Current Status and Future Directions: The Application of Artificial Intelligence/Machine Learning for Precision Medicine.

Technological innovations, such as artificial intelligence (AI) and machine learning (ML), have the potential to expedite the goal of precision medicine, especially when combined with increased capacity for voluminous data from multiple sources and expanded therapeutic modalities; however, they also present several challenges. In this communication, we first discuss the goals of precision medicine, and contextualize the use of AI in precision medicine by showcasing innovative applications (e.g., prediction of tumor growth and overall survival, biomarker identification using biomedical images, and identification of patient population for clinical practice) which were presented during the February 2023 virtual public workshop entitled "Application of Artificial Intelligence and Machine Learning for Precision Medicine," hosted by the US Food and Drug Administration (FDA) and University of Maryland Center of Excellence in Regulatory Science and Innovation (M-CERSI). Next, we put forward challenges brought about by the multidisciplinary nature of AI, particularly highlighting the need for AI to be trustworthy. To address such challenges, we subsequently note practical approaches, viz., differential privacy, synthetic data generation, and federated learning. The proposed strategies - some of which are highlighted presentations from the workshop - are for the protection of personal information and intellectual property. In addition, methods such as the risk-based management approach and the need for an agile regulatory ecosystem are discussed. Finally, we lay out a call for action that includes sharing of data and algorithms, development of regulatory guidance documents, and pooling of expertise from a broad-spectrum of stakeholders to enhance the application of AI in precision medicine.

An AI Approach to Generating MIDD Assets Across the Drug Development Continuum.

Model-informed drug development involves developing and applying exposure-based, biological, and statistical models derived from preclinical and clinical data sources to inform drug development and decision-making. Discrete models are generated from individual experiments resulting in a single model expression that is utilized to inform a single stage-gate decision. Other model types provide a more holistic view of disease biology and potentially disease progression depending on the appropriateness of the underlying data sources for that purpose. Despite this awareness, most data integration and model development approaches are still reliant on internal (within company) data stores and traditional structural model types. An AI/ML-based MIDD approach relies on more diverse data and is informed by past successes and failures including data outside a host company (external data sources) that may enhance predictive value and enhance data generated by the sponsor to reflect more informed and timely experimentation. The AI/ML methodology also provides a complementary approach to more traditional modeling efforts that support MIDD and thus yields greater fidelity in decision-making. Early pilot studies support this assessment but will require broader adoption and regulatory support for more evidence and refinement of this paradigm. An AI/ML-based approach to MIDD has the potential to transform regulatory science and the current drug development paradigm, optimize information value, and increase candidate and eventually product confidence with respect to safety and efficacy. We highlight early experiences with this approach using the AI compute platforms as representative examples of how MIDD can be facilitated with an AI/ML approach.

An exploratory machine learning approach to identify placebo responders in pharmacological binge eating disorder trials.

Randomized, placebo-controlled trials for binge eating disorder (BED) have revealed highly variable, and often marked, rates of short-term placebo response. Several quantitative based analyses in patients with BED have inconsistently demonstrated which patient factors attribute to an increase in placebo response. The objective of this study is to utilize machine learning (ML) algorithms to identify moderators of placebo response in patients with BED. Data were pooled from 12 randomized placebo-controlled trials evaluating different treatment options for BED. The final dataset consisted of 189 adults receiving placebo with complete information of baseline variables. Placebo responders were defined as patients experiencing ≥75% reduction in binge eating frequency (BEF) at study end point. Nine patient prerandomization variables were included as predictors. Patients were divided into training and testing subsets according to an 75%:25% distribution while preserving the proportion of placebo responders. All analysis was performed in the software Pumas 2.0. Gaussian Naïve Bayes algorithm showed the best cross-validation accuracy (~64%) and was chosen as the final algorithm. Shapley analysis suggested that patients with low baseline BEF and anxiety status were strong moderators of placebo response. Upon applying the final algorithm on the test dataset, the resulting sensitivity was 88% and prediction accuracy was 72%. This is the first application of ML to identify moderators of placebo response in BED. The results of this analysis confirm previous findings of lesser baseline disease severity and adds that patients with no anxiety are more susceptible to placebo response.

Population Pharmacokinetics of Vancomycin in Pregnant Women.

Objective: Vancomycin is a glycopeptide antibacterial indicated for serious gram-positive infections. Pharmacokinetics (PK) of vancomycin have not been described in pregnant women. This study aims to characterize the PK disposition of vancomycin in pregnant women based on data acquired from a database of routine hospital care for therapeutic drug monitoring to better inform dosing decisions. Methods: In this study, plasma drug concentration data from 34 pregnant hospitalized women who were administered intravenous vancomycin was analyzed. A population pharmacokinetic (PPK) model was developed using non-linear mixed effects modeling. Model selection was based on statistical criterion, graphical analysis, and physiologic relevance. Using the final model AUC0-24 (PK efficacy index of vancomycin) was compared with non-pregnant population. Results: Vancomycin PK in pregnant women were best described by a two-compartment model with first-order elimination and the following parameters: clearance (inter individual variability) of 7.64 L/hr (32%), central volume of 67.35 L, inter-compartmental clearance of 9.06 L/h, and peripheral volume of 37.5 L in a typical patient with 175 ml/min creatinine clearance (CRCL) and 45 kg fat-free mass (FFM). The calculated geometric mean of AUC0-24 for the pregnant population was 223 ug.h/ ml and 226 ug.h/ ml for the non-pregnant population. Conclusion: Our analysis suggests that vancomycin PK in pregnant women is consistent with non-pregnant adults and the dosing regimens used for non-pregnant patients may also be applicable to pregnant patients.

In search of an ideal test for diagnosis and prognosis of kala-azar.

The latex agglutination test (KAtex), direct agglutination test (DAT), and the rK39 immuno-chromatographic strip test (dipstick test) were evaluated for their role in the diagnosis and prognosis of visceral leishmaniasis (kala-azar) in India. Sera and urine samples from 455 subjects--150 confirmed visceral leishmaniasis cases, 160 endemic controls, 100 non-endemic controls, and 45 other febrile diseases--were included in the study. The sensitivity of the KAtex, DAT, and rK39 strip test was 87% [95% confidence interval (CI) 80-96], 93.3% (95% CI 88-100), and 98% (95% CI 93-100) respectively. The specificity of these tests was 98% (95% CI 93-100), 93% (95% CI 87-100), and 89% (95% CI 82-97) for the KAtex, DAT, and rK39 strip test respectively. Fifty cases were followed up and subjected to the KAtex, DAT, and rK39 strip test after 30 days of successful treatment. The DAT and rK39 strip test showed positive results in all the 50 cases whereas the KAtex showed no positive reaction in any case. Based on the results, it is concluded that the sensitivity and specificity of the DAT and rK39 strip test are comparable but the greater convenience of use of the strip test makes it a better tool for the diagnosis of visceral leishmaniasis in the peripheral areas of endemic regions whereas the sensitivity of the KAtex needs to be improved to promote its use as a first-line diagnostic test in the field-setting. It may be used for the prognosis of the disease as antigen becomes undetectable in urine after 30 days of the completion of the treatment. Alternatively, it can be used as an adjunct with rK39 for sero-epidemiological surveys.