Results From a Pilot Study of an Automated Directly Observed Therapy Intervention Using Artificial Intelligence With Conditional Economic Incentives Among Young Adults With HIV.

BACKGROUND: Despite improvements in antiretroviral therapy (ART) availability, suboptimal adherence is common among youth with HIV (YWH) and can increase drug resistance and poor clinical outcomes. Our study examined an innovative mobile app-based intervention that used automated directly observed therapy (aDOT) using artificial intelligence, along with conditional economic incentives (CEIs) to improve ART adherence and enhance viral suppression among YWH. SETTING: We conducted a pilot study of the aDOT-CEI intervention, informed by the operant framework of Key Principles in Contingency Management Implementation, to improve ART adherence among YWH (18-29) in California and Florida who had an unsuppressed HIV viral load. METHODS: We recruited 28 virally unsuppressed YWH from AIDS Healthcare Foundation clinics, who used the aDOT platform for 3 months. Study outcomes included feasibility and acceptability, self-reported ART adherence, and HIV viral load. RESULTS: Participants reported high satisfaction with the app (91%), and 82% said that it helped them take their medication. Comfort with the security and privacy of the app was moderate (55%), and 59% indicated the incentives helped improve daily adherence. CONCLUSIONS: Acceptability and feasibility of the aDOT-CEI intervention were high with potential to improve viral suppression, although some a priori metrics were not met. Pilot results suggest refinements which may improve intervention outcomes, including increased incentive amounts, provision of additional information, and reassurance about app privacy and security. Additional research is recommended to test the efficacy of the aDOT-CEI intervention to improve viral suppression in a larger sample.

PopShift: A Thermodynamically Sound Approach to Estimate Binding Free Energies by Accounting for Ligand-Induced Population Shifts from a Ligand-Free Markov State Model.

Obtaining accurate binding free energies from in silico screens has been a long-standing goal for the computational chemistry community. However, accuracy and computational cost are at odds with one another, limiting the utility of methods that perform this type of calculation. Many methods achieve massive scale by explicitly or implicitly assuming that the target protein adopts a single structure, or undergoes limited fluctuations around that structure, to minimize computational cost. Others simulate each protein-ligand complex of interest, accepting lower throughput in exchange for better predictions of binding affinities. Here, we present the PopShift framework for accounting for the ensemble of structures a protein adopts and their relative probabilities. Protein degrees of freedom are enumerated once, and then arbitrarily many molecules can be screened against this ensemble. Specifically, we use Markov state models (MSMs) as a compressed representation of a protein's thermodynamic ensemble. We start with a ligand-free MSM and then calculate how addition of a ligand shifts the populations of each protein conformational state based on the strength of the interaction between that protein conformation and the ligand. In this work we use docking to estimate the affinity between a given protein structure and ligand, but any estimator of binding affinities could be used in the PopShift framework. We test PopShift on the classic benchmark pocket T4 Lysozyme L99A. We find that PopShift is more accurate than common strategies, such as docking to a single structure and traditional ensemble docking─producing results that compare favorably with alchemical binding free energy calculations in terms of RMSE but not correlation─and may have a more favorable computational cost profile in some applications. In addition to predicting binding free energies and ligand poses, PopShift also provides insight into how the probability of different protein structures is shifted upon addition of various concentrations of ligand, providing a platform for predicting affinities and allosteric effects of ligand binding. Therefore, we expect PopShift will be valuable for hit finding and for providing insight into phenomena like allostery.

Youth Ending the HIV Epidemic (YEHE): Protocol for a pilot of an automated directly observed therapy intervention with conditional economic incentives among young adults with HIV.

BACKGROUND: Young adults have a disproportionately high rate of HIV infection, high rates of attrition at all stages of the HIV care continuum, and an elevated probability of disease progression and transmission. Tracking and monitoring objective measures of antiretroviral therapy (ART) adherence in real time is critical to bolster the accuracy of research data, support adherence, and improve clinical outcomes. However, adherence monitoring often relies on self-reported and retrospective data or requires additional effort from providers to understand individual adherence patterns. In this study, we will monitor medication-taking using a real-time objective measure of adherence that does not rely on self-report or healthcare providers for measurement. METHODS: The Youth Ending the HIV Epidemic (YEHE) study will pilot a novel automated directly observed therapy-conditional economic incentive (aDOT-CEI) intervention to improve ART adherence among youth with HIV (YWH) in California and Florida who have an unsuppressed HIV viral load. The aDOT app uses facial recognition to record adherence each day, and then economic incentives are given based on a participant's confirmed adherence. We will enroll participants in a 3-month pilot study to assess the feasibility and acceptability of the aDOT-CEI intervention using predefined metrics. During and after the trial, a subsample of the pilot participants and staff/providers from participating AIDS Healthcare Foundation (AHF) clinics will participate in individual in-depth interviews to explore intervention and implementation facilitators and barriers. DISCUSSION: YEHE will provide data on the use of an aDOT-CEI intervention to improve adherence among YWH who are not virologically suppressed. The YEHE study will document the feasibility and acceptability and will explore preliminary data to inform a trial to test the efficacy of aDOT-CEI. This intervention has the potential to effectively improve ART adherence and virologic suppression among a key population experiencing health disparities. TRIAL REGISTRATION: The trial registration number is NCT05789875.