Deng, Yihong

Introduction: Recently, an artificial intelligence (AI) algorithm was validated for identifying ECG signatures of atrial fibrillation (AF) risk during normal sinus rhythm. Traditionally, socioeconomically disadvantaged populations are less likely to receive novel or guideline-recommended treatments, and have high chronic disease burden, including cardiovascular diseases. There have also been concerns about new technologies creating a digital divide, worsening existing health disparities. Hypothesis: An AI algorithm will detect AF risk unequally across patients with different levels of social determinants of health (SDOH). Methods: The initial prospective, non-randomized, interventional study leveraged EHR and digital technologies to prospectively enroll 1004 patients with a broad range of AI-ECG risks of AF, who received continuous cardiac rhythm monitoring for up to 30 days. The Area Deprivation Index (ADI) was used as a composite measure of SDOH which is comprised of indicators spanning four domains: income, education, employment, and house quality. 904 intervention patients linked to the ADI data were matched to 904 real-world control patients derived from eligible but unenrolled patients. Those with ADI under 33% were defined as having better SODH; and patients with ADI above 33% were defined as having worse SODH. Results: Median age was 74 years and 38% were women. After matching, the intervention and control arms were balanced in all baseline characteristics, including HF, HTN, diabetes, stroke, CAD and ADI. A hazard ratio of 3.11 (P<0.001) was computed when comparing intervention to control for primary AF diagnosis outcome. In patients with worse SDOH, the intervention increased AF detection from 2.6% to 8.8% (HR 3.63 [2.09, 6.32]); in the better SDOH, the intervention increased AF detection from 3.9% to 9.3% (2.41 [1.23, 4.74]). Conclusions: An AI-guided AF screening program increased the detection of AF in both patients with better or worse SDOH. The current study validates the use of AI in historically disadvantaged populations displaying the possibility for broad implementation with decreased possibility of perpetuating disparities.

Objective To build on the recently completed GRADE (Glycemia Reduction Approaches in Diabetes: A Comparative Effectiveness Study) randomised trial examining the comparative effectiveness of second line glucose lowering drugs in achieving and maintaining glycaemic control in adults with type 2 diabetes. Design Emulation of a target trial. Setting Medical and pharmacy claims data from the OptumLabs Data Warehouse, a de-identified US national dataset of beneficiaries of commercially insured and Medicare Advantage plans, 29 March 2013 to 30 June 2021. Participants Adults (≥18 years) with type 2 diabetes who first started taking glimepiride, sitagliptin, liraglutide, insulin glargine, or canagliflozin between 29 March 2013 and 30 June 2021. Participants were treatment naive or were receiving metformin monotherapy at the time of starting the study drug. Main outcome measures The main outcomes were time to primary and secondary metabolic failure of the assigned treatment, calculated as days to haemoglobin A1c levels of ≥7.0% and >7.5%, respectively. Secondary metabolic, cardiovascular, and microvascular outcomes were analysed as specified in the GRADE statistical analysis plan. Propensity scores were estimated with the gradient boosting method, and inverse propensity score weighting was used to emulate randomisation to the treatment groups, which were then compared with Cox proportional hazards regression. (Results The study cohort included participants starting treatment with glimepiride (n=20 511), liraglutide (n=5569), sitagliptin (n=13 039), insulin glargine (n=7262), and canagliflozin (n=5290). The insulin glargine arm was excluded because of insufficient control of confounding. Median times to primary metabolic failure were 439 (95% confidence interval 400 to 489) days in the canagliflozin arm, 439 (426 to 453) days in the glimepiride arm, 624 (567 to 731) days in the liraglutide arm, and 461 (442 to 482) days in the sitagliptin arm. Median time to secondary metabolic failure was also longest in the liraglutide arm. Adults receiving liraglutide had the lowest one year cumulative incidence rate of primary metabolic failure (0.37, 95% confidence interval 0.35 to 0.40) followed by sitagliptin (0.44, 0.43 to 0.45), glimepiride (0.45, 0.44 to 0.45), and canagliflozin (0.46, 0.44 to 0.48). Similarly, the one year cumulative incidence rate of secondary metabolic failure was 0.27 (0.25 to 0.29) in the canagliflozin arm, 0.28 (0.27 to 0.29) in the glimepiride arm, 0.23 (0.21 to 0.26) in the liraglutide arm, and 0.28 (0.27 to 0.29) in the sitagliptin arm. No differences were observed between the study arms in the rates of microvascular and macrovascular complications. Conclusions In this target trial emulation of an expanded GRADE study framework, liraglutide was more effective in achieving and maintaining glycaemic control as a second line glucose lowering drug than canagliflozin, sitagliptin, or glimepiride.

Background/aims There has been growing interest in better understanding the potential of observational research methods in medical product evaluation and regulatory decision-making. Previously, we used linked claims and electronic health record data to emulate two ongoing randomized controlled trials, characterizing the populations and results of each randomized controlled trial prior to publication of its results. Here, our objective was to compare the populations and results from the emulated trials with those of the now-published randomized controlled trials. Methods This study compared participants’ demographic and clinical characteristics and study results between the emulated trials, which used structured data from OptumLabs Data Warehouse, and the published PRONOUNCE and GRADE trials. First, we examined the feasibility of implementing the baseline participant characteristics included in the published PRONOUNCE and GRADE trials’ using real-world data and classified each variable as ascertainable, partially ascertainable, or not ascertainable. Second, we compared the emulated trials and published randomized controlled trials for baseline patient characteristics (concordance determined using standardized mean differences <0.20) and results of the primary and secondary endpoints (concordance determined by direction of effect estimates and statistical significance). Results The PRONOUNCE trial enrolled 544 participants, and the emulated trial included 2226 propensity score-matched participants. In the PRONOUNCE trial publication, one of the 32 baseline participant characteristics was listed as an exclusion criterion on ClinicalTrials.gov but was ultimately not used. Among the remaining 31 characteristics, 9 (29.0%) were ascertainable, 11 (35.5%) were partially ascertainable, and 10 (32.2%) were not ascertainable using structured data from OptumLabs. For one additional variable, the PRONOUNCE trial did not provide sufficient detail to allow its ascertainment. Of the nine variables that were ascertainable, values in the emulated trial and published randomized controlled trial were discordant for 6 (66.7%). The primary endpoint of time from randomization to the first major adverse cardiovascular event and secondary endpoints of nonfatal myocardial infarction and stroke were concordant between the emulated trial and published randomized controlled trial. The GRADE trial enrolled 5047 participants, and the emulated trial included 7540 participants. In the GRADE trial publication, 8 of 34 (23.5%) baseline participant characteristics were ascertainable, 14 (41.2%) were partially ascertainable, and 11 (32.4%) were not ascertainable using structured data from OptumLabs. For one variable, the GRADE trial did not provide sufficient detail to allow for ascertainment. Of the eight variables that were ascertainable, values in the emulated trial and published randomized controlled trial were discordant for 4 (50.0%). The primary endpoint of time to hemoglobin A1c ≥7.0% was mostly concordant between the emulated trial and the published randomized controlled trial. Conclusion Despite challenges, observational methods and real-world data can be leveraged in certain important situations for a more timely evaluation of drug effectiveness and safety in more diverse and representative patient populations.

ImportancePatterns of clinical utilization and comparative effectiveness of anticoagulants for cancer-associated thrombosis (CAT) remain largely unexplored.ObjectivesTo assess patterns of and factors associated with anticoagulant use and to evaluate the comparative effectiveness of contemporary anticoagulants in patients with active cancer in a clinical setting.Design, Setting, and ParticipantsThis retrospective cohort study obtained deidentified OptumLabs electronic health record claims data from January 1, 2012, to September 30, 2019. Adult patients (≥18 years of age) with a primary cancer diagnosis (except skin cancer) during at least 1 inpatient or 2 outpatient visits within 6 months before the venous thromboembolism (VTE) date were included. Data were analyzed from April 2020 to September 2021.ExposuresThe patients were grouped according to the anticoagulant prescribed: (1) direct oral anticoagulants (DOACs), (2) low-molecular-weight heparin (LMWH), and (3) warfarin.Main Outcomes and MeasuresOdds ratios (ORs) were used to present the association between factors of interest and utilization of anticoagulants. Main efficacy outcomes included risk of VTE recurrence and all-cause mortality. Main safety outcomes included the risk of hospitalization due to major bleeding. Relative treatment effect estimates were expressed as hazard ratios (HRs) with 95% CIs.ResultsThis study included 5100 patients (mean [SD] age, 66.3 [12.3] years; 2670 [52.4%] women; 799 [15.7%] Black, 389 [7.6%] Hispanic, and 3559 [69.8%] White individuals). Overall, 2512 (49.3%), 1488 (29.2%), and 1460 (28.6%) filled prescriptions for DOACs, LMWH, and warfarin, respectively. The median (IQR) treatment duration was 3.2 (1.0-6.5) months for DOACs, 3.1 (1.0-6.8) months for warfarin, and 1.8 (0.9-3.8) months for LWMH. Patients with lung (OR, 2.07; 95% CI, 1.12-3.65), urological (OR, 1.94; 95% CI,1.08-3.49), gynecological (OR, 4.25; 95% CI, 2.31-7.82), and colorectal (OR, 2.26; 95% CI, 1.20-4.32) cancer were associated with increased prescriptions for LMWH compared with DOACs. LMWH (HR, 1.47; 95% CI, 1.14-1.90) and warfarin (HR, 1.46; 95% CI, 1.13-1.87) were associated with an increased risk of VTE recurrences compared with DOACs. LMWH was associated with an increased risk of major bleeding (HR, 2.27; 95% CI, 1.62-3.20) and higher all-cause mortality (HR, 1.61; 95% CI, 1.15-2.25) compared with DOACs.Conclusions and RelevanceIn this comparative effectiveness study of claims-based data, patients with CAT received anticoagulation for a remarkably short duration in clinical settings. DOACs was associated with a lower risk of VTE recurrence, major bleeding, and mortality. Warfarin may still be considered for patients with contraindications to DOACs and those with poor persistence on LMWH.

Introduction: Prior AF screening trials demonstrated low yield, highlighting the need for more targeted approaches. An AI algorithm was developed to identify ECG signatures of AF risk during normal sinus rhythm, which has been validated in diverse external populations. Hypothesis: An AI-guided, targeted screening approach could improve the diagnosis of AF. Methods We conducted a pragmatic decentralized trial to prospectively recruit patients with stroke risk factors but no prior AF. The AI algorithm was applied to the ECGs performed in routine practice and divided patients into high- or low-risk groups. The primary endpoint was AF lasting ≥ 30 seconds on a subsequent 30-day continuous cardiac rhythm monitor. In a secondary analysis, trial participants were 1:1 propensity score-matched to real-world controls derived from the eligible but unenrolled population. Results A total of 1,003 patients from 40 U.S. states completed the study, with a mean age of 74 [SD 8.8] years. Over a mean of 22.3 days of continuous monitoring, AF was detected in 6 (1.6%) of low-risk patients and 48 (7.6%) of high-risk patients (OR 4.98 [2.11-11.75], p<0.001). Compared to usual care, AI-guided AF screening was associated with increased detection of AF (high-risk group: 4.2% vs. 11.1%, p<0.001; low-risk group: 0.9% vs. 2.4%, p=0.12) over a median follow-up of 10 months. Conclusions A prospective pragmatic study found that the AI a can risk-stratify a relatively uniform population (i.e., older adults at risk for stroke) to detect AF during short-term cardiac monitoring. Furthermore, when compared with usual care, AI-guided cardiac monitoring was associated with increased AF detection. As such, an AI-guided AF screening approach, leveraging existing EHR data and infrastructure, could be effective, patient-centered, and massively scalable, thereby reducing unnecessary health utilization and diagnosis-related anxiety (Clinicaltrials.gov: NCT04208971).

Abstract Objective To emulate the GRADE (Glycemia Reduction Approaches in Diabetes: A Comparative Effectiveness Study) trial using real world data before its publication. GRADE directly compared second line glucose lowering drugs for their ability to lower glycated hemoglobin A 1c (HbA 1c ). Design Observational study. Setting OptumLabs® Data Warehouse (OLDW), a nationwide claims database in the US, 25 January 2010 to 30 June 2019. Participants Adults with type 2 diabetes and HbA 1c 6.8-8.5% while using metformin monotherapy, identified according to the GRADE trial specifications, who also used glimepiride, liraglutide, sitagliptin, or insulin glargine. Main outcome measures The primary outcome was time to HbA 1c ≥7.0%. Secondary outcomes were time to HbA 1c >7.5%, incident microvascular complications, incident macrovascular complications, adverse events, all cause hospital admissions, and all cause mortality. Propensity scores were estimated using the gradient boosting machine method, and inverse propensity score weighting was used to emulate randomization of the treatment groups, which were then compared using Cox proportional hazards regression. Results 8252 people were identified (19.7% of adults starting the study drugs in OLDW) who met eligibility criteria for the GRADE trial (glimepiride arm=4318, liraglutide arm=690, sitagliptin arm=2993, glargine arm=251). The glargine arm was excluded from analyses owing to small sample size. Median times to HbA 1c ≥7.0% were 442 days (95% confidence interval 394 to 480 days) for glimepiride, 764 (741 to not calculable) days for liraglutide, and 427 (380 to 483) days for sitagliptin. Liraglutide was associated with lower risk of reaching HbA 1c ≥7.0% compared with glimepiride (hazard ratio 0.57, 95% confidence interval 0.43 to 0.75) and sitagliptin (0.55, 0.41 to 0.73). Results were consistent for the secondary outcome of time to HbA 1c >7.5%. No significant differences were observed among treatment groups for the remaining secondary outcomes. Conclusions In this emulation of the GRADE trial, liraglutide was statistically significantly more effective at maintaining glycemic control than glimepiride or sitagliptin when added to metformin monotherapy. Generating timely evidence on medical treatments using real world data as a complement to prospective trials is of value.