Race adjustments in clinical algorithms can help correct for racial disparities in data quality.

Despite ethical and historical arguments for removing race from clinical algorithms, the consequences of removal remain unclear. Here, we highlight a largely undiscussed consideration in this debate: varying data quality of input features across race groups. For example, family history of cancer is an essential predictor in cancer risk prediction algorithms but is less reliably documented for Black participants and may therefore be less predictive of cancer outcomes. Using data from the Southern Community Cohort Study, we assessed whether race adjustments could allow risk prediction models to capture varying data quality by race, focusing on colorectal cancer risk prediction. We analyzed 77,836 adults with no history of colorectal cancer at baseline. The predictive value of self-reported family history was greater for White participants than for Black participants. We compared two cancer risk prediction algorithms-a race-blind algorithm which included standard colorectal cancer risk factors but not race, and a race-adjusted algorithm which additionally included race. Relative to the race-blind algorithm, the race-adjusted algorithm improved predictive performance, as measured by goodness of fit in a likelihood ratio test (P-value: <0.001) and area under the receiving operating characteristic curve among Black participants (P-value: 0.006). Because the race-blind algorithm underpredicted risk for Black participants, the race-adjusted algorithm increased the fraction of Black participants among the predicted high-risk group, potentially increasing access to screening. More broadly, this study shows that race adjustments may be beneficial when the data quality of key predictors in clinical algorithms differs by race group.

A perspective on genetic and polygenic risk scores-advances and limitations and overview of associated tools.

Polygenetic Risk Scores are used to evaluate an individual's vulnerability to developing specific diseases or conditions based on their genetic composition, by taking into account numerous genetic variations. This article provides an overview of the concept of Polygenic Risk Scores (PRS). We elucidate the historical advancements of PRS, their advantages and shortcomings in comparison with other predictive methods, and discuss their conceptual limitations in light of the complexity of biological systems. Furthermore, we provide a survey of published tools for computing PRS and associated resources. The various tools and software packages are categorized based on their technical utility for users or prospective developers. Understanding the array of available tools and their limitations is crucial for accurately assessing and predicting disease risks, facilitating early interventions, and guiding personalized healthcare decisions. Additionally, we also identify potential new avenues for future bioinformatic analyzes and advancements related to PRS.

ChemFREE: a one-stop comprehensive platform for ecological and environmental risk evaluation of chemicals in one health world.

Addressing health and safety crises stemming from various environmental and ecological issues is a core focus of One Health (OH), which aims to balance and optimize the health of humans, animals, and the environment. While many chemicals contribute significantly to our quality of life when properly used, others pose environmental and ecological health risks. Recently, assessing the ecological and environmental risks associated with chemicals has gained increasing significance in the OH world. In silico models may address time-consuming and costly challenges, and fill gaps in situations where no experimental data is available. However, despite their significant contributions, these assessment models are not web-integrated, leading to user inconvenience. In this study, we developed a one-stop comprehensive web platform for freely evaluating the eco-environmental risk of chemicals, named ChemFREE (Chemical Formula Risk Evaluation of Eco-environment, available in http://chemfree.agroda.cn/chemfree/). Inputting SMILES string of chemicals, users will obtain the assessment outputs of ecological and environmental risk, etc. A performance evaluation of 2935 external chemicals revealed that most classification models achieved an accuracy rate above 0.816. Additionally, the $Q_{F1}^2$ metric for regression models ranges from 0.618 to 0.898. Therefore, it will facilitate the eco-environmental risk evaluation of chemicals in the OH world.

Inflammatory risk and cardiovascular events in patients without obstructive coronary artery disease: the ORFAN multicentre, longitudinal cohort study.

BACKGROUND: Coronary computed tomography angiography (CCTA) is the first line investigation for chest pain, and it is used to guide revascularisation. However, the widespread adoption of CCTA has revealed a large group of individuals without obstructive coronary artery disease (CAD), with unclear prognosis and management. Measurement of coronary inflammation from CCTA using the perivascular fat attenuation index (FAI) Score could enable cardiovascular risk prediction and guide the management of individuals without obstructive CAD. The Oxford Risk Factors And Non-invasive imaging (ORFAN) study aimed to evaluate the risk profile and event rates among patients undergoing CCTA as part of routine clinical care in the UK National Health Service (NHS); to test the hypothesis that coronary arterial inflammation drives cardiac mortality or major adverse cardiac events (MACE) in patients with or without CAD; and to externally validate the performance of the previously trained artificial intelligence (AI)-Risk prognostic algorithm and the related AI-Risk classification system in a UK population. METHODS: This multicentre, longitudinal cohort study included 40 091 consecutive patients undergoing clinically indicated CCTA in eight UK hospitals, who were followed up for MACE (ie, myocardial infarction, new onset heart failure, or cardiac death) for a median of 2·7 years (IQR 1·4-5·3). The prognostic value of FAI Score in the presence and absence of obstructive CAD was evaluated in 3393 consecutive patients from the two hospitals with the longest follow-up (7·7 years [6·4-9·1]). An AI-enhanced cardiac risk prediction algorithm, which integrates FAI Score, coronary plaque metrics, and clinical risk factors, was then evaluated in this population. FINDINGS: In the 2·7 year median follow-up period, patients without obstructive CAD (32 533 [81·1%] of 40 091) accounted for 2857 (66·3%) of the 4307 total MACE and 1118 (63·7%) of the 1754 total cardiac deaths in the whole of Cohort A. Increased FAI Score in all the three coronary arteries had an additive impact on the risk for cardiac mortality (hazard ratio [HR] 29·8 [95% CI 13·9-63·9], p<0·001) or MACE (12·6 [8·5-18·6], p<0·001) comparing three vessels with an FAI Score in the top versus bottom quartile for each artery. FAI Score in any coronary artery predicted cardiac mortality and MACE independently from cardiovascular risk factors and the presence or extent of CAD. The AI-Risk classification was positively associated with cardiac mortality (6·75 [5·17-8·82], p<0·001, for very high risk vs low or medium risk) and MACE (4·68 [3·93-5·57], p<0·001 for very high risk vs low or medium risk). Finally, the AI-Risk model was well calibrated against true events. INTERPRETATION: The FAI Score captures inflammatory risk beyond the current clinical risk stratification and CCTA interpretation, particularly among patients without obstructive CAD. The AI-Risk integrates this information in a prognostic algorithm, which could be used as an alternative to traditional risk factor-based risk calculators. FUNDING: British Heart Foundation, NHS-AI award, Innovate UK, National Institute for Health and Care Research, and the Oxford Biomedical Research Centre.

Combined use of the CLivD score and FIB-4 for prediction of liver-related outcomes in the population.

BACKGROUND AND AIMS: A need exists for effective and practical tools to identify individuals at increased risk of liver-related outcomes (LROs) within the general population. APPROACH AND RESULTS: We externally validated the chronic liver disease (CLivD) score for LROs in the UK Biobank cohort. We also investigated the sequential combined use of CLivD and fibrosis-4 (FIB-4) scores. Our analysis included 369,832 adults without baseline liver disease and with available data for CLivD and FIB-4 computation. LROs reflecting compensated or decompensated liver cirrhosis or HCC were ascertained through linkages with electronic health care registries. Discriminatory performance and cumulative incidence were evaluated with competing-risk methodologies. Over a 10-year follow-up, time-dependent AUC values for LRO prediction were 0.80 for CLivD lab (including gamma-glutamyltransferase), 0.72 for CLivD non-lab (excluding laboratory values), and 0.75 for FIB-4. CLivD lab demonstrated AUC values exceeding 0.85 for liver-related death and severe alcohol-associated liver outcomes. The predictive performance of FIB-4 increased with rising CLivD scores; 10-year FIB-4 AUC values ranged from 0.60 within the minimal-risk CLivD subgroup to 0.81 within the high-risk CLivD subgroup. Moreover, in the minimal-risk CLivD subgroup, the cumulative incidence of LRO varied from 0.05% to 0.3% across low-to-high FIB-4 strata. In contrast, within the high-risk CLivD subgroup, the corresponding incidence ranged from 1.7% to 21.1% (up to 33% in individuals with FIB-4 >3.25). CONCLUSIONS: The CLivD score is a valid tool for LRO risk assessment and improves the predictive performance of FIB-4. The combined use of CLivD and FIB-4 identified a subgroup where 1 in 3 individuals developed LROs within 10 years.

Precision medicine for psychotic disorders: objective assessment, risk prediction, and pharmacogenomics.

Psychosis occurs inside the brain, but may have external manifestations (peripheral molecular biomarkers, behaviors) that can be objectively and quantitatively measured. Blood biomarkers that track core psychotic manifestations such as hallucinations and delusions could provide a window into the biology of psychosis, as well as help with diagnosis and treatment. We endeavored to identify objective blood gene expression biomarkers for hallucinations and delusions, using a stepwise discovery, prioritization, validation, and testing in independent cohorts design. We were successful in identifying biomarkers that were predictive of high hallucinations and of high delusions states, and of future psychiatric hospitalizations related to them, more so when personalized by gender and diagnosis. Top biomarkers for hallucinations that survived discovery, prioritization, validation and testing include PPP3CB, DLG1, ENPP2, ZEB2, and RTN4. Top biomarkers for delusions include AUTS2, MACROD2, NR4A2, PDE4D, PDP1, and RORA. The top biological pathways uncovered by our work are glutamatergic synapse for hallucinations, as well as Rap1 signaling for delusions. Some of the biomarkers are targets of existing drugs, of potential utility in pharmacogenomics approaches (matching patients to medications, monitoring response to treatment). The top biomarkers gene expression signatures through bioinformatic analyses suggested a prioritization of existing medications such as clozapine and risperidone, as well as of lithium, fluoxetine, valproate, and the nutraceuticals omega-3 fatty acids and magnesium. Finally, we provide an example of how a personalized laboratory report for doctors would look. Overall, our work provides advances for the improved diagnosis and treatment for schizophrenia and other psychotic disorders.

Lipidomic risk scores are independent of polygenic risk scores and can predict incidence of diabetes and cardiovascular disease in a large population cohort.

Type 2 diabetes (T2D) and cardiovascular disease (CVD) represent significant disease burdens for most societies and susceptibility to these diseases is strongly influenced by diet and lifestyle. Physiological changes associated with T2D or CVD, such has high blood pressure and cholesterol and glucose levels in the blood, are often apparent prior to disease incidence. Here we integrated genetics, lipidomics, and standard clinical diagnostics to assess future T2D and CVD risk for 4,067 participants from a large prospective population-based cohort, the Malmö Diet and Cancer-Cardiovascular Cohort. By training Ridge regression-based machine learning models on the measurements obtained at baseline when the individuals were healthy, we computed several risk scores for T2D and CVD incidence during up to 23 years of follow-up. We used these scores to stratify the participants into risk groups and found that a lipidomics risk score based on the quantification of 184 plasma lipid concentrations resulted in a 168% and 84% increase of the incidence rate in the highest risk group and a 77% and 53% decrease of the incidence rate in lowest risk group for T2D and CVD, respectively, compared to the average case rates of 13.8% and 22.0%. Notably, lipidomic risk correlated only marginally with polygenic risk, indicating that the lipidome and genetic variants may constitute largely independent risk factors for T2D and CVD. Risk stratification was further improved by adding standard clinical variables to the model, resulting in a case rate of 51.0% and 53.3% in the highest risk group for T2D and CVD, respectively. The participants in the highest risk group showed significantly altered lipidome compositions affecting 167 and 157 lipid species for T2D and CVD, respectively. Our results demonstrated that a subset of individuals at high risk for developing T2D or CVD can be identified years before disease incidence. The lipidomic risk, which is derived from only one single mass spectrometric measurement that is cheap and fast, is informative and could extend traditional risk assessment based on clinical assays.

Benchmarking multi-ancestry prostate cancer polygenic risk scores in a real-world cohort.

Prostate cancer is a heritable disease with ancestry-biased incidence and mortality. Polygenic risk scores (PRSs) offer promising advancements in predicting disease risk, including prostate cancer. While their accuracy continues to improve, research aimed at enhancing their effectiveness within African and Asian populations remains key for equitable use. Recent algorithmic developments for PRS derivation have resulted in improved pan-ancestral risk prediction for several diseases. In this study, we benchmark the predictive power of six widely used PRS derivation algorithms, including four of which adjust for ancestry, against prostate cancer cases and controls from the UK Biobank and All of Us cohorts. We find modest improvement in discriminatory ability when compared with a simple method that prioritizes variants, clumping, and published polygenic risk scores. Our findings underscore the importance of improving upon risk prediction algorithms and the sampling of diverse cohorts.

Development and Validation of a Protein Risk Score for Mortality in Heart Failure : A Community Cohort Study.

BACKGROUND: Heart failure (HF) is a complex clinical syndrome with high mortality. Current risk stratification approaches lack precision. High-throughput proteomics could improve risk prediction. Its use in clinical practice to guide the management of patients with HF depends on validation and evidence of clinical benefit. OBJECTIVE: To develop and validate a protein risk score for mortality in patients with HF. DESIGN: Community-based cohort. SETTING: Southeast Minnesota. PARTICIPANTS: Patients with HF enrolled between 2003 and 2012 and followed through 2021. MEASUREMENTS: A total of 7289 plasma proteins in 1351 patients with HF were measured using the SomaScan Assay (SomaLogic). A protein risk score was derived using least absolute shrinkage and selection operator regression and temporal validation in patients enrolled between 2003 and 2007 (development cohort) and 2008 and 2012 (validation cohort). Multivariable Cox regression was used to examine the association between the protein risk score and mortality. The performance of the protein risk score to predict 5-year mortality risk was assessed using calibration plots, decision curves, and relative utility analyses and compared with a clinical model, including the Meta-Analysis Global Group in Chronic Heart Failure mortality risk score and N-terminal pro-B-type natriuretic peptide. RESULTS: The development (n = 855; median age, 78 years; 50% women; 29% with ejection fraction <40%) and validation cohorts (n = 496; median age, 76 years; 45% women; 33% with ejection fraction <40%) were mostly similar. In the development cohort, 38 unique proteins were selected for the protein risk score. Independent of ejection fraction, the protein risk score demonstrated good calibration, reclassified mortality risk particularly at the extremes of the risk distribution, and showed greater clinical utility compared with the clinical model. LIMITATION: Participants were predominantly of European ancestry, potentially limiting the generalizability of the findings to different patient populations. CONCLUSION: Validation of the protein risk score demonstrated good calibration and evidence of predicted benefits to stratify the risk for death in HF superior to that of clinical methods. Further studies are needed to prospectively evaluate the score's performance in diverse populations and determine risk thresholds for interventions. PRIMARY FUNDING SOURCE: Division of Intramural Research at the National Heart, Lung, and Blood Institute of the National Institutes of Health.

Point-of-care high-sensitivity cardiac troponin in suspected acute myocardial infarction assessed at baseline and 2†h.

BACKGROUND AND AIMS: Strategies to assess patients with suspected acute myocardial infarction (AMI) using a point-of-care (POC) high-sensitivity cardiac troponin I (hs-cTnI) assay may expedite emergency care. A 2-h POC hs-cTnI strategy for emergency patients with suspected AMI was derived and validated. METHODS: In two international, multi-centre, prospective, observational studies of adult emergency patients (1486 derivation cohort and 1796 validation cohort) with suspected AMI, hs-cTnI (Siemens Atellica® VTLi) was measured at admission and 2 h later. Adjudicated final diagnoses utilized the hs-cTn assay in clinical use. A risk stratification algorithm was derived and validated. The primary diagnostic outcome was index AMI (Types 1 and 2). The primary safety outcome was 30-day major adverse cardiac events incorporating AMI and cardiac death. RESULTS: Overall, 81 (5.5%) and 88 (4.9%) patients in the derivation and validation cohorts, respectively, had AMI. The 2-h algorithm defined 66.1% as low risk with a sensitivity of 98.8% [95% confidence interval (CI) 89.3%-99.9%] and a negative predictive value of 99.9 (95% CI 99.2%-100%) for index AMI in the derivation cohort. In the validation cohort, 53.3% were low risk with a sensitivity of 98.9% (95% CI 92.4%-99.8%) and a negative predictive value of 99.9% (95% CI 99.3%-100%) for index AMI. The high-risk metrics identified 5.4% of patients with a specificity of 98.5% (95% CI 96.6%-99.4%) and a positive predictive value of 74.5% (95% CI 62.7%-83.6%) for index AMI. CONCLUSIONS: A 2-h algorithm using a POC hs-cTnI concentration enables safe and efficient risk assessment of patients with suspected AMI. The short turnaround time of POC testing may support significant efficiencies in the management of the large proportion of emergency patients with suspected AMI.

Merging machine learning and patient preference: a novel tool for risk prediction of percutaneous coronary interventions.

BACKGROUND AND AIMS: Predicting personalized risk for adverse events following percutaneous coronary intervention (PCI) remains critical in weighing treatment options, employing risk mitigation strategies, and enhancing shared decision-making. This study aimed to employ machine learning models using pre-procedural variables to accurately predict common post-PCI complications. METHODS: A group of 66 adults underwent a semiquantitative survey assessing a preferred list of outcomes and model display. The machine learning cohort included 107 793 patients undergoing PCI procedures performed at 48 hospitals in Michigan between 1 April 2018 and 31 December 2021 in the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) registry separated into training and validation cohorts. External validation was conducted in the Cardiac Care Outcomes Assessment Program database of 56 583 procedures in 33 hospitals in Washington. RESULTS: Overall rate of in-hospital mortality was 1.85% (n = 1999), acute kidney injury 2.51% (n = 2519), new-onset dialysis 0.44% (n = 462), stroke 0.41% (n = 447), major bleeding 0.89% (n = 942), and transfusion 2.41% (n = 2592). The model demonstrated robust discrimination and calibration for mortality {area under the receiver-operating characteristic curve [AUC]: 0.930 [95% confidence interval (CI) 0.920-0.940]}, acute kidney injury [AUC: 0.893 (95% CI 0.883-0.903)], dialysis [AUC: 0.951 (95% CI 0.939-0.964)], stroke [AUC: 0.751 (95%CI 0.714-0.787)], transfusion [AUC: 0.917 (95% CI 0.907-0.925)], and major bleeding [AUC: 0.887 (95% CI 0.870-0.905)]. Similar discrimination was noted in the external validation population. Survey subjects preferred a comprehensive list of individually reported post-procedure outcomes. CONCLUSIONS: Using common pre-procedural risk factors, the BMC2 machine learning models accurately predict post-PCI outcomes. Utilizing patient feedback, the BMC2 models employ a patient-centred tool to clearly display risks to patients and providers (https://shiny.bmc2.org/pci-prediction/). Enhanced risk prediction prior to PCI could help inform treatment selection and shared decision-making discussions.

Atherosclerosis evaluation and cardiovascular risk estimation using coronary computed tomography angiography.

Clinical risk scores based on traditional risk factors of atherosclerosis correlate imprecisely to an individual's complex pathophysiological predisposition to atherosclerosis and provide limited accuracy for predicting major adverse cardiovascular events (MACE). Over the past two decades, computed tomography scanners and techniques for coronary computed tomography angiography (CCTA) analysis have substantially improved, enabling more precise atherosclerotic plaque quantification and characterization. The accuracy of CCTA for quantifying stenosis and atherosclerosis has been validated in numerous multicentre studies and has shown consistent incremental prognostic value for MACE over the clinical risk spectrum in different populations. Serial CCTA studies have advanced our understanding of vascular biology and atherosclerotic disease progression. The direct disease visualization of CCTA has the potential to be used synergistically with indirect markers of risk to significantly improve prevention of MACE, pending large-scale randomized evaluation.

Integration of a polygenic score into guideline-recommended prediction of cardiovascular disease.

BACKGROUND AND AIMS: It is not clear how a polygenic risk score (PRS) can be best combined with guideline-recommended tools for cardiovascular disease (CVD) risk prediction, e.g. SCORE2. METHODS: A PRS for coronary artery disease (CAD) was calculated in participants of UK Biobank (n = 432 981). Within each tenth of the PRS distribution, the odds ratios (ORs)-referred to as PRS-factor-for CVD (i.e. CAD or stroke) were compared between the entire population and subgroups representing the spectrum of clinical risk. Replication was performed in the combined Framingham/Atherosclerosis Risk in Communities (ARIC) populations (n = 10 757). The clinical suitability of a multiplicative model 'SCORE2 × PRS-factor' was tested by risk reclassification. RESULTS: In subgroups with highly different clinical risks, CVD ORs were stable within each PRS tenth. SCORE2 and PRS showed no significant interactive effects on CVD risk, which qualified them as multiplicative factors: SCORE2 × PRS-factor = total risk. In UK Biobank, the multiplicative model moved 9.55% of the intermediate (n = 145 337) to high-risk group increasing the individuals in this category by 56.6%. Incident CVD occurred in 8.08% of individuals reclassified by the PRS-factor from intermediate to high risk, which was about two-fold of those remained at intermediate risk (4.08%). Likewise, the PRS-factor shifted 8.29% of individuals from moderate to high risk in Framingham/ARIC. CONCLUSIONS: This study demonstrates that absolute CVD risk, determined by a clinical risk score, and relative genetic risk, determined by a PRS, provide independent information. The two components may form a simple multiplicative model improving precision of guideline-recommended tools in predicting incident CVD.

Incident heart failure in chronic kidney disease: proteomics informs biology and risk stratification.

BACKGROUND AND AIMS: Incident heart failure (HF) among individuals with chronic kidney disease (CKD) incurs hospitalizations that burden patients and health care systems. There are few preventative therapies, and the Pooled Cohort equations to Prevent Heart Failure (PCP-HF) perform poorly in the setting of CKD. New drug targets and better risk stratification are urgently needed. METHODS: In this analysis of incident HF, SomaScan V4.0 (4638 proteins) was analysed in 2906 participants of the Chronic Renal Insufficiency Cohort (CRIC) with validation in the Atherosclerosis Risk in Communities (ARIC) study. The primary outcome was 14-year incident HF (390 events); secondary outcomes included 4-year HF (183 events), HF with reduced ejection fraction (137 events), and HF with preserved ejection fraction (165 events). Mendelian randomization and Gene Ontology were applied to examine causality and pathways. The performance of novel multi-protein risk models was compared to the PCP-HF risk score. RESULTS: Over 200 proteins were associated with incident HF after adjustment for estimated glomerular filtration rate at P < 1 × 10-5. After adjustment for covariates including N-terminal pro-B-type natriuretic peptide, 17 proteins remained associated at P < 1 × 10-5. Mendelian randomization associations were found for six proteins, of which four are druggable targets: FCG2B, IGFBP3, CAH6, and ASGR1. For the primary outcome, the C-statistic (95% confidence interval [CI]) for the 48-protein model in CRIC was 0.790 (0.735, 0.844) vs. 0.703 (0.644, 0.762) for the PCP-HF model (P = .001). C-statistic (95% CI) for the protein model in ARIC was 0.747 (0.707, 0.787). CONCLUSIONS: Large-scale proteomics reveal novel circulating protein biomarkers and potential mediators of HF in CKD. Proteomic risk models improve upon the PCP-HF risk score in this population.

Impact of age, comorbidities and relevant changes on surveillance strategy of intraductal papillary mucinous neoplasms: a competing risk analysis.

OBJECTIVE: Cost-effectiveness of surveillance for branch-duct intraductal papillary mucinous neoplasms (BD-IPMNs) is debated. We combined different categories of risks of IPMN progression and of IPMN-unrelated mortality to improve surveillance strategies. DESIGN: Retrospective analysis of 926 presumed BD-IPMNs lacking worrisome features (WFs)/high-risk stigmata (HRS) under surveillance. Charlson Comorbidity Index (CACI) defined the severity of comorbidities. IPMN relevant changes included development of WF/HRS, pancreatectomy or death for IPMN or pancreatic cancer. Pancreatic malignancy-unrelated death was recorded. Cumulative incidence of IPMN relevant changes were estimated using the competing risk approach. RESULTS: 5-year cumulative incidence of relevant changes was 17.83% and 1.6% developed pancreatic malignancy. 5-year cumulative incidences for IPMN relevant changes were 13.73%, 19.93% and 25.04% in low-risk, intermediate-risk and high-risk groups, respectively. Age ≥75 (HR: 4.15) and CACI >3 (HR: 3.61) were independent predictors of pancreatic malignancy-unrelated death. 5-year cumulative incidence for death for other causes was 15.93% for age ≥75+CACI >3 group and 1.49% for age <75+CACI ≤3. 5-year cumulative incidence of IPMN relevant changes were 13.94% in patients with age <75+CACI ≤3 compared with 29.60% in those with age ≥75+CACI >3. In this group 5-year rate of malignancy-free patients was 95.56% with a 5-year survival of 79.51%. CONCLUSION: Although it is not uncommon the occurrence of changes considered by current guidelines as relevant during surveillance of low risk BD-IPMNs, malignancy rate is low and survival is significantly affected by competing patients' age and comorbidities. IPMN surveillance strategy should be tailored based on these features and modulated over time.

Existing Nongated CT Coronary Calcium Predicts Operative Risk in Patients Undergoing Noncardiac Surgeries (ENCORES).

BACKGROUND: Preoperative cardiovascular risk stratification before noncardiac surgery is a common clinical challenge. Coronary artery calcium scores from ECG-gated chest computed tomography (CT) imaging are associated with perioperative events. At the time of preoperative evaluation, many patients will not have had ECG-gated CT imaging, but will have had nongated chest CT studies performed for a variety of noncardiac indications. We evaluated relationships between coronary calcium severity estimated from previous nongated chest CT imaging and perioperative major clinical events (MCE) after noncardiac surgery. METHODS: We retrospectively identified consecutive adults age ≥45 years who underwent in-hospital, major noncardiac surgery from 2016 to 2020 at a large academic health system composed of 4 acute care centers. All patients had nongated (contrast or noncontrast) chest CT imaging performed within 1 year before surgery. Coronary calcium in each vessel was retrospectively graded from absent to severe using a 0 to 3 scale (absent, mild, moderate, severe) by physicians blinded to clinical data. The estimated coronary calcium burden (ECCB) was computed as the sum of scores for each coronary artery (0 to 9 scale). A Revised Cardiac Risk Index was calculated for each patient. Perioperative MCE was defined as all-cause death or myocardial infarction within 30 days of surgery. RESULTS: A total of 2554 patients (median age, 68 years; 49.7% women; median Revised Cardiac Risk Index, 1) were included. The median time interval from nongated chest CT imaging to noncardiac surgery was 15 days (interquartile range, 3-106 days). The median ECCB was 1 (interquartile range, 0-3). Perioperative MCE occurred in 136 (5.2%) patients. Higher ECCB values were associated with stepwise increases in perioperative MCE (0: 2.9%, 1-2: 3.7%, 3-5: 8.0%; 6-9: 12.6%, P<0.001). Addition of ECCB to a model with the Revised Cardiac Risk Index improved the C-statistic for MCE (from 0.675 to 0.712, P=0.018), with a net reclassification improvement of 0.428 (95% CI, 0.254-0.601, P<0.0001). An ECCB ≥3 was associated with 2-fold higher adjusted odds of MCE versus an ECCB <3 (adjusted odds ratio, 2.11 [95% CI, 1.42-3.12]). CONCLUSIONS: Prevalence and severity of coronary calcium obtained from existing nongated chest CT imaging improve preoperative clinical risk stratification before noncardiac surgery.

Low-Density Lipoprotein Cholesterol Is Predominantly Associated With Atherosclerotic Cardiovascular Disease Events in Patients With Evidence of Coronary Atherosclerosis: The Western Denmark Heart Registry.

BACKGROUND: Low-density lipoprotein cholesterol (LDL-C) is an important causal risk factor for atherosclerotic cardiovascular disease (ASCVD). However, a sizable proportion of middle-aged individuals with elevated LDL-C level have not developed coronary atherosclerosis as assessed by coronary artery calcification (CAC). Whether presence of CAC modifies the association of LDL-C with ASCVD risk is unknown. We evaluated the association of LDL-C with future ASCVD events in patients with and without CAC. METHODS: The study included 23 132 consecutive symptomatic patients evaluated for coronary artery disease using coronary computed tomography angiography (CTA) from the Western Denmark Heart Registry, a seminational, multicenter-based registry with longitudinal registration of patient and procedure data. We assessed the association of LDL-C level obtained before CTA with ASCVD (myocardial infarction and ischemic stroke) events occurring during follow-up stratified by CAC>0 versus CAC=0 using Cox regression models adjusted for baseline characteristics. Outcomes were identified through linkage among national registries covering all hospitals in Denmark. We replicated our results in the National Heart, Lung, and Blood Institute-funded Multi-Ethnic Study of Atherosclerosis. RESULTS: During a median follow-up of 4.3 years, 552 patients experienced a first ASCVD event. In the overall population, LDL-C (per 38.7 mg/dL increase) was associated with ASCVD events occurring during follow-up (adjusted hazard ratio [aHR], 1.14 [95% CI, 1.04-1.24]). When stratified by the presence or absence of baseline CAC, LDL-C was only associated with ASCVD in the 10 792/23 132 patients (47%) with CAC>0 (aHR, 1.18 [95% CI, 1.06-1.31]); no association was observed among the 12 340/23 132 patients (53%) with CAC=0 (aHR, 1.02 [95% CI, 0.87-1.18]). Similarly, a very high LDL-C level (>193 mg/dL) versus LDL-C <116 mg/dL was associated with ASCVD in patients with CAC>0 (aHR, 2.42 [95% CI, 1.59-3.67]) but not in those without CAC (aHR, 0.92 [0.48-1.79]). In patients with CAC=0, diabetes, current smoking, and low high-density lipoprotein cholesterol levels were associated with future ASCVD events. The principal findings were replicated in the Multi-Ethnic Study of Atherosclerosis. CONCLUSIONS: LDL-C appears to be almost exclusively associated with ASCVD events over ≈5 years of follow-up in middle-aged individuals with versus without evidence of coronary atherosclerosis. This information is valuable for individualized risk assessment among middle-aged people with or without coronary atherosclerosis.

Heterogeneity in the Association Between the Presence of Coronary Artery Calcium and Cardiovascular Events: A Machine-Learning Approach in the MESA Study.

BACKGROUND: Coronary artery calcium (CAC) has been widely recognized as an important predictor of cardiovascular disease (CVD). Given the finite resources, it is important to identify individuals who would receive the most benefit from detecting positive CAC by screening. However, the evidence is limited as to whether the burden of positive CAC on CVD differs by multidimensional individual characteristics. We sought to investigate the heterogeneity in the association between positive CAC and incident CVD. METHODS: This cohort study included adults from MESA (Multi-Ethnic Study of Atherosclerosis) ages ≥45 years and free of cardiovascular disease. After propensity score matching in a 1:1 ratio, we applied a machine learning causal forest model to (1) evaluate the heterogeneity in the association between positive CAC and incident CVD, and (2) predict the increase in CVD risk at 10-years when CAC>0 (versus CAC=0) at the individual level. We then compared the estimated increase in CVD risk when CAC>0 to the absolute 10-year atherosclerotic CVD (ASCVD) risk calculated by the 2013 American College of Cardiology/American Heart Association pooled cohort equations. RESULTS: Across 3328 adults in our propensity score-matched analysis, our causal forest model showed the heterogeneity in the association between CAC>0 and incident CVD. We found a dose-response relationship of the estimated increase in CVD risk when CAC>0 with higher 10-year ASCVD risk. Almost all individuals (2293 of 2428 [94.4%]) with borderline risk of ASCVD or higher showed ≥2.5% increase in CVD risk when CAC>0. Even among 900 adults with low ASCVD risk, 689 (69.2%) showed ≥2.5% increase in CVD risk when CAC>0; these individuals were more likely to be male, Hispanic, and have unfavorable CVD risk factors than others. CONCLUSIONS: The expected increases in CVD risk when CAC>0 were heterogeneous across individuals. Moreover, nearly 70% of people with low ASCVD risk showed a large increase in CVD risk when CAC>0, highlighting the need for CAC screening among such low-risk individuals. Future studies are needed to assess whether targeting individuals for CAC measurements based on not only the absolute ASCVD risk but also the expected increase in CVD risk when CAC>0 improves cardiovascular outcomes.

Deep learning-based risk stratification of preoperative breast biopsies using digital whole slide images.

BACKGROUND: Nottingham histological grade (NHG) is a well established prognostic factor in breast cancer histopathology but has a high inter-assessor variability with many tumours being classified as intermediate grade, NHG2. Here, we evaluate if DeepGrade, a previously developed model for risk stratification of resected tumour specimens, could be applied to risk-stratify tumour biopsy specimens. METHODS: A total of 11,955,755 tiles from 1169 whole slide images of preoperative biopsies from 896 patients diagnosed with breast cancer in Stockholm, Sweden, were included. DeepGrade, a deep convolutional neural network model, was applied for the prediction of low- and high-risk tumours. It was evaluated against clinically assigned grades NHG1 and NHG3 on the biopsy specimen but also against the grades assigned to the corresponding resection specimen using area under the operating curve (AUC). The prognostic value of the DeepGrade model in the biopsy setting was evaluated using time-to-event analysis. RESULTS: Based on preoperative biopsy images, the DeepGrade model predicted resected tumour cases of clinical grades NHG1 and NHG3 with an AUC of 0.908 (95% CI: 0.88; 0.93). Furthermore, out of the 432 resected clinically-assigned NHG2 tumours, 281 (65%) were classified as DeepGrade-low and 151 (35%) as DeepGrade-high. Using a multivariable Cox proportional hazards model the hazard ratio between DeepGrade low- and high-risk groups was estimated as 2.01 (95% CI: 1.06; 3.79). CONCLUSIONS: DeepGrade provided prediction of tumour grades NHG1 and NHG3 on the resection specimen using only the biopsy specimen. The results demonstrate that the DeepGrade model can provide decision support to identify high-risk tumours based on preoperative biopsies, thus improving early treatment decisions.

Validation of an AI-based solution for breast cancer risk stratification using routine digital histopathology images.

BACKGROUND: Stratipath Breast is a CE-IVD marked artificial intelligence-based solution for prognostic risk stratification of breast cancer patients into high- and low-risk groups, using haematoxylin and eosin (H&E)-stained histopathology whole slide images (WSIs). In this validation study, we assessed the prognostic performance of Stratipath Breast in two independent breast cancer cohorts. METHODS: This retrospective multi-site validation study included 2719 patients with primary breast cancer from two Swedish hospitals. The Stratipath Breast tool was applied to stratify patients based on digitised WSIs of the diagnostic H&E-stained tissue sections from surgically resected tumours. The prognostic performance was evaluated using time-to-event analysis by multivariable Cox Proportional Hazards analysis with progression-free survival (PFS) as the primary endpoint. RESULTS: In the clinically relevant oestrogen receptor (ER)-positive/human epidermal growth factor receptor 2 (HER2)-negative patient subgroup, the estimated hazard ratio (HR) associated with PFS between low- and high-risk groups was 2.76 (95% CI: 1.63-4.66, p-value < 0.001) after adjusting for established risk factors. In the ER+/HER2- Nottingham histological grade (NHG) 2 subgroup, the HR was 2.20 (95% CI: 1.22-3.98, p-value = 0.009) between low- and high-risk groups. CONCLUSION: The results indicate an independent prognostic value of Stratipath Breast among all breast cancer patients, as well as in the clinically relevant ER+/HER2- subgroup and the NHG2/ER+/HER2- subgroup. Improved risk stratification of intermediate-risk ER+/HER2- breast cancers provides information relevant for treatment decisions of adjuvant chemotherapy and has the potential to reduce both under- and overtreatment. Image-based risk stratification provides the added benefit of short lead times and substantially lower cost compared to molecular diagnostics and therefore has the potential to reach broader patient groups.