trained staff may engage more efficiently and focus their attention on time-sensitive issues.

Background: Symptom distress in patients toward the end of life can change rapidly. Family caregivers have the potential to help patients manage those symptoms, as well as their own stress, if they are equipped with the proper resources. Electronic health (eHealth) systems may be able to provide those resources. Very sick patients may not be able to use such systems themselves to report their symptoms but family caregivers could. Objective: The aim of this paper was to assess the effects on cancer patient symptom distress of an eHealth system that alerts clinicians to significant changes in the patient’s symptoms, as reported by a family caregiver. Methods: A pooled analysis from two randomized clinical trials (NCT00214162 and NCT00365963) compared outcomes at 12 months for two unblinded groups: a control group (Comprehensive Health Enhancement Support System [CHESS]-Only) that gave caregivers access to CHESS, an online support system, and an experimental group (CHESS+CR [Clinician Report]), which also had CHESS but with a CR that automatically alerted clinicians if symptoms exceeded a predetermined threshold of severity. Participants were dyads (n=235) of patients with advanced lung, breast, or prostate cancer and their respective family caregivers from 5 oncology clinics in the United States of America. The proportion of improved patient threshold symptoms was compared between groups using area-under-the-curve analysis and binomial proportion tests. The proportion of threshold symptoms out of all reported symptoms was also examined. Results: When severe caregiver-reported symptoms were shared with clinicians, the symptoms were more likely to be subsequently reported as improved than when the symptoms were not shared with clinicians (P