Search

Skin cancers occur commonly worldwide. The prognosis and disease burden are highly dependent on the cancer type and disease stage at diagnosis. We systematically reviewed studies on artificial intelligence and machine learning (AI/ML) algorithms that aim to facilitate the early diagnosis of skin cancers, focusing on their application in primary and community care settings. We searched MEDLINE, Embase, Scopus, and Web of Science (from Jan 1, 2000, to Aug 9, 2021) for all studies providing evidence on applying AI/ML algorithms to the early diagnosis of skin cancer, including all study designs and languages. The primary outcome was diagnostic accuracy of the algorithms for skin cancers. The secondary outcomes included an overview of AI/ML methods, evaluation approaches, cost-effectiveness, and acceptability to patients and clinicians. We identified 14 224 studies. Only two studies used data from clinical settings with a low prevalence of skin cancers. We reported data from all 272 studies that could be relevant in primary care. The primary outcomes showed reasonable mean diagnostic accuracy for melanoma (89·5% [range 59·7-100%]), squamous cell carcinoma (85·3% [71·0-97·8%]), and basal cell carcinoma (87·6% [70·0-99·7%]). The secondary outcomes showed a heterogeneity of AI/ML methods and study designs, with high amounts of incomplete reporting (eg, patient demographics and methods of data collection). Few studies used data on populations with a low prevalence of skin cancers to train and test their algorithms; therefore, the widespread adoption into community and primary care practice cannot currently be recommended until efficacy in these populations is shown. We did not identify any health economic, patient, or clinician acceptability data for any of the included studies. We propose a methodological checklist for use in the development of new AI/ML algorithms to detect skin cancer, to facilitate their design, evaluation, and implementation.

BACKGROUND There is uncertainty regarding the impact of statins on the risk of atherosclerotic cardiovascular disease (ASCVD) and its major complication, acute heart failure (AHF). OBJECTIVES The aim of this study was to investigate whether previous statin therapy translates into lower AHF events and improved survival from AHF among patients presenting with an acute coronary syndrome (ACS) as a first manifestation of ASCVD. METHODS Data were drawn from the International Survey of Acute Coronary Syndromes Archives. The study participants consisted of 14,542 Caucasian patients presenting with ACS without previous ASCVD events. Statin users before the index event were compared with nonusers by using inverse probability weighting models. Estimates were compared by test of interaction on the log scale. Main outcome measures were the incidence of AHF according to Killip class and the rate of 30-day all-cause mortality in patients presenting with AHF. RESULTS Previous statin therapy was associated with a significantly decreased rate of AHF on admission (4.3% absolute risk reduction; risk ratio [RR]: 0.72; 95% CI: 0.62-0.83) regardless of younger (40-75 years) or older age (interaction P = 0.27) and sex (interaction P = 0.22). Moreover, previous statin therapy predicted a lower risk of 30-day mortality in the subset of patients presenting with AHF on admission (5.2 % absolute risk reduction; RR: 0.71; 95% CI: 0.50-0.99). CONCLUSIONS Among adults presenting with ACS as a first manifestation of ASCVD, previous statin therapy is associated with a reduced risk of AHF and improved survival from AHF. (C) 2022 by the American College of Cardiology Foundation.

Background: Although a family history (FHx) is an accepted risk factor for cardiovascular (CV) disease, few studies have examined the predictive strength of a positive FHx after adjusting for other conventional risk factors and medications Methods: We analyzed 12,922 patients with ACSs, without evidence of prior CV disease enrolled in the ISACS-TC registry between January 2010 to January 2021. Main outcome measures were the adjusted rates of STEMI and 30-day mortality from STEMI using multivariable logistic regression models Results: Overall, 3,147 patients (24,4%) self-reported an FHx of CV disease, defined as first-degree relative with premature CV events (men, age

Machine learning has shown enormous potential for computer-aided drug discovery. Here we show how modern convolutional neural networks (CNNs) can be applied to structure-based virtual screening. We have coupled our densely connected CNN (DenseNet) with a transfer learning approach which we use to produce an ensemble of protein family-specific models. We conduct an in-depth empirical study and provide the first guidelines on the minimum requirements for adopting a protein family-specific model. Our method also highlights the need for additional data, even in data-rich protein families. Our approach outperforms recent benchmarks on the DUD-E dataset and an independent test set constructed from the ChEMBL database. Using a clustered cross-validation on DUD-E, we achieve an average AUC ROC of 0.92 and a 0.5% ROC enrichment factor of 79. This represents an improvement in early enrichment of over 75% compared to a recent machine learning benchmark. Our results demonstrate that the continued improvements in machine learning architecture for computer vision apply to structure-based virtual screening.

Background: Delay from symptom onset to reperfusion by primary percutaneous coronary intervention (PCI) is longer in women and has been linked to increased mortality and worse clinical outcome. The mechanism underlying this association is still unclear. Purpose: We sought to investigate the impact of delay from symptom onset to hospital presentation on sex difference in TIMI flow grades and 30-day mortality after primary PCI for STEMI. Methods: The current study evaluated 2596 patients with STEMI who underwent primary PCI within 12 hours from symptom onset and had a stent implantation between 2010 and 2016 in the ISACS-TC registry (ClinicalTrials.gov, NCT01218776). Main outcomes measures were adjusted 30-day mortality rates and suboptimal post-PCI TIMI (Thrombolysis In Myocardial Infarction) flow (grades ≤2) estimated using inverse probability of treatment weighted (IPTW) models. Time from symptom onset to hospital presentation was classified as

Background The relationship between female sex and cardiovascular mortality in myocardial infarction (MI) is controversial. Most available data are from high-income countries (HIC) where baseline risk is lower and revascularization procedures are more likely, so the generalizability to other populations is unclear. Purpose The main goal of this study was to unravel the relation between patient-specific revascularization through percutaneous coronary intervention (PCI) and mortality among women and men. Methods Data were drawn from the ISACS-Archives (NCT04008173) which includes a large cohort of patients enrolled in 6 European HIC (Croatia, Italy, Lithuania, Hungary, Romania, and United Kingdom) and 7 middle-income countries (MIC; Bosnia & Herzegovina, Kosovo, Macedonia, Moldova, Montenegro, and Serbia). Participants were stratified by MI subtypes: STEMI and NSTEMI. The primary outcome was 30-day mortality. To yield unbiased sex estimates of the effects of MI on mortality we modeled covariates and outcomes by propensity score-based analytic methods. We calculated the women to men risk ratios (RRs) using weighting with estimates compared by test of interaction on the log scale. Results The cohort consisted of 22,087 patients with MI (30.2% women). Patient outcomes varied according to the subtype of MI. Females was associated with a greater excess risk of 30-day mortality in STEMI (RR: 1.94; 95% CI: 1.71–2.21) compared with NSTEMI (RR: 1.12; 95% CI: 0.95–1.50; P interaction Conclusion Women presenting with STEMI have worse early mortality rates than their male counterparts in both HIC and MIC even in patients undergoing revascularization. By contrast, sex differences are attenuated or no longer apparent in NSTEMI. With no information on the type of MI on admission, sex differences in early outcomes are difficult to be fully understood. Funding Acknowledgement Type of funding sources: None.

Background The debate about statins in primary prevention of cardiovascular (CV) disease is still alive, especially in old and very old adults. Purpose We undertook a propensity match-weighted cohort study to investigate whether statin treatment recommendations translate into improved cardiovascular (CV) outcomes in the current routine clinical care of the elderly. Methods We included in our analysis 5,619 people aged 65 years or older from the ISACS (International Survey of Acute Coronary Syndrome) Archives (NCT04008173) who presented to hospital with a first manifestation of CV disease. Participants were stratified as statin users versus nonusers and as old (65 to 75 years) versus very old (76 years or over) adults. We estimated the effects of statins on the most severe clinical manifestation of CV disease, namely ST segment elevation myocardial infarction (STEMI), using inverse probability of treatment weighting models. Estimates were compared by test of interaction on the log scale. Results The risk of STEMI was much lower in statin users than in nonusers in both patients aged 65 to 75 years (14.7% absolute risk reduction; relative risk [RR] ratio: 0.55, 95% CI 0.45 to 0.66) and those aged 76 years and older (13.3% absolute risk reduction; RR ratio: 0.58, 95% CI 0.46 to 0.72). Estimates were similar in patients with and without history of hypercholesterolemia (interaction test; p value= 0.2408). Proportional reductions in STEMI diminished with female sex in the old (p for interaction=0.002), but not in the very old age (p for interaction=0.26). We also observed a remarkable reduction in the risk of 30- day mortality from STEMI with statin therapy in both age groups (10.2% absolute risk reduction; RR ratio: 0.39; 95% CI 0.23 – 0.68 for patients aged 76 or over and 3.8% absolute risk reduction; RR ratio 0.37; 95% CI 0.17 – 0.82 for patients aged 65 to 75 years old; interaction test, p value=0.4570). Conclusion Preventive statin therapy in the elderly reduces the risk of STEMI with benefits in mortality from STEMI, irrespective of the presence of a history of hypercholesterolemia. This effect persists after the age of 76 years. Benefits are less pronounced in women. Funding Acknowledgement Type of funding sources: None.

BACKGROUND ST-segment elevation myocardial infarction (STEMI) complicated by symptoms of acute de novo heart failure is associated with excess mortality. Whether development of heart failure and its outcomes differ by sex is unknown. OBJECTIVES This study sought to examine the relationships among sex, acute heart failure, and related outcomes after STEMI in patients with no prior history of heart failure recorded at baseline. METHODS Patients were recruited from a network of hospitals in the ISACS-TC (International Survey of Acute Coronary Syndromes in Transitional Countries) registry (NCT01218776). Main outcome measures were incidence of Killip class >= II at hospital presentation and risk-adjusted 30-day mortality rates were estimated using inverse probability of weighting and logistic regression models. RESULTS This study included 10,443 patients (3,112 women). After covariate adjustment and matching for age, cardiovascular risk factors, comorbidities, disease severity, and delay to hospital presentation, the incidence of de novo heart failure at hospital presentation was significantly higher for women than for men (25.1% vs. 20.0%, odds ratio [OR]: 1.34; 95% confidence interval [CI]: 1.21 to 1.48). Women with de novo heart failure had higher 30-day mortality than did their male counterparts (25.1% vs. 20.6%; OR: 1.29; 95% CI: 1.05 to 1.58). The sex-related difference in mortality rates was still apparent in patients with de novo heart failure undergoing reperfusion therapy after hospital presentation (21.3% vs. 15.7%; OR: 1.45; 95% CI: 1.07 to 1.96). CONCLUSIONS Women are at higher risk to develop de novo heart failure after STEMI and women with de novo heart failure have worse survival than do their male counterparts. Therefore, de novo heart failure is a key feature to explain mortality gap after STEMI among women and men. (C) 2019 by the American College of Cardiology Foundation.

The usefulness of β-blockers has been questioned for patients who have hypertension without a prior manifestation of coronary heart disease or heart failure. In addition, sex-based differences in the efficacy of β-blockers for prevention of heart failure during acute myocardial ischemia have never been evaluated. We explored whether the effect of β-blocker therapy varied according to the sex among patients with hypertension who have no prior history of cardiovascular disease. Data were drawn from the ISACS (International Survey of Acute Coronary Syndromes)-Archives. The study population consisted of 13 764 patients presenting with acute coronary syndromes. There were 2590 patients in whom hypertension was treated previously with β-blocker (954 women and 1636 men). Primary outcome measure was the incidence of heart failure according to Killip class classification. Subsidiary analyses were conducted to estimate the association between heart failure and all-cause mortality at 30 days. Outcome rates were assessed using the inverse probability of treatment weighting and logistic regression models. Estimates were compared by test of interaction on the log scale. Among patients taking β-blockers before admission, there was an absolute difference of 4.6% between women and men in the rate of heart failure (Killip ≥2) at hospital presentation (21.3% versus 16.7%; relative risk ratio, 1.35 [95% CI, 1.10–1.65]). On the opposite, the rate of heart failure was approximately similar among women and men who did not receive β-blockers (17.2% versus 16.1%; relative risk ratio, 1.09 [95% CI, 0.97–1.21]). The test of interaction identified a significant ( P =0.034) association between sex and β-blocker therapy. Heart failure was predictive of mortality at 30-day either in women (odds ratio, 7.54 [95% CI, 5.78–9.83]) or men (odds ratio, 9.62 [95% CI, 7.67–12.07]). In conclusion, β-blockers use may be an acute precipitant of heart failure in new-onset coronary heart disease among women, but not men. Heart failure increases the risk of death. Registration URL: https://www.clinicaltrials.gov . Unique identifier: NCT04008173.

Survival analysis has attracted the development of new deep learning models, most notably the recent state-of-the-art model DeepHit for competing risks. However, in real-world medical settings with many features and insufficient data, deep learning models can suffer from severe performance deficits. In this dissertation, we propose robust changes to DeepHit’s architecture and training procedure to counter this problem. Furthermore, we develop several methods to improve DeepHit’s performance through novel approaches to automatic feature selection in deep survival analysis. We propose both filter and hybrid methods for hard feature selection, as well as neural network architecture adaptations that achieve soft feature selection. Despite only sparse literature around feature selection for deep neural networks, and little previous evidence for its benefits, our experiments on two medical datasets demonstrate that substantial performance improvements against the original DeepHit model are achievable.

Background: It remains uncertain whether female sex is itself a strong risk factor for worse outcomes in ACS. We hypothesized that sex differences in vulnerability to heart failure after ACS may modify the association between sex and outcomes Methods: Data were drawn from the ISACS-Archives network of registries (NCT04008173). The study population consisted of 87,812 patients with known time from symptom onset to hospital presentation. Participants were stratified by ACS subtypes: STEMI and NSTEACS Data on presenting heart failure symptoms were collected from medical record abstraction. Heart failure was categorized as Killip class >2. Time from symptom onset to hospital presentation was categorized as early (≤120 minutes) or late (>120 minutes). The primary outcome measure was 30-day mortality. Estimates were performed using a parametric balancing strategy by weighting and compared by test of interaction on the log scale Results: Among the study sample, 30922 (35.2%) patients were women. Patient outcomes varied according to subtype of ACS. The mortality rates at 30-days were significantly higher among women vs men in STEMI (RR:1.65; 95%CI: 1.56-1.73) compared with NSTEACS (RR:1.18; 95%CI: 1.09-1.28; P interaction

Background: Controversies persist about the role of statins in primary prevention of atherosclerotic cardiovascular disease (ASCVD). We sought to determine whether initiation of statin therapy for primary prevention of cardiovascular disease may lead to a reduction in cardiovascular outcomes across age, sex, and risk factors. Methods: We investigated 14,542 patients aged ≥40 years presenting to hospitals with ACS as first manifestation of cardiovascular disease from 2010 to 2019 in the ISACS Archives network of registries (NCT04008173). Individual risk of STEMI, acute heart failure (HF) on hospital admission and all-cause 30-day mortality were assessed using inverse probability of treatment weighting models matching for concomitant medications. Acute HF was defined as Killip class≥ 2. Estimates were compared by test of interaction on the log scale. Results: Among the study population 12.5% of patients were on statin therapy. Mean (SD) estimated 10-year risk for ASCVD was 25.8 (17.9) in statin users vs 22.5 (17.1) in non-users. The risk of STEMI was much lower in the statin-users than in the non-users (relative risk [RR] ratio 0.64; 95%CI 0.58-0.71). This effect persisted in both sexes, but was substantially stronger in men (absolute reduction: 11.5%; RR ratio: 0.61, 95%CI: 0.54-0.69) than in women (absolute reduction: 6.3%; RR ratio: 0.76, 95% CI: 0.64-0.90, p interaction=0.02). These benefits translated into reductions in acute HF on hospital admission with statin therapy for both women (RR ratio 0.66, 95%CI: 0.53-0.83) and men (RR ratio 0.74, 95%CI 0.62-0.89; p interaction=0.22). No effect on the rates of STEMI or acute HF was noted in patients with 10-year ASCVD risk lower than 10% for either sex. Acute HF was predictive of mortality at 30 days both in women and in men. Conclusion: Preventive statin therapy reduces the risk of STEMI as initial manifestation of cardiovascular disease and acute HF with potential benefits in mortality. The most gain is attained in male subjects with 10-year CV risk equal or more than 10%.