Assessing the Benefits and Harms of Pharmacotherapy in Older Adults with Frailty: Insights from Pharmacoepidemiologic Studies of Routine Health Care Data.

The objective of this review is to summarize and appraise the research methodology, emerging findings, and future directions in pharmacoepidemiologic studies assessing the benefits and harms of pharmacotherapies in older adults with different levels of frailty. Older adults living with frailty are at elevated risk for poor health outcomes and adverse effects from pharmacotherapy. However, current evidence is limited due to the under-enrollment of frail older adults and the lack of validated frailty assessments in clinical trials. Recent advancements in measuring frailty in administrative claims and electronic health records (database-derived frailty scores) have enabled researchers to identify patients with frailty and to evaluate the heterogeneity of treatment effects by patients' frailty levels using routine health care data. When selecting a database-derived frailty score, researchers must consider the type of data (e.g., different coding systems), the length of the predictor assessment period, the extent of validation against clinically validated frailty measures, and the possibility of surveillance bias arising from unequal access to care. We reviewed 13 pharmacoepidemiologic studies published on PubMed from 2013 to 2023 that evaluated the benefits and harms of cardiovascular medications, diabetes medications, anti-neoplastic agents, antipsychotic medications, and vaccines by frailty levels. These studies suggest that, while greater frailty is positively associated with adverse treatment outcomes, older adults with frailty can still benefit from pharmacotherapy. Therefore, we recommend routine frailty subgroup analyses in pharmacoepidemiologic studies. Despite data and design limitations, the findings from such studies may be informative to tailor pharmacotherapy for older adults across the frailty spectrum.

Emulation of randomized trials of direct oral anticoagulants with claims data and implications for new Factor XI inhibitors.

Direct oral anticoagulants (DOACs) revolutionized the management of thromboembolic disorders. Clinical care may be further improved as Factor XIs undergo large-scale outcome trials. What role can non-randomized database studies play in expediting understanding of these drugs in clinical practice? The RCT-DUPLICATIVE Initiative emulated the design of eight DOAC randomized clinical trials (RCT) using non-randomized claims database studies. RCT study design parameters and measurements were closely emulated by the database studies and produced highly concordant results. The results of the single database study that did not meet all agreement metrics with the specific RCT it was emulating were aligned with a meta-analysis of six trials studying similar questions, suggesting the trial result was an outlier. Well-designed database studies using fit-for-purpose data came to the same conclusions as DOAC trials, illustrating how database studies could complement RCTs for Factor XI inhibitors-by accelerating insights in underrepresented populations, demonstrating effectiveness and safety in clinical practice, and testing broader indications.

Validation of alopecia coding in US claims data among women of childbearing age.

BACKGROUND: Accurately identifying alopecia in claims data is important to study this rare medication side effect. OBJECTIVES: To develop and validate a claims-based algorithm to identify alopecia in women of childbearing age. METHODS: We linked electronic health records from a large healthcare system in Massachusetts (Mass General Brigham) with Medicaid claims data from 2016 through 2018 to identify all women aged 18 to 50 years with an ICD-10 code for alopecia, including alopecia areata, androgenic alopecia, non-scarring alopecia, or cicatricial alopecia, from a visit to the MGB system. Using eight predefined algorithms to identify alopecia in Medicaid claims data, we randomly selected 300 women for whom we reviewed their charts to validate the alopecia diagnosis. Positive predictive values (PPVs) were computed for the primary algorithm and seven algorithm variations, stratified by race. RESULTS: Out of 300 patients with at least 1 ICD-10 code for alopecia in the Medicaid claims, 286 had chart-confirmed alopecia (PPV = 95.3%). The algorithm requiring two diagnosis codes plus one prescription claim for alopecia treatment identified 55 patients (PPV = 100%). The algorithm requiring 1 diagnosis code for alopecia plus 1 procedure claim for intralesional triamcinolone injection identified 35 patients (PPV = 100%). Across all 8 algorithms tested, the PPV varied between 95.3% and 100%. The PPV for alopecia ranged from 94% to 100% in White and 96%-100% in 48 non-White women. The exact date of alopecia onset was difficult to determine in charts. CONCLUSION: At least one recorded ICD-10 code for alopecia in claims data identified alopecia in women of childbearing age with high accuracy.

Development and Validation of an Intracranial Hemorrhage Risk Score in Older Adults with Atrial Fibrillation Treated with Oral Anticoagulant.

Background: High risk of intracranial hemorrhage (ICH) is a leading reason for withholding anticoagulation in patients with atrial fibrillation (AF). We aimed to develop a claims-based ICH risk prediction model in older adults with AF initiating oral anticoagulation (OAC). Methods: We used US Medicare claims data to identify new users of OAC aged ≥65 years with AF in 2010-2017. We used regularized Cox regression to select predictors of ICH. We compared our AF ICH risk score with the HAS-BLED bleed risk and Homer fall risk scores by area under the receiver operating characteristic curve (AUC) and assessed net reclassification improvement (NRI) when predicting 1-year risk of ICH. Results: Our study cohort comprised 840,020 patients (mean [SD] age 77.5 [7.4] years and female 52.2%) split geographically into training (3963 ICH events [0.6%] in 629,804 patients) and validation (1397 ICH events [0.7%] in 210,216 patients) sets. Our AF ICH risk score, including 50 predictors, had superior AUCs of 0.653 and 0.650 in the training and validation sets than the HAS-BLED score of 0.580 and 0.567 (p<0.001) and the Homer score of 0.624 and 0.623 (p<0.001). In the validation set, our AF ICH risk score reclassified 57.8%, 42.5%, and 43.9% of low, intermediate, and high-risk patients, respectively, by HAS-BLED score (NRI: 15.3%, p<0.001). Similarly, it reclassified 0.0, 44.1, and 19.4% of low, intermediate, and high-risk patients, respectively, by the Homer score (NRI: 21.9%, p<0.001). Conclusion: Our novel claims-based ICH risk prediction model outperformed the standard HAS-BLED score and can inform OAC prescribing decisions.

Patient Characteristics Associated With Using Transcatheter Left Atrial Appendage Occlusion Versus Oral Anticoagulants for Atrial Fibrillation.

BACKGROUND: Transcatheter left atrial appendage occlusion (LAAO) is an alternative to oral anticoagulants (OACs) for stroke prevention in patients with atrial fibrillation, but the predictors of LAAO use in routine care are unclear. We aimed to assess the utilization trends of LAAO and compare the change in characteristics of LAAO users versus OACs since its marketing. METHODS: Using the US Medicare claims database (March 15, 2015, to December 31, 2020), we identified patients with atrial fibrillation, ≥65 years, and CHA2DS2-VASc score ≥2 (men) or ≥3 (women), with either first implantation of an LAAO device or initiation of OACs, including apixaban, dabigatran, rivaroxaban, edoxaban, or warfarin. Patient characteristics, measured 365 days before the first LAAO or OAC use date, were compared using logistic regression. RESULTS: There were 30 058 LAAO recipients (mean age, 77.74 years; female, 42.1%) and 792 600 OAC initiators (mean age, 78.48; female, 53.3%). In 2020, patients had higher odds of initiating LAAO use than in 2015 (0.52 versus 9.32%; adjusted odds ratio [aOR], 13.64 [95% CI, 12.56-14.81]). Old age (ie, >85 versus 65-75 years; aOR, 0.84 [95% CI, 0.80-0.88]), female sex (aOR, 0.74 [95% CI, 0.71-0.76]), Black race (aOR, 0.63 [95% CI, 0.58-0.68]) versus White race, and Medicaid eligibility (aOR, 0.61 [95% CI, 0.58-0.64]) were associated with lower odds of receiving LAAO. Among clinical characteristics, frailty, cancer, fractures, and venous thromboembolism were associated with lower odds of LAAO use, while history of intracranial and extracranial bleeding, coagulopathy, and falls were associated with higher odds of receiving LAAO. CONCLUSIONS: Among patients with atrial fibrillation receiving stroke-preventive therapy, LAAO use increased rapidly from 2015 to 2020 and was positively associated with the risk factors for OAC complications but negatively associated with old age, advanced frailty, and cancer. Black race and female sex were associated with a lower likelihood of receiving LAAO.

Targeted Learning with an Undersmoothed Lasso Propensity Score Model for Large-Scale Covariate Adjustment in Healthcare Database Studies.

Lasso regression is widely used for large-scale propensity score (PS) estimation in healthcare database studies. In these settings, previous work has shown that undersmoothing (overfitting) Lasso PS models can improve confounding control, but it can also cause problems of non-overlap in covariate distributions. It remains unclear how to select the degree of undersmoothing when fitting large-scale Lasso PS models to improve confounding control while avoiding issues that can result from reduced covariate overlap. Here, we used simulations to evaluate the performance of using collaborative-controlled targeted learning to data-adaptively select the degree of undersmoothing when fitting large-scale PS models within both singly and doubly robust frameworks to reduce bias in causal estimators. Simulations showed that collaborative learning can data-adaptively select the degree of undersmoothing to reduce bias in estimated treatment effects. Results further showed that when fitting undersmoothed Lasso PS-models, the use of cross-fitting was important for avoiding non-overlap in covariate distributions and reducing bias in causal estimates.

Identifying Functional Status Impairment in People Living With Dementia Through Natural Language Processing of Clinical Documents: Cross-Sectional Study.

BACKGROUND: Assessment of activities of daily living (ADLs) and instrumental ADLs (iADLs) is key to determining the severity of dementia and care needs among older adults. However, such information is often only documented in free-text clinical notes within the electronic health record and can be challenging to find. OBJECTIVE: This study aims to develop and validate machine learning models to determine the status of ADL and iADL impairments based on clinical notes. METHODS: This cross-sectional study leveraged electronic health record clinical notes from Mass General Brigham's Research Patient Data Repository linked with Medicare fee-for-service claims data from 2007 to 2017 to identify individuals aged 65 years or older with at least 1 diagnosis of dementia. Notes for encounters both 180 days before and after the first date of dementia diagnosis were randomly sampled. Models were trained and validated using note sentences filtered by expert-curated keywords (filtered cohort) and further evaluated using unfiltered sentences (unfiltered cohort). The model's performance was compared using area under the receiver operating characteristic curve and area under the precision-recall curve (AUPRC). RESULTS: The study included 10,000 key-term-filtered sentences representing 441 people (n=283, 64.2% women; mean age 82.7, SD 7.9 years) and 1000 unfiltered sentences representing 80 people (n=56, 70% women; mean age 82.8, SD 7.5 years). Area under the receiver operating characteristic curve was high for the best-performing ADL and iADL models on both cohorts (>0.97). For ADL impairment identification, the random forest model achieved the best AUPRC (0.89, 95% CI 0.86-0.91) on the filtered cohort; the support vector machine model achieved the highest AUPRC (0.82, 95% CI 0.75-0.89) for the unfiltered cohort. For iADL impairment, the Bio+Clinical bidirectional encoder representations from transformers (BERT) model had the highest AUPRC (filtered: 0.76, 95% CI 0.68-0.82; unfiltered: 0.58, 95% CI 0.001-1.0). Compared with a keyword-search approach on the unfiltered cohort, machine learning reduced false-positive rates from 4.5% to 0.2% for ADL and 1.8% to 0.1% for iADL. CONCLUSIONS: In this study, we demonstrated the ability of machine learning models to accurately identify ADL and iADL impairment based on free-text clinical notes, which could be useful in determining the severity of dementia.

Development and Validation of a Claims-Based Model to Predict Categories of Obesity.

We developed and validated a claims-based algorithm that classifies patients into obesity categories. Using Medicare (2007-2017) and Medicaid (2000-2014) claims data linked to 2 electronic health record (EHR) systems in Boston, Massachusetts, we identified a cohort of patients with an EHR-based body mass index (BMI) measurement (calculated as weight (kg)/height (m)2). We used regularized regression to select from 137 variables and built generalized linear models to classify patients with BMIs of ≥25, ≥30, and ≥40. We developed the prediction model using EHR system 1 (training set) and validated it in EHR system 2 (validation set). The cohort contained 123,432 patients in the Medicare population and 40,736 patients in the Medicaid population. The model comprised 97 variables in the Medicare set and 95 in the Medicaid set, including BMI-related diagnosis codes, cardiovascular and antidiabetic drugs, and obesity-related comorbidities. The areas under the receiver-operating-characteristic curve in the validation set were 0.72, 0.75, and 0.83 (Medicare) and 0.66, 0.66, and 0.70 (Medicaid) for BMIs of ≥25, ≥30, and ≥40, respectively. The positive predictive values were 81.5%, 80.6%, and 64.7% (Medicare) and 81.6%, 77.5%, and 62.5% (Medicaid), for BMIs of ≥25, ≥30, and ≥40, respectively. The proposed model can identify obesity categories in claims databases when BMI measurements are missing and can be used for confounding adjustment, defining subgroups, or probabilistic bias analysis.

Comparative Safety and Effectiveness of Warfarin or Rivaroxaban Versus Apixaban in Patients With Advanced CKD and Atrial Fibrillation: Nationwide US Cohort Study.

RATIONALE & OBJECTIVE: Head-to-head data comparing the effectiveness and safety of oral anticoagulants in patients with atrial fibrillation (AF) and advanced chronic kidney disease (CKD) are lacking. We compared the safety and effectiveness of warfarin or rivaroxaban versus apixaban in patients with AF and non-dialysis-dependent CKD stage 4/5. STUDY DESIGN: Propensity score-matched cohort study. SETTING & PARTICIPANTS: 2 nationwide US claims databases, Medicare and Optum's deidentified Clinformatics Data Mart Database, were searched for the interval from January 1, 2013, through March 31, 2022, for patients with nonvalvular AF and CKD stage 4/5 who initiated warfarin versus apixaban (matched cohort, n=12,488) and rivaroxaban versus apixaban (matched cohort, n = 5,720). EXPOSURES: Warfarin, rivaroxaban, or apixaban. OUTCOMES: Primary outcomes included major bleeding and ischemic stroke. Secondary outcomes included all-cause mortality, major gastrointestinal bleeding, and intracranial bleeding. ANALYTICAL APPROACH: Cox regression was used to estimate HRs, and 1:1 propensity-score matching was used to adjust for 80 potential confounders. RESULTS: Compared with apixaban, warfarin initiation was associated with a higher rate of major bleeding (HR, 1.85; 95% CI, 1.59-2.15), including major gastrointestinal bleeding (1.86; 1.53-2.25) and intracranial bleeding (2.15; 1.42-3.25). Compared with apixaban, rivaroxaban was also associated with a higher rate of major bleeding (1.69; 1.33-2.15). All-cause mortality was similar for warfarin (1.08; 0.98-1.18) and rivaroxaban (0.94; 0.81-1.10) versus apixaban. Furthermore, no statistically significant differences for ischemic stroke were observed for warfarin (1.14; 0.83-1.57) or rivaroxaban (0.71; 0.40-1.24) versus apixaban, but the CIs were wide. Similar results were observed for warfarin versus apixaban in the positive control cohort of patients with CKD stage 3, consistent with randomized trial findings. LIMITATIONS: Few ischemic stroke events, potential residual confounding. CONCLUSIONS: In patients with AF and advanced CKD, rivaroxaban and warfarin were associated with higher rates of major bleeding compared with apixaban, suggesting a superior safety profile for apixaban in this high-risk population. PLAIN-LANGUAGE SUMMARY: Different anticoagulants have been shown to reduce the risk of stroke in patients with atrial fibrillation, such as warfarin and direct oral anticoagulants like apixaban and rivaroxaban. Unfortunately, the large-scale randomized trials that compared direct anticoagulants versus warfarin excluded patients with advanced chronic kidney disease. Therefore, the comparative safety and effectiveness of warfarin, apixaban, and rivaroxaban are uncertain in this population. In this study, we used administrative claims data from the United States to answer this question. We found that warfarin and rivaroxaban were associated with increased risks of major bleeding compared with apixaban. There were few stroke events, with no major differences among the 3 drugs in the risk of stroke. In conclusion, this study suggests that apixaban has a better safety profile than warfarin and rivaroxaban.

A population-based cohort defined risk of hyperkalemia after initiating SGLT-2 inhibitors, GLP1 receptor agonists or DPP-4 inhibitors to patients with chronic kidney disease and type 2 diabetes.

Hyperkalemia is a common adverse event in patients with chronic kidney disease (CKD) and type 2 diabetes and limits the use of guideline-recommended therapies such as renin-angiotensin system inhibitors. Here, we evaluated the comparative effects of sodium-glucose cotransporter-2 inhibitors (SGLT-2i), glucagon-like peptide-1 receptor agonists (GLP-1RA) and dipeptidyl peptidase-4 inhibitors (DPP-4i) on the risk of hyperkalemia. We conducted a population-based active-comparator, new-user cohort study using claims data from Medicare and two large United States commercial insurance databases (April 2013-April 2022). People with CKD stages 3-4 and type 2 diabetes who newly initiated SGLT-2i vs. DPP-4i (141671 patients), GLP-1RA vs. DPP-4i (159545 patients) and SGLT-2i vs. GLP-1RA (93033 patients) were included. The primary outcome was hyperkalemia diagnosed in inpatient or outpatient settings. Secondary outcomes included hyperkalemia diagnosed in inpatient or emergency department setting, and serum potassium levels of 5.5 mmol/L or more. Pooled hazard ratios and rate differences were estimated after propensity score matching to adjust for over 140 potential confounders. Initiation of SGLT-2i was associated with a lower risk of hyperkalemia compared with DPP-4i (hazard ratio 0.74; 95% confidence interval 0.68-0.80) and contrasted to GLP-1RA (0.92; 0.86-0.99). Compared with DPP-4i, GLP-1RA were also associated with a lower risk of hyperkalemia (0.80; 0.75-0.86). Corresponding absolute rate differences/1000 person-years were -24.8 (95% confidence interval -31.8 to -17.7), -5.0 (-10.9 to 0.8), and -17.7 (-23.4 to -12.1), respectively. Similar findings were observed for the secondary outcomes, among subgroups, and across single agents within the SGLT-2i and GLP-1RA classes. Thus, SGLT-2i and GLP-1RA are associated with a lower risk of hyperkalemia than DPP-4i in patients with CKD and type 2 diabetes, further supporting the use of these drugs in this population.

Frailty, Home Time, and Health Care Costs in Older Adults With Atrial Fibrillation Receiving Oral Anticoagulants.

Importance: There are no data on patient-centered outcomes and health care costs by frailty in patients with atrial fibrillation (AF) taking oral anticoagulants (OACs). Objective: To compare home time, clinical events, and health care costs associated with OACs by frailty levels in older adults with AF. Design, Setting, and Participants: This community-based cohort study assessed Medicare fee-for-service beneficiaries 65 years or older with AF from January 1, 2013, to December 31, 2019. Data analysis was performed from January to December 2022. Exposures: Apixaban, rivaroxaban, and warfarin use were measured from prescription claims. Frailty was measured using a validated claims-based frailty index. Main outcomes and measures: Outcome measures were (1) home time (days alive out of the hospital and skilled nursing facility) loss greater than 14 days; (2) a composite end point of ischemic stroke, systemic embolism, major bleeding, or death; and (3) total cost per member per year after propensity score overlap weighting. Results: The weighted population comprised 136 551 beneficiaries, including 45 950 taking apixaban (mean [SD] age, 77.6 [7.3] years; 51.3% female), 45 320 taking rivaroxaban (mean [SD] age, 77.6 [7.3] years; 51.9% female), and 45 281 taking warfarin (mean [SD] age, 77.6 [7.3] years; 52.0% female). Compared with apixaban, rivaroxaban was associated with increased risk of home time lost greater than 14 days (risk difference per 100 persons, 1.8 [95% CI, 1.5-2.1]), composite end point (rate difference per 1000 person-years, 21.3 [95% CI, 16.4-26.2]), and total cost (mean difference, $890 [95% CI, $652-$1127]), with greater differences among the beneficiaries with frailty. Use of warfarin relative to apixaban was associated with increased home time lost (risk difference per 100 persons, 3.2 [95% CI, 2.9-3.5]) and composite end point (rate difference per 1000 person-years, 29.4 [95% CI, 24.5-34.3]), with greater differences among the beneficiaries with frailty. Compared with apixaban, warfarin was associated with lower total cost (mean difference, -$1166 [95% CI, -$1396 to -$937]) but higher cost when excluding OAC cost (mean difference, $1409 [95% CI, $1177 to $1642]) regardless of frailty levels. Conclusions and Relevance: In older adults with AF, apixaban was associated with increased home time and lower rates of clinical events than rivaroxaban and warfarin, especially for those with frailty. Apixaban was associated with lower total cost compared with rivaroxaban but higher cost compared with warfarin due to higher OAC cost. These findings suggest that apixaban may be preferred for older adults with AF, particularly those with frailty.

Utilization of P2Y12 Inhibitors in Older Adults With ST-Elevation Myocardial Infarction and Frailty.

Choosing optimal P2Y12 inhibitor in frail older adults is challenging because they are at increased risk of both ischemic and bleeding events. We conducted a retrospective cohort study of Medicare Advantage Plan beneficiaries who were prescribed clopidogrel, prasugrel, or ticagrelor after percutaneous coronary intervention-treated ST-elevation myocardial infarction from January 1, 2010 to December 31, 2020. Frailty was defined using claims-based frailty index ≥0.25. We conducted multivariable logistic regression to identify factors associated with using potent P2Y12 inhibitors and multivariable-adjusted competing risk analyses to compare the rate of discontinuation of potent P2Y12 inhibitors in frail versus non-frail patients. There were 11,239 patients (mean age 74 years, 39% women). The prevalence of cardiovascular and geriatric co-morbidities was as follows: 32% chronic kidney disease, 28% heart failure, 10% previous myocardial infarction, 6% dementia, 20% anemia, and 12% frailty. The proportion of patients receiving clopidogrel decreased from 78.3% in 2010 to 2013 to 42.1% in 2018 to 2020, with a concurrent increase in those receiving potent P2Y12 inhibitors (mostly ticagrelor) from 21.7% to 57.9%. Frailty was independently associated with reduced odds of initiation (odds ratio 0.78, 95% confidence interval 0.67 to 0.90) but not with discontinuation of potent P2Y12 inhibitors (subdistribution hazard ratio 1.09, 95% confidence interval 0.98 to 1.22). In conclusion, frail older adults are less likely to receive potent P2Y12 inhibitors after percutaneous coronary intervention-treated ST-elevation myocardial infarction, but they are as likely as non-frail patients to continue with the prescribed P2Y12 inhibitor.

Comparison of EHR Data-Completeness in Patients with Different Types of Medical Insurance Coverage in the United States.

Prior studies have demonstrated that misclassification of study variables due to electronic health record (EHR)-discontinuity can be mitigated by restricting EHR-based analyses to subjects with high predicted EHR-continuity based on a simple algorithm. In this study, we compared EHR continuity in populations covered by Medicare, Medicaid, or commercial insurance. Using claims-linked EHRs from a multicenter network in Massachusetts, including Medicare (MA EHR-Medicare cohort) and Medicaid (MA EHR-Medicaid cohort) claims data; and TriNetX (TriNetX cohort) claims-linked EHR data from 11 US-based healthcare organizations, we assessed (1) EHR-continuity quantified by proportion of encounters captured by EHR (capture proportion (CP)); (2) area under receiver operating curve (AUROC) of previously validated model to identify patients with high EHR-continuity (CP ≥ 0.6); (3) misclassification of 40 patient characteristics, quantified by average standardized absolute mean difference (ASAMD). Study participants were ≥ 65 years (Medicare) or ≥ 18 years (Medicaid, TriNetX) with ≥ 365 days of continuous insurance enrollment overlapping with an EHR encounter. We found that the mean CP was 0.30, 0.18, and 0.19 and AUROC of the prediction model to identify patients with high EHR-continuity was 0.92, 0.89, and 0.77 in the MA EHR-Medicare, MA EHR-Medicaid, and TriNetX cohorts, respectively. Restricting to patients with predicted EHR-continuity percentile of top 20%, 50%, and 50% in MA EHR-Medicare, MA EHR-Medicaid, and TriNetX cohorts resulted in acceptable levels of misclassification (ASAMD < 0.1). Using a prediction model to identify cohorts with high EHR-continuity can improve validity, but cutoffs to achieve this goal vary by population.

Claims-Based Frailty Index as a Measure of Dementia Severity in Medicare Claims Data.

BACKGROUND: Dementia severity is unavailable in administrative claims data. We examined whether a claims-based frailty index (CFI) can measure dementia severity in Medicare claims. METHODS: This cross-sectional study included the National Health and Aging Trends Study Round 5 participants with possible or probable dementia whose Medicare claims were available. We estimated the Functional Assessment Staging Test (FAST) scale (range: 3 [mild cognitive impairment] to 7 [severe dementia]) using information from the survey. We calculated CFI (range: 0-1, higher scores indicating greater frailty) using Medicare claims 12 months prior to the participants' interview date. We examined C-statistics to evaluate the ability of the CFI in identifying moderate-to-severe dementia (FAST stage 5-7) and determined the optimal CFI cut-point that maximized both sensitivity and specificity. RESULTS: Of the 814 participants with possible or probable dementia and measurable CFI, 686 (72.2%) patients were ≥75 years old, 448 (50.8%) were female, and 244 (25.9%) had FAST stage 5-7. The C-statistic of CFI to identify FAST stage 5-7 was 0.78 (95% confidence interval: 0.72-0.83), with a CFI cut-point of 0.280, achieving the maximum sensitivity of 76.9% and specificity of 62.8%. Participants with CFI ≥0.280 had a higher prevalence of disability (19.4% vs 58.3%) and dementia medication use (6.0% vs 22.8%) and higher risk of mortality (10.7% vs 26.3%) and nursing home admission (4.5% vs 10.6%) over 2 years than those with CFI <0.280. CONCLUSIONS: Our study suggests that CFI can be useful in identifying moderate-to-severe dementia from administrative claims among older adults with dementia.

The impact of electronic health record discontinuity on prediction modeling.

BACKGROUND: To determine the impact of electronic health record (EHR)-discontinuity on the performance of prediction models. METHODS: The study population consisted of patients with a history of cardiovascular (CV) comorbidities identified using US Medicare claims data from 2007 to 2017, linked to EHR from two networks (used as model training and validation set, respectively). We built models predicting one-year risk of mortality, major CV events, and major bleeding events, stratified by high vs. low algorithm-predicted EHR-continuity. The best-performing models for each outcome were chosen among 5 commonly used machine-learning models. We compared model performance by Area under the ROC curve (AUROC) and Area under the precision-recall curve (AUPRC). RESULTS: Based on 180,950 in the training and 103,061 in the validation set, we found EHR captured only 21.0-28.1% of all the non-fatal outcomes in the low EHR-continuity cohort but 55.4-66.1% of that in the high EHR-continuity cohort. In the validation set, the best-performing model developed among high EHR-continuity patients had consistently higher AUROC than that based on low-continuity patients: AUROC was 0.849 vs. 0.743 when predicting mortality; AUROC was 0.802 vs. 0.659 predicting the CV events; AUROC was 0.635 vs. 0.567 predicting major bleeding. We observed a similar pattern when using AUPRC as the outcome metric. CONCLUSIONS: Among patients with CV comorbidities, when predicting mortality, major CV events, and bleeding outcomes, the prediction models developed in datasets with low EHR-continuity consistently had worse performance compared to models developed with high EHR-continuity.

Prognostic Factors of COVID-19: An Umbrella Review Endorsed by the International Society for Pharmacoepidemiology.

During the coronavirus disease 2019 (COVID-19) pandemic, the urgency for updated evidence to inform public health and clinical care placed systematic literature reviews (SLRs) at the cornerstone of research. We aimed to summarize evidence on prognostic factors for COVID-19 outcomes through published SLRs and to critically assess quality elements in the findings' interpretation. An umbrella review was conducted via electronic databases from January 2020 to April 2022. All SLRs (and meta-analyses) in English were considered. Data screening and extraction were conducted by two independent reviewers. AMSTAR 2 tool was used to assess SLR quality. The study was registered with PROSPERO (CRD4202232576). Out of 4,564 publications, 171 SLRs were included of which 3 were umbrella reviews. Our primary analysis included 35 SLRs published in 2022, which incorporated studies since the beginning of the pandemic. Consistent findings showed that, for adults, older age, obesity, heart disease, diabetes, and cancer were more strongly predictive of risk of hospitalization, intensive care unit admission, and mortality due to COVID-19. Male sex was associated with higher risk of short-term adverse outcomes, but female sex was associated with higher risk of long COVID. For children, socioeconomic determinants that may unravel COVID-19 disparities were rarely reported. This review highlights key prognostic factors of COVID-19, which can help clinicians and health officers identify high-risk groups for optimal care. Findings can also help optimize confounding adjustment and patient phenotyping in comparative effectiveness research. A living SLR approach may facilitate dissemination of new findings. This paper is endorsed by the International Society for Pharmacoepidemiology.

Common non-cardiovascular multimorbidity groupings and clinical outcomes in older adults with major cardiovascular disease.

BACKGROUND: Among older adults, non-cardiovascular multimorbidity often coexists with cardiovascular disease (CVD) but their clinical significance is uncertain. We identified common non-cardiovascular comorbidity patterns and their association with clinical outcomes in Medicare fee-for-service beneficiaries with acute myocardial infarction (AMI), congestive heart failure (CHF), or atrial fibrillation (AF). METHODS: Using 2015-2016 Medicare data, we took 1% random sample to create 3 cohorts of beneficiaries diagnosed with AMI (n = 24,808), CHF (n = 57,285), and AF (n = 36,277) prior to 1/1/2016. Within each cohort, we applied latent class analysis to classify beneficiaries based on 9 non-cardiovascular comorbidities (anemia, cancer, chronic kidney disease, chronic lung disease, dementia, depression, diabetes, hypothyroidism, and musculoskeletal disease). Mortality, cardiovascular and non-cardiovascular hospitalizations, and home time lost over a 1-year follow-up period were compared across non-cardiovascular multimorbidity classes. RESULTS: Similar non-cardiovascular multimorbidity classes emerged from the 3 CVD cohorts: (1) minimal, (2) depression-lung, (3) chronic kidney disease (CKD)-diabetes, and (4) multi-system class. Across CVD cohorts, multi-system class had the highest risk of mortality (hazard ratio [HR], 2.7-3.9), cardiovascular hospitalization (HR, 1.6-3.3), non-cardiovascular hospitalization (HR, 3.1-7.2), and home time lost (rate ratio, 2.7-5.4). Among those with AMI, the CKD-diabetes class was more strongly associated with all the adverse outcomes than the depression-lung class. In CHF and AF, differences in risk between the depression-lung and CKD-diabetes classes varied per outcome; and the depression-lung and multi-system classes had double the rates of non-cardiovascular hospitalizations than cardiovascular hospitalizations. CONCLUSION: Four non-cardiovascular multimorbidity patterns were found among Medicare beneficiaries with CHF, AMI, or AF. Compared to the minimal class, the multi-system, CKD-diabetes, and depression-lung classes were associated with worse outcomes. Identification of these classes offers insight into specific segments of the population that may benefit from more than the usual cardiovascular care.

Outcomes for patients with dementia undergoing emergency and elective colorectal surgery: A large multi-institutional comparative cohort study.

BACKGROUND: Alzheimer's Disease and Related Dementias (ADRD) may result in poor surgical outcomes. The current study aims to characterize the risk of ADRD on outcomes for patients undergoing colorectal surgery. METHODS: Colorectal surgery patients with and without ADRD from 2007 to 2017 were identified using electronic health record-linked Medicare claims data from two large health systems. Unadjusted and adjusted analyses were performed to evaluate postoperative outcomes. RESULTS: 5926 patients (median age 74) underwent colorectal surgery of whom 4.8% (n = 285) had ADRD. ADRD patients were more likely to undergo emergent operations (27.7% vs. 13.6%, p < 0.001) and be discharged to a facility (49.8% vs 28.9%, p < 0.001). After multi-variable adjustment, ADRD patients were more likely to have complications (61.1% vs 48.3%, p < 0.001) and required longer hospitalization (7.1 vs 6.1 days, p = 0.001). CONCLUSIONS: The diagnosis of ADRD is an independent risk factor for prolonged hospitalization and postoperative complications after colorectal surgery.

The Impact of Longitudinal Data-Completeness of Electronic Health Record Data on the Prediction Performance of Clinical Risk Scores.

The impact of electronic health record (EHR) discontinuity (i.e., receiving care outside of a given EHR system) on EHR-based risk prediction is unknown. We aimed to assess the impact of EHR-continuity on the performance of clinical risk scores. The study cohort consisted of patients aged ≥ 65 years with ≥ 1 EHR encounter in the 2 networks in Massachusetts (MA; 2007/1/1-2017/12/31, internal training and validation dataset), and one network in North Carolina (NC; 2007/1/1-2016/12/31, external validation dataset) that were linked with Medicare claims data. Risk scores were calculated using EHR data alone vs. linked EHR-claims data (not subject to misclassification due to EHR-discontinuity): (i) combined comorbidity score (CCS), (ii) claim-based frailty score (CFI), (iii) CHAD2 DS2 -VASc, and (iv) Hypertension, Abnormal renal/liver function, Stroke, Bleeding, Labile, Elderly, and Drugs (HAS-BLED). We assessed the performance of CCS and CFI predicting death, CHAD2 DS2 -VASc predicting ischemic stroke, and HAS-BLED predicting bleeding by area under receiver operating characteristic curve (AUROC), stratified by quartiles of predicted EHR-continuity (Q1-4). There were 319,740 patients in the MA systems and 125,380 in the NC system. In the external validation dataset, AUROC for EHR-based CCS predicting 1-year risk of death was 0.583 in Q1 (lowest) EHR-continuity group, which increased to 0.739 in Q4 (highest) EHR-continuity group. The corresponding improvement in AUROC was 0.539 to 0.647 for CFI, 0.556 to 0.637 for CHAD2 DS2 -VASc, and 0.517 to 0.556 for HAS-BLED. The AUROC in Q4 EHR-continuity group based on EHR alone approximates that based on EHR-claims data. The prediction performance of four clinical risk scores was substantially worse in patients with lower vs. high EHR-continuity.

Emulation of Randomized Clinical Trials With Nonrandomized Database Analyses: Results of 32 Clinical Trials.

Importance: Nonrandomized studies using insurance claims databases can be analyzed to produce real-world evidence on the effectiveness of medical products. Given the lack of baseline randomization and measurement issues, concerns exist about whether such studies produce unbiased treatment effect estimates. Objective: To emulate the design of 30 completed and 2 ongoing randomized clinical trials (RCTs) of medications with database studies using observational analogues of the RCT design parameters (population, intervention, comparator, outcome, time [PICOT]) and to quantify agreement in RCT-database study pairs. Design, Setting, and Participants: New-user cohort studies with propensity score matching using 3 US claims databases (Optum Clinformatics, MarketScan, and Medicare). Inclusion-exclusion criteria for each database study were prespecified to emulate the corresponding RCT. RCTs were explicitly selected based on feasibility, including power, key confounders, and end points more likely to be emulated with real-world data. All 32 protocols were registered on ClinicalTrials.gov before conducting analyses. Emulations were conducted from 2017 through 2022. Exposures: Therapies for multiple clinical conditions were included. Main Outcomes and Measures: Database study emulations focused on the primary outcome of the corresponding RCT. Findings of database studies were compared with RCTs using predefined metrics, including Pearson correlation coefficients and binary metrics based on statistical significance agreement, estimate agreement, and standardized difference. Results: In these highly selected RCTs, the overall observed agreement between the RCT and the database emulation results was a Pearson correlation of 0.82 (95% CI, 0.64-0.91), with 75% meeting statistical significance, 66% estimate agreement, and 75% standardized difference agreement. In a post hoc analysis limited to 16 RCTs with closer emulation of trial design and measurements, concordance was higher (Pearson r, 0.93; 95% CI, 0.79-0.97; 94% meeting statistical significance, 88% estimate agreement, 88% standardized difference agreement). Weaker concordance occurred among 16 RCTs for which close emulation of certain design elements that define the research question (PICOT) with data from insurance claims was not possible (Pearson r, 0.53; 95% CI, 0.00-0.83; 56% meeting statistical significance, 50% estimate agreement, 69% standardized difference agreement). Conclusions and Relevance: Real-world evidence studies can reach similar conclusions as RCTs when design and measurements can be closely emulated, but this may be difficult to achieve. Concordance in results varied depending on the agreement metric. Emulation differences, chance, and residual confounding can contribute to divergence in results and are difficult to disentangle.