Using artificial intelligence to optimize delivery of weight loss treatment: Protocol for an efficacy and cost-effectiveness trial.

Gold standard behavioral weight loss (BWL) is limited by the availability of expert clinicians and high cost of delivery. The artificial intelligence (AI) technique of reinforcement learning (RL) is an optimization solution that tracks outcomes associated with specific actions and, over time, learns which actions yield a desired outcome. RL is increasingly utilized to optimize medical treatments (e.g., chemotherapy dosages), and has very recently started to be utilized by behavioral treatments. For example, we previously demonstrated that RL successfully optimized BWL by dynamically choosing between treatments of varying cost/intensity each week for each participant based on automatic monitoring of digital data (e.g., weight change). In that preliminary work, participants randomized to the AI condition required one-third the amount of coaching contact as those randomized to the gold standard condition but had nearly identical weight losses. The current protocol extends our pilot work and will be the first full-scale randomized controlled trial of a RL system for weight control. The primary aim is to evaluate the hypothesis that a RL-based 12-month BWL program will produce non-inferior weight losses to standard BWL treatment, but at lower costs. Secondary aims include testing mechanistic targets (calorie intake, physical activity) and predictors (depression, binge eating). As such, adults with overweight/obesity (N = 336) will be randomized to either a gold standard condition (12 months of weekly BWL groups) or AI-optimized weekly interventions that represent a combination of expert-led group, expert-led call, paraprofessional-led call, and automated message). Participants will be assessed at 0, 1, 6 and 12 months.

Examining virtual driving test performance and its relationship to individuals with HIV-associated neurocognitive disorders.

Significance: Existing screening tools for HIV-associated neurocognitive disorders (HAND) are often clinically impractical for detecting milder forms of impairment. The formal diagnosis of HAND requires an assessment of both cognition and impairment in activities of daily living (ADL). To address the critical need for identifying patients who may have disability associated with HAND, we implemented a low-cost screening tool, the Virtual Driving Test (VDT) platform, in a vulnerable cohort of people with HIV (PWH). The VDT presents an opportunity to cost-effectively screen for milder forms of impairment while providing practical guidance for a cognitively demanding ADL. Objectives: We aimed to: (1) evaluate whether VDT performance variables were associated with a HAND diagnosis and if so; (2) systematically identify a manageable subset of variables for use in a future screening model for HAND. As a secondary objective, we examined the relative associations of identified variables with impairment within the individual domains used to diagnose HAND. Methods: In a cross-sectional design, 62 PWH were recruited from an established HIV cohort and completed a comprehensive neuropsychological assessment (CNPA), followed by a self-directed VDT. Dichotomized diagnoses of HAND-specific impairment and impairment within each of the seven CNPA domains were ascertained. A systematic variable selection process was used to reduce the large amount of VDT data generated, to a smaller subset of VDT variables, estimated to be associated with HAND. In addition, we examined associations between the identified variables and impairment within each of the CNPA domains. Results: More than half of the participants (N = 35) had a confirmed presence of HAND. A subset of twenty VDT performance variables was isolated and then ranked by the strength of its estimated associations with HAND. In addition, several variables within the final subset had statistically significant associations with impairment in motor function, executive function, and attention and working memory, consistent with previous research. Conclusion: We identified a subset of VDT performance variables that are associated with HAND and assess relevant functional abilities among individuals with HAND. Additional research is required to develop and validate a predictive HAND screening model incorporating this subset.

Simulator Pre-Screening of Underprepared Drivers Prior to Licensing On-Road Examination: Clustering of Virtual Driving Test Time Series Data.

BACKGROUND: A large Midwestern state commissioned a virtual driving test (VDT) to assess driving skills preparedness before the on-road examination (ORE). Since July 2017, a pilot deployment of the VDT in state licensing centers (VDT pilot) has collected both VDT and ORE data from new license applicants with the aim of creating a scoring algorithm that could predict those who were underprepared. OBJECTIVE: Leveraging data collected from the VDT pilot, this study aimed to develop and conduct an initial evaluation of a novel machine learning (ML)-based classifier using limited domain knowledge and minimal feature engineering to reliably predict applicant pass/fail on the ORE. Such methods, if proven useful, could be applicable to the classification of other time series data collected within medical and other settings. METHODS: We analyzed an initial dataset that comprised 4308 drivers who completed both the VDT and the ORE, in which 1096 (25.4%) drivers went on to fail the ORE. We studied 2 different approaches to constructing feature sets to use as input to ML algorithms: the standard method of reducing the time series data to a set of manually defined variables that summarize driving behavior and a novel approach using time series clustering. We then fed these representations into different ML algorithms to compare their ability to predict a driver's ORE outcome (pass/fail). RESULTS: The new method using time series clustering performed similarly compared with the standard method in terms of overall accuracy for predicting pass or fail outcome (76.1% vs 76.2%) and area under the curve (0.656 vs 0.682). However, the time series clustering slightly outperformed the standard method in differentially predicting failure on the ORE. The novel clustering method yielded a risk ratio for failure of 3.07 (95% CI 2.75-3.43), whereas the standard variables method yielded a risk ratio for failure of 2.68 (95% CI 2.41-2.99). In addition, the time series clustering method with logistic regression produced the lowest ratio of false alarms (those who were predicted to fail but went on to pass the ORE; 27.2%). CONCLUSIONS: Our results provide initial evidence that the clustering method is useful for feature construction in classification tasks involving time series data when resources are limited to create multiple, domain-relevant variables.

Can the artificial intelligence technique of reinforcement learning use continuously-monitored digital data to optimize treatment for weight loss?

Behavioral weight loss (WL) trials show that, on average, participants regain lost weight unless provided long-term, intensive-and thus costly-intervention. Optimization solutions have shown mixed success. The artificial intelligence principle of "reinforcement learning" (RL) offers a new and more sophisticated form of optimization in which the intensity of each individual's intervention is continuously adjusted depending on patterns of response. In this pilot, we evaluated the feasibility and acceptability of a RL-based WL intervention, and whether optimization would achieve equivalent benefit at a reduced cost compared to a non-optimized intensive intervention. Participants (n = 52) completed a 1-month, group-based in-person behavioral WL intervention and then (in Phase II) were randomly assigned to receive 3 months of twice-weekly remote interventions that were non-optimized (NO; 10-min phone calls) or optimized (a combination of phone calls, text exchanges, and automated messages selected by an algorithm). The Individually-Optimized (IO) and Group-Optimized (GO) algorithms selected interventions based on past performance of each intervention for each participant, and for each group member that fit into a fixed amount of time (e.g., 1 h), respectively. Results indicated that the system was feasible to deploy and acceptable to participants and coaches. As hypothesized, we were able to achieve equivalent Phase II weight losses (NO = 4.42%, IO = 4.56%, GO = 4.39%) at roughly one-third the cost (1.73 and 1.77 coaching hours/participant for IO and GO, versus 4.38 for NO), indicating strong promise for a RL system approach to weight loss and maintenance.

Design of an experimental protocol to examine medication non-adherence among young drivers diagnosed with ADHD: A driving simulator study.

The diagnosis of ADHD among teens and young adults has been associated with a higher likelihood of motor vehicle crashes. Some studies suggest a beneficial effect of ADHD medication but the exact efficacy is still being debated. Further, medication adherence, which is low in this age group, can further reduce effectiveness. Our long-term objective is to reduce unsafe driving among drivers with ADHD by detecting medication non-adherence through driver behavior modeling and monitoring. As a first step, we developed the described lab study protocol to obtain reliable driver behavior data that will then be used to design and train behavior models built through machine learning. This experimental study protocol was developed to systematically compare driving behaviors under two medication conditions (before and after intake of medication) among young adults with ADHD and a control group of non-ADHD. A driving simulator was used to examine driving behaviors and interactions with traffic. The primary outcome was speed management for two comparisons (ADHD vs. non-ADHD and before vs. after medication), and secondary objectives involved understanding differences among the participants utilizing self-reported surveys about ADHD symptoms, drivers' knowledge, and perception about safety. The study protocol was designed to maximize participant safety and efficiency of data collection, as multiple measures were collected over two 2-h study visits. The sampled ADHD drivers were demographically and psychosocially similar but clinically different from the non-ADHD group. Overall, this protocol was effective in participant recruitment and retention, allowed staggered data collection, and can be incorporated in a subsequent clinical trial that examines the efficacy of a machine-learning based driver monitoring intervention.

Behavioral Modeling Based on Probabilistic Finite Automata: An Empirical Study.

Imagine an agent that performs tasks according to different strategies. The goal of Behavioral Recognition (BR) is to identify which of the available strategies is the one being used by the agent, by simply observing the agent's actions and the environmental conditions during a certain period of time. The goal of Behavioral Cloning (BC) is more ambitious. In this last case, the learner must be able to build a model of the behavior of the agent. In both settings, the only assumption is that the learner has access to a training set that contains instances of observed behavioral traces for each available strategy. This paper studies a machine learning approach based on Probabilistic Finite Automata (PFAs), capable of achieving both the recognition and cloning tasks. We evaluate the performance of PFAs in the context of a simulated learning environment (in this case, a virtual Roomba vacuum cleaner robot), and compare it with a collection of other machine learning approaches.

Encyclopedia of bacterial gene circuits whose presence or absence correlate with pathogenicity--a large-scale system analysis of decoded bacterial genomes.

BACKGROUND: Bacterial infections comprise a global health challenge as the incidences of antibiotic resistance increase. Pathogenic potential of bacteria has been shown to be context dependent, varying in response to environment and even within the strains of the same genus. RESULTS: We used the KEGG repository and extensive literature searches to identify among the 2527 bacterial genomes in the literature those implicated as pathogenic to the host, including those which show pathogenicity in a context dependent manner. Using data on the gene contents of these genomes, we identified sets of genes highly abundant in pathogenic but relatively absent in commensal strains and vice versa. In addition, we carried out genome comparison within a genus for the seventeen largest genera in our genome collection. We projected the resultant lists of ortholog genes onto KEGG bacterial pathways to identify clusters and circuits, which can be linked to either pathogenicity or synergy. Gene circuits relatively abundant in nonpathogenic bacteria often mediated biosynthesis of antibiotics. Other synergy-linked circuits reduced drug-induced toxicity. Pathogen-abundant gene circuits included modules in one-carbon folate, two-component system, type-3 secretion system, and peptidoglycan biosynthesis. Antibiotics-resistant bacterial strains possessed genes modulating phagocytosis, vesicle trafficking, cytoskeletal reorganization, and regulation of the inflammatory response. Our study also identified bacterial genera containing a circuit, elements of which were previously linked to Alzheimer's disease. CONCLUSIONS: Present study produces for the first time, a signature, in the form of a robust list of gene circuitry whose presence or absence could potentially define the pathogenicity of a microbiome. Extensive literature search substantiated a bulk majority of the commensal and pathogenic circuitry in our predicted list. Scanning microbiome libraries for these circuitry motifs will provide further insights into the complex and context dependent pathogenicity of bacteria.