Augmenting the Transplant Team With Artificial Intelligence: Toward Meaningful AI Use in Solid Organ Transplant.

Advances in systems immunology, such as new biomarkers, offer the potential for highly personalized immunosuppression regimens that could improve patient outcomes. In the future, integrating all of this information with other patient history data will likely have to rely on artificial intelligence (AI). AI agents can help augment transplant decision making by discovering patterns and making predictions for specific patients that are not covered in the literature or in ways that are impossible for humans to anticipate by integrating vast amounts of data (e.g. trending across numerous biomarkers). Similar to other clinical decision support systems, AI may help overcome human biases or judgment errors. However, AI is not widely utilized in transplant to date. In this rapid review, we survey the methods employed in recent research in transplant-related AI applications and identify concerns related to implementing these tools. We identify three key challenges (bias/accuracy, clinical decision process/AI explainability, AI acceptability criteria) holding back AI in transplant. We also identify steps that can be taken in the near term to help advance meaningful use of AI in transplant (forming a Transplant AI Team at each center, establishing clinical and ethical acceptability criteria, and incorporating AI into the Shared Decision Making Model).

Patient access to chronic medications during the Covid-19 pandemic: Evidence from a comprehensive dataset of US insurance claims.

Patient access and adherence to chronic medications is critical. In this work, we evaluate whether disruptions related to Covid-19 have affected new and existing patients' access to pharmacological therapies without interruption. We do so by performing a retrospective analysis on a dataset of 9.4 billion US prescription drug claims from 252 million patients from May, 2019 through August, 2020 (about 93% of prescriptions dispensed within those months). Using fixed effect (conditional likelihood) linear models, we evaluate continuity of care, how many days of supply patients received, and the likelihood of discontinuing therapy for drugs from classes with significant population health impacts. Findings indicate that more prescriptions were filled in March 2020 than in any prior month, followed by a significant drop in monthly dispensing. Compared to the pre-Covid era, a patient's likelihood of discontinuing some medications increased after the spread of Covid: norgestrel-ethinyl estradiol (hormonal contraceptive) discontinuation increased 0.62% (95% CI: 0.59% to 0.65%, p<0.001); dexmethylphenidate HCL (ADHD stimulant treatment) discontinuation increased 2.84% (95% CI: 2.79% to 2.89%, p<0.001); escitalopram oxalate (SSRI antidepressant) discontinuation increased 0.57% (95% CI: 0.561% to 0.578%, p<0.001); and haloperidol (antipsychotic) discontinuation increased 1.49% (95% CI: 1.41% to 1.57%, p<0.001). In contrast, the likelihood of discontinuing tacrolimus (immunosuppressant) decreased 0.15% (95% CI: 0.12% to 0.19%, p<0.001). The likelihood of discontinuing buprenorphine/naloxone (opioid addiction therapy) decreased 0.59% (95% CI: 0.55% to 0.62% decrease, p<0.001). We also observe a notable decline in new patients accessing these latter two therapies. Most US patients were able to access chronic medications during the early months of Covid-19, but still were more likely to discontinue their therapies than in previous months. Further, fewer than normal new patients started taking medications that may be vital to their care. Providers would do well to inquire about adherence and provide prompt, nonjudgmental, re-initiation of medications. From a policy perspective, opioid management programs seem to demonstrate a robust ability to manage existing patients in spite of disruption.