Sharp, Richard R.

Abstract Pharmacogenomic (PGx) biomarkers integrated using machine learning can be embedded within the electronic health record (EHR) to provide clinicians with individualized predictions of drug treatment outcomes. Currently, however, drug alerts in the EHR are largely generic (not patient‐specific) and contribute to increased clinician stress and burnout. Improving the usability of PGx alerts is an urgent need. Therefore, this work aimed to identify principles for optimal PGx alert design through a health‐system‐wide, mixed‐methods study. Clinicians representing multiple practices and care settings ( N = 1062) in urban, rural, and underserved regions were invited to complete an electronic survey comparing the usability of three drug alerts for citalopram, as a case study. Alert 1 contained a generic warning of pharmacogenomic effects on citalopram metabolism. Alerts 2 and 3 provided patient‐specific predictions of citalopram efficacy with varying depth of information. Primary outcomes included the System's Usability Scale score (0–100 points) of each alert, the perceived impact of each alert on stress and decision‐making, and clinicians' suggestions for alert improvement. Secondary outcomes included the assessment of alert preference by clinician age, practice type, and geographic setting. Qualitative information was captured to provide context to quantitative information. The final cohort comprised 305 geographically and clinically diverse clinicians. A simplified, individualized alert (Alert 2) was perceived as beneficial for decision‐making and stress compared with a more detailed version (Alert 3) and the generic alert (Alert 1) regardless of age, practice type, or geographic setting. Findings emphasize the need for clinician‐guided design of PGx alerts in the era of digital medicine.

Background/Objectives: Multi-gene, multi-cancer, hereditary cancer risk screenings may be useful in cancer prevention and treatment, not only for cancer patients but also for patients’ family members. If genetic cancer screening is to have the widest possible benefit, it must be extended into diverse cancer care settings that serve diverse patient communities, providing cancer patients and their relatives with individualized cancer risk evaluations. Little research, to date, has examined the impact of extending multigenic cancer screening into diverse settings. Without empirical data characterizing the support needs of cancer patients and their family members, we may not adequately satisfy the needs of all patients and risk exacerbating existing disparities in cancer care and outcomes. Methods: We examined patient perspectives on the sharing of genetic results with at-risk family members by surveying a racially diverse sample of cancer patients receiving a multi-gene, multi-cancer risk screen in a community hospital setting. Results: In a survey of 230 cancer patients, we found that intent to share results with family members was high but varied across family member types. More respondents planned to disclose results to at least one sister (82.5%) compared to at least one brother (73.1%). Over one-fourth of participants (27.4%) were either uncertain about sharing or intended to withhold their genomic screening results from at least one at-risk family member eligible for cascade testing. Participants were more likely to withhold their results from a sibling than from a child. Furthermore, intent to share across all family member types was lower if probands failed to identify at least one benefit to sharing. Conclusions: Understanding factors associated with decisions to share results with at-risk relatives in diverse patient populations can help clinicians support cascade genetic cancer screenings in diverse communities and settings.

Background: Large biobanks that link biological specimens with specimen donors’ health histories are a critical tool for precision medicine, and many health care institutions have invested significant resources in setting up and building up large collections for this purpose. As biobanks require consented participation from thousands of individual donors, much research has focused on the values and preferences of new and prospective donors who are actively contemplating an invitation to participate in the collection. Few studies, however, have focused on participants’ opinions about their biobank participation in the months and years following enrollment. Methods: We conducted a survey in a large, established biobank and evaluated participants’ levels of decisional regret regarding their decision to enroll in the biobank. Results: We found very low levels of decisional regret among established biobank participants. Multivariable regression analysis found that age, length of time in the biobank, lower educational attainment, inadequate health literacy, and previous invitations to research participation were all significant predictors of elevated regret. Discussion: Among those with elevated regret, several demographic factors may point to elevated likelihood of decisional regret. More research is needed to identify factors associated with long-term satisfaction with biobank participation and with elevated risk of regret and/or withdrawal from the collection.

Importance Artificial intelligence (AI) tools are rapidly integrating into cancer care. Understanding stakeholder views on ethical issues associated with the implementation of AI in oncology is critical to optimal deployment. Objective To evaluate oncologists’ views on the ethical domains of the use of AI in clinical care, including familiarity, predictions, explainability (the ability to explain how a result was determined), bias, deference, and responsibilities. Design, Setting, and Participants This cross-sectional, population-based survey study was conducted from November 15, 2022, to July 31, 2023, among 204 US-based oncologists identified using the National Plan & Provider Enumeration System. Main Outcomes and Measures The primary outcome was response to a question asking whether participants agreed or disagreed that patients need to provide informed consent for AI model use during cancer treatment decisions. Results Of 387 surveys, 204 were completed (response rate, 52.7%). Participants represented 37 states, 120 (63.7%) identified as male, 128 (62.7%) as non-Hispanic White, and 60 (29.4%) were from academic practices; 95 (46.6%) had received some education on AI use in health care, and 45.3% (92 of 203) reported familiarity with clinical decision models. Most participants (84.8% [173 of 204]) reported that AI-based clinical decision models needed to be explainable by oncologists to be used in the clinic; 23.0% (47 of 204) stated they also needed to be explainable by patients. Patient consent for AI model use during treatment decisions was supported by 81.4% of participants (166 of 204). When presented with a scenario in which an AI decision model selected a different treatment regimen than the oncologist planned to recommend, the most common response was to present both options and let the patient decide (36.8% [75 of 204]); respondents from academic settings were more likely than those from other settings to let the patient decide (OR, 2.56; 95% CI, 1.19-5.51). Most respondents (90.7% [185 of 204]) reported that AI developers were responsible for the medico-legal problems associated with AI use. Some agreed that this responsibility was shared by physicians (47.1% [96 of 204]) or hospitals (43.1% [88 of 204]). Finally, most respondents (76.5% [156 of 204]) agreed that oncologists should protect patients from biased AI tools, but only 27.9% (57 of 204) were confident in their ability to identify poorly representative AI models. Conclusions and Relevance In this cross-sectional survey study, few oncologists reported that patients needed to understand AI models, but most agreed that patients should consent to their use, and many tasked patients with choosing between physician- and AI-recommended treatment regimens. These findings suggest that the implementation of AI in oncology must include rigorous assessments of its effect on care decisions as well as decisional responsibility when problems related to AI use arise.

Introduction Artificial Intelligence (AI) is an emerging technology that promises advancements across blood cancer discovery and care delivery. There are already FDA-approved uses of AI in hematology and oncology but few data available about its use or utility. Concerns have been raised over AI's potential biases, “explainability,” and who is responsible for its use. Oncologists' familiarity with AI and perspectives on these issues are not well known and are critical to understanding the ethical deployment of AI in blood cancer care. Methods From January to July 2023, we performed a national cross-sectional survey of practicing oncologists. A draft survey instrument was developed by a team with content and methodological expertise. Iterative refinement occurred through cognitive debriefing with 5 practicing hematologist/oncologists. The final instrument included 24 questions covering domains of AI familiarity, predictions, explainability, and responsibilities. A random sample of US oncologists was identified using the National Plan & Provider Enumeration System. Paper surveys were mailed with $25 incentivizing gift cards. Reminder letters and phone calls were used for non-responders with an electronic survey option provided. Responses were analyzed descriptively. X2 testing assessed bivariate associations between responses and participant practice setting, with odds ratios (OR) reported. Results Of 399 mailed surveys, 12 were undeliverable and 201 were completed for a response rate of 51.9%. Question missingness was <1%. Participants were 63.2% White, 16.9% Indian Asian, 10.0% Eastern Asian or Pacific Islander, and 4.5% Black; 6.0% were Hispanic. They represented 37 states. The majority were male (63.7%), 40-59 years old (54.2%), and had no specific training in AI (52.2%); 68.2% had at least 11 years in practice and 29.9% practiced at a primary academic hospital. Questions assessing overall familiarity with and predictions related to AI are shown in Table 1. Those at primary academic hospitals were more likely to be familiar with radiology models (OR 2.82, p<0.001) but not pathology, prognostic, or clinical decision models (all p>0.05). They were more likely to predict that AI would improve side effect management (OR 2.01, p=0.03) and end-of-life decision making (OR 2.07, p=0.02). High proportions of respondents thought that AI prognostic (67.1%) and clinical decision models (62.1%) needed to be explainable by clinicians and researchers to be used in clinic. When posed with a scenario where an FDA-approved AI model selects a different regimen than the oncologist planned to propose (Figure 1), the largest proportion reported they would present both options and let the patient decide (37.3%). Of those recommending a regimen, respondents from primary academic hospitals more frequently recommend the AI-generated regimen (56.1%), while respondents from elsewhere recommended their original regimen (69.0%; OR 2.85, p=0.007). Acceptability of some direct-to-patient AI model applications is shown in Table 1. A majority of respondents (90.5%) thought that AI developers should be responsible for medico-legal problems caused by AI use; 47.8% thought that physicians using the tool should be responsible. Though most (76.1%) agreed that it was oncologists' responsibility to protect patients from biased AI tools, few (27.3%) were confident in their ability to identify how representative the data used in an AI model was relative to the population with that cancer (including 66.7% of those who agreed it was oncologists' responsibility). More respondents thought that patients should need to consent to the use of AI tools in cancer treatment decisions (81.1%) than cancer diagnosis (55.7%); those from primary academic hospitals were less likely to respond that patients should consent for treatment or diagnosis (OR 0.43, p=0.02 and OR 0.44, p=0.009). Conclusions In this national survey of oncologists' views on AI, there was optimism about its impact on care with notable caveats related to end-of-life care, patient trust, and care disparities. Despite many approving use of AI models too complex for patients to explain, a substantial proportion deferred to patient choice when AI and physician recommendations differed. There was also dissonance between accepting responsibility to protect patients from bias and respondents' self-perceived ability to do so.

Introduction: Relatively little is known about outcomes following return of secondary findings detected in large scale sequencing projects. We assessed 1-year outcomes following return of pathogenic/likely pathogenic (P/LP) variants associated with familial hypercholesterolemia (FH) in phase III of the eMERGE network (2015-2019). Methods: Adult participants (n=18,544) at 7 sites were enrolled in a prospective cohort study to study the clinical impact of returning results from targeted sequencing of 68 actionable genes, including LDLR , APOB , and PCSK9 . Process, intermediate, and/or clinical outcomes within 1-year after return of results (RoR) were ascertained by electronic health record (EHR) review. A process outcome was defined as referral to a specialist or ordering new tests, including lipid profile and screening tests for coronary heart disease. An intermediate outcome was defined as new diagnosis of FH or atherosclerotic cardiovascular disease. A clinical outcome was defined as initiation or change in lipid-lowering medication. The primary outcomes were a new diagnosis of FH and modification of lipid lowering therapy. Results: Results were returned to 134 individuals, and data for 119 participants were available for the outcomes analysis. Process (86%), intermediate (49%), and/or clinical (26%) outcomes occurred in 92% of participants. Process outcomes included 72% with new tests ordered and 61% referred to a specialist. Before RoR, 86.5% of individuals with FH associated P/LP variants had a diagnosis of hypercholesterolemia but only 17.6% had a diagnosis of FH; 89% were on a statin but only 58% were on a high intensity statin. Following RoR, 44% (52/119) received a new diagnosis of FH. Lipid lowering treatment was modified in 26% (31/119), including initiation of a statin in 5%, increasing statin dose in 13%, and adding ezetimibe or a PCSK9 inhibitor in 12.6%. Conclusions: In a multisite cohort of EHR-linked biobanks, monogenic FH was underdiagnosed (only 17.6% had a specific diagnosis) and undertreated (only 58% were on a high intensity statin); 44% of participants received a new diagnosis of FH and 26% had lipid lowering treatment modified after RoR. These results highlight the clinical utility of returning FH variants in EHR-linked biobanks.

Background: The implications of secondary findings detected in large-scale sequencing projects remain uncertain. We assessed prevalence and penetrance of pathogenic familial hypercholesterolemia (FH) variants, their association with coronary heart disease (CHD), and 1-year outcomes following return of results in phase III of the electronic medical records and genomics network. Methods: Adult participants (n=18 544) at 7 sites were enrolled in a prospective cohort study to assess the clinical impact of returning results from targeted sequencing of 68 actionable genes, including LDLR , APOB , and PCSK9 . FH variant prevalence and penetrance (defined as low-density lipoprotein cholesterol >155 mg/dL) were estimated after excluding participants enrolled on the basis of hypercholesterolemia. Multivariable logistic regression was used to estimate the odds of CHD compared to age- and sex-matched controls without FH-associated variants. Process (eg, referral to a specialist or ordering new tests), intermediate (eg, new diagnosis of FH), and clinical (eg, treatment modification) outcomes within 1 year after return of results were ascertained by electronic health record review. Results: The prevalence of FH-associated pathogenic variants was 1 in 188 (69 of 13,019 unselected participants). Penetrance was 87.5%. The presence of an FH variant was associated with CHD (odds ratio, 3.02 [2.00–4.53]) and premature CHD (odds ratio, 3.68 [2.34–5.78]). At least 1 outcome occurred in 92% of participants; 44% received a new diagnosis of FH and 26% had treatment modified following return of results. Conclusions: In a multisite cohort of electronic health record–linked biobanks, monogenic FH was prevalent, penetrant, and associated with presence of CHD. Nearly half of participants with an FH-associated variant received a new diagnosis of FH and a quarter had treatment modified after return of results. These results highlight the potential utility of sequencing electronic health record–linked biobanks to detect FH.