Conceptualizing socially-assistive robots as a digital therapeutic tool in healthcare.

Artificial Intelligence (AI)-driven Digital Health (DH) systems are poised to play a critical role in the future of healthcare. In 2021, $57.2 billion was invested in DH systems around the world, recognizing the promise this concept holds for aiding in delivery and care management. DH systems traditionally include a blend of various technologies, AI, and physiological biomarkers and have shown a potential to provide support for individuals with various health conditions. Digital therapeutics (DTx) is a more specific set of technology-enabled interventions within the broader DH sphere intended to produce a measurable therapeutic effect. DTx tools can empower both patients and healthcare providers, informing the course of treatment through data-driven interventions while collecting data in real-time and potentially reducing the number of patient office visits needed. In particular, socially assistive robots (SARs), as a DTx tool, can be a beneficial asset to DH systems since data gathered from sensors onboard the robot can help identify in-home behaviors, activity patterns, and health status of patients remotely. Furthermore, linking the robotic sensor data to other DH system components, and enabling SAR to function as part of an Internet of Things (IoT) ecosystem, can create a broader picture of patient health outcomes. The main challenge with DTx, and DH systems in general, is that the sheer volume and limited oversight of different DH systems and DTxs is hindering validation efforts (from technical, clinical, system, and privacy standpoints) and consequently slowing widespread adoption of these treatment tools.

A Novel Approach to Clustering Accelerometer Data for Application in Passive Predictions of Changes in Depression Severity.

The treatment of mood disorders, which can become a lifelong process, varies widely in efficacy between individuals. Most options to monitor mood rely on subjective self-reports and clinical visits, which can be burdensome and may not portray an accurate representation of what the individual is experiencing. A passive method to monitor mood could be a useful tool for those with these disorders. Some previously proposed models utilized sensors from smartphones and wearables, such as the accelerometer. This study examined a novel approach of processing accelerometer data collected from smartphones only while participants of the open-science branch of the BiAffect study were typing. The data were modeled by von Mises-Fisher distributions and weighted networks to identify clusters relating to different typing positions unique for each participant. Longitudinal features were derived from the clustered data and used in machine learning models to predict clinically relevant changes in depression from clinical and typing measures. Model accuracy was approximately 95%, with 97% area under the ROC curve (AUC). The accelerometer features outperformed the vast majority of clinical and typing features, which suggested that this new approach to analyzing accelerometer data could contribute towards unobtrusive detection of changes in depression severity without the need for clinical input.

Smartphone accelerometer data as a proxy for clinical data in modeling of bipolar disorder symptom trajectory.

Being able to track and predict fluctuations in symptoms of mental health disorders such as bipolar disorder outside the clinic walls is critical for expanding access to care for the global population. To that end, we analyze a dataset of 291 individuals from a smartphone app targeted at bipolar disorder, which contains rich details about their smartphone interactions (including typing dynamics and accelerometer motion) collected everyday over several months, along with more traditional clinical features. The aim is to evaluate whether smartphone accelerometer data could serve as a proxy for traditional clinical data, either by itself or in combination with typing dynamics. Results show that accelerometer data improves the predictive performance of machine learning models by nearly 5% over those previously reported in the literature based only on clinical data and typing dynamics. This suggests it is possible to elicit essentially the same "information" about bipolar symptomology using different data sources, in a variety of settings.

Effects of mood and aging on keystroke dynamics metadata and their diurnal patterns in a large open-science sample: A BiAffect iOS study.

OBJECTIVE: Ubiquitous technologies can be leveraged to construct ecologically relevant metrics that complement traditional psychological assessments. This study aims to determine the feasibility of smartphone-derived real-world keyboard metadata to serve as digital biomarkers of mood. MATERIALS AND METHODS: BiAffect, a real-world observation study based on a freely available iPhone app, allowed the unobtrusive collection of typing metadata through a custom virtual keyboard that replaces the default keyboard. User demographics and self-reports for depression severity (Patient Health Questionnaire-8) were also collected. Using >14 million keypresses from 250 users who reported demographic information and a subset of 147 users who additionally completed at least 1 Patient Health Questionnaire, we employed hierarchical growth curve mixed-effects models to capture the effects of mood, demographics, and time of day on keyboard metadata. RESULTS: We analyzed 86 541 typing sessions associated with a total of 543 Patient Health Questionnaires. Results showed that more severe depression relates to more variable typing speed (P < .001), shorter session duration (P < .001), and lower accuracy (P < .05). Additionally, typing speed and variability exhibit a diurnal pattern, being fastest and least variable at midday. Older users exhibit slower and more variable typing, as well as more pronounced slowing in the evening. The effects of aging and time of day did not impact the relationship of mood to typing variables and were recapitulated in the 250-user group. CONCLUSIONS: Keystroke dynamics, unobtrusively collected in the real world, are significantly associated with mood despite diurnal patterns and effects of age, and thus could serve as a foundation for constructing digital biomarkers.

PARO robot affects diverse interaction modalities in group sensory therapy for older adults with dementia.

We evaluated the seal-like robot PARO in the context of multi-sensory behavioral therapy in a local nursing home. Participants were 10 elderly nursing home residents with varying levels of dementia. We report three principle findings from our observations of interactions between the residents, PARO, and a therapist during seven weekly therapy sessions. Firstly, we show PARO provides indirect benefits for users by increasing their activity in particular modalities of social interaction, including visual, verbal, and physical interaction, which vary between primary and non-primary interactors. Secondly, PARO's positive effects on older adults' activity levels show steady growth over the duration of our study, suggesting they are not due to short-term "novelty effects." Finally, we show a variety of ways in which individual participants interacted with PARO and relate this to the "interpretive flexibility" of its design.

Artificial intelligence framework for simulating clinical decision-making: a Markov decision process approach.

OBJECTIVE: In the modern healthcare system, rapidly expanding costs/complexity, the growing myriad of treatment options, and exploding information streams that often do not effectively reach the front lines hinder the ability to choose optimal treatment decisions over time. The goal in this paper is to develop a general purpose (non-disease-specific) computational/artificial intelligence (AI) framework to address these challenges. This framework serves two potential functions: (1) a simulation environment for exploring various healthcare policies, payment methodologies, etc., and (2) the basis for clinical artificial intelligence - an AI that can "think like a doctor". METHODS: This approach combines Markov decision processes and dynamic decision networks to learn from clinical data and develop complex plans via simulation of alternative sequential decision paths while capturing the sometimes conflicting, sometimes synergistic interactions of various components in the healthcare system. It can operate in partially observable environments (in the case of missing observations or data) by maintaining belief states about patient health status and functions as an online agent that plans and re-plans as actions are performed and new observations are obtained. This framework was evaluated using real patient data from an electronic health record. RESULTS: The results demonstrate the feasibility of this approach; such an AI framework easily outperforms the current treatment-as-usual (TAU) case-rate/fee-for-service models of healthcare. The cost per unit of outcome change (CPUC) was $189 vs. $497 for AI vs. TAU (where lower is considered optimal) - while at the same time the AI approach could obtain a 30-35% increase in patient outcomes. Tweaking certain AI model parameters could further enhance this advantage, obtaining approximately 50% more improvement (outcome change) for roughly half the costs. CONCLUSION: Given careful design and problem formulation, an AI simulation framework can approximate optimal decisions even in complex and uncertain environments. Future work is described that outlines potential lines of research and integration of machine learning algorithms for personalized medicine.

Utilizing RxNorm to support practical computing applications: capturing medication history in live electronic health records.

RxNorm was utilized as the basis for direct-capture of medication history data in a live EHR system deployed in a large, multi-state outpatient behavioral healthcare provider in the United States serving over 75,000 distinct patients each year across 130 clinical locations. This tool incorporated auto-complete search functionality for medications and proper dosage identification assistance. The overarching goal was to understand if and how standardized terminologies like RxNorm can be used to support practical computing applications in live EHR systems. We describe the stages of implementation, approaches used to adapt RxNorm's data structure for the intended EHR application, and the challenges faced. We evaluate the implementation using a four-factor framework addressing flexibility, speed, data integrity, and medication coverage. RxNorm proved to be functional for the intended application, given appropriate adaptations to address high-speed input/output (I/O) requirements of a live EHR and the flexibility required for data entry in multiple potential clinical scenarios. Future research around search optimization for medication entry, user profiling, and linking RxNorm to drug classification schemes holds great potential for improving the user experience and utility of medication data in EHRs.

Investigation of ancient DNA from Western Siberia and the Sargat culture.

Mitochondrial DNA from 14 archaeological samples at the Ural State University in Yekaterinburg, Russia, was extracted to test the feasibility of ancient DNA work on their collection. These samples come from a number of sites that fall into two groupings. Seven samples are from three sites, dating to the 8th-12th century AD, that belong to a northern group of what are thought to be Ugrians, who lived along the Ural Mountains in northwestern Siberia. The remaining seven samples are from two sites that belong to a southern group representing the Sargat culture, dating between roughly the 5th century BC and the 5th century AD, from southwestern Siberia near the Ural Mountains and the present-day Kazakhstan border. The samples are derived from several burial types, including kurgan burials. They also represent a number of different skeletal elements and a range of observed preservation. The northern sites repeatedly failed to amplify after multiple extraction and amplification attempts, but the samples from the southern sites were successfully extracted and amplified. The sequences obtained from the southern sites support the hypothesis that the Sargat culture was a potential zone of intermixture between native Ugrian and/or Siberian populations and steppe peoples from the south, possibly early Iranian or Indo-Iranian, which has been previously suggested by archaeological analysis.

Reanalysis of Eurasian population history: ancient DNA evidence of population affinities.

Mitochondrial hypervariable region I genetic data from ancient populations at two sites in Asia-Linzi in Shandong (northern China) and Egyin Gol in Mongolia-were reanalyzed to detect population affinities. Data from 51 modern populations were used to generate distance measures (Fst's) to the two ancient populations. The tests first analyzed relationships at the regional level and then compiled the top regional matches for an overall comparison to the two probe populations. The reanalysis showed that the Egyin Gol and Linzi populations have clear distinctions in genetic affinity. The Egyin Gol population as a whole appears to bear close affinities with modern populations of northern East Asia. The Linzi population seems to have some genetic affinities with the West, as suggested by the original analysis, although the original attribution of "European-like" seems to be misleading. We suggest that the Linzi individuals are potentially related to early Iranians, who are thought to have been widespread in parts of Central Eurasia and the steppe regions in the first millennium B.C., although some significant admixture between a number of populations of varying origin cannot be ruled out. We also examine the effect of sequence length on this type of genetic data analysis and discuss the results of previous studies on the Linzi sample.