Background/Objectives Patient reported outcome measures (PROMs) capture the patient’s own perspective on their health, illness, and therapeutic effects on the illness. However, their analysis and interpretation is challenging due to their multidimensional nature, poor correlation with clinical and physiological outcomes, lack of a standardized interpretation, and discrete nature of the data. We describe a generative stochastic modeling approach and show that it improves the pharmacometric characterization of multi-item PROMS.

Methods The Restricted Boltzmann Machine (RBM) modelling approach was described and used to model the relationship between efavirenz mid-dose concentrations,clinical variables (CD count and Viral load) and time varying patient reported neuropsychological impairment symptoms. The model was used to derive a variable importance ranking for all the PROM items, clinical variables, and drug concentrations.

Results The model adequately characterizes the PROMs. Variable importance ranking reveals that mid-dose concentrations are not more predictive of post-baseline PROMs than clinical variables and baseline PROMs.

Conclusions Generative stochastic modeling with RBMs adequately characterizes PROMS and their relationship to other variables and drug concentrations, is readily adaptable to the pharmacometric workflow, and is able to generate individual level disease progression trajectories using baseline variables.

The authors have declared no competing interest.

This study did not receive any funding

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The study that generated the data used in this analysis was approved by the institutional review boards of Mulago and Butabika hospitals and the Uganda and National Council for Science and Technology. The data has been published before in different forms multiple times and no new data was collected for this analysis

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

Conflict of Interest Non to declare

Funding This study was not funded

Data Sharing and Data Availability The data used in this study are available upon reasonable request.

All data produced in the present work are contained in the manuscript