Abstract Background Atrial fibrillation (AF) and heart failure (HF) frequently coexist, share overlapping pathophysiologic mechanisms and a bidirectional causal relationship. Their concurrence is associated with worse clinical outcomes. Early detection of AF in HF patients may offer timely interventions and improve outcomes. Purpose To develop and validate an AF detection algorithm based on machine-learning analysis of photoplethysmography (PPG) signals, integrated into a CE-certified (MDR IIb) HF telemonitoring platform. Methods We included 247 HF patients (43627 individual PPG recordings, mean age 65.3 ± 11.8 years; 33.6% female, predominantly NYHA class: II 54.1% and III 26.0%, 49% non-ischemic etiology, HFpEF 32.8%, HFmrEF 16.2%, HFrEF 47.0%) from an ongoing telemonitoring study, STOP-DHF (Strategy TO Prevent Decompensated HF). Patients were classified into two groups based on ECG and clinical data: (1) permanent AF , defined as history of permanent AF together with documented AF on a 12-lead (n = 47; 7423 PPG recordings); and (2) non-AF , defined as sinus rhythm on the index 12-lead ECG with no prior documented AF episodes (n = 200; 35,844 PPG recordings). External validation was performed on 936 PPG recordings from 167 patients, combining data from the MIMIC database (n=35; 683 PPGs) and cardiology outpatients (n=132; 253 PPGs). A second validation used a proprietary dataset (n=21; 51 PPG–ECG pairs) with frequent irregular extrasystoles. A third patient-level validation included proprietary PPG–ECG pairs from a patient with frequent sinus–AF transitions. Fifteen waveform features were extracted, including heart rate statistics, time- and frequency-domain heart rate variability measures, count-based variability indices, and autocorrelation descriptors reflecting rhythm irregularity. Three algorithms (logistic regression, random forest, and LightGBM) were trained and compared using stratified five-fold cross-validation. Results The LightGBM classifier demonstrated the best overall performance. In 5-fold internal cross-validation, the model achieved a mean ROC AUC = 0.98 ± 0.01, mean average precision 0.96 ± 0.04, sensitivity 0.96 ± 0.02 and specificity 0.97 ± 0.02 at the Youden threshold. In external validation, it reached AUC = 0.99 (95% CI: 0.98–1.00) and average precision of 0.98, with sensitivity 0.97 (CI: 0.94-0.98) and specificity 0.93 (CI: 0.91-0.95) at the Youden threshold. In the extrasystolic validation, specificity remained high (0.94; 95% CI: 0.84–0.98) with a low false-positive rate 0.06, despite frequent irregular ectopy. A third patient-level validation confirmed accurate discrimination during frequent sinus–AF transitions (figure 2). Conclusions Our PPG-based AF detection algorithm demonstrated high and consistent performance across internal, external, and patient-level validations. Its integration into HF telemonitoring platform could enable early AF recognition.Figure 1Figure 2
The therapeutic landscape of metastatic castration-resistant prostate cancer (mCRPC) has evolved substantially over the past decade with the integration of androgen receptor signaling inhibitors (ARSI), taxane chemotherapy, radioligand therapy, and molecularly targeted agents. Among the most relevant recent developments is the combination of poly(ADP-ribose) polymerase inhibitors (PARPi) with ARSI in the first-line mCRPC setting. This strategy is supported by a strong biological rationale, as androgen receptor signaling interacts with DNA damage repair pathways, and AR blockade may induce a “BRCAness” phenotype that enhances tumor sensitivity to PARP inhibition [1, 2]. Randomized phase III trials, including PROpel, MAGNITUDE, and TALAPRO‑2, have consistently demonstrated significant improvements in radiographic progression-free survival (rPFS) with PARPi–ARSI combinations [3–5]. However, overall survival (OS) outcomes remain heterogeneous and appear to depend largely on homologous recombination repair (HRR) mutation status. Patients with BRCA 1/2 alterations derive the most pronounced benefit, whereas evidence supporting use in unselected populations remains inconsistent, with no uniform demonstration of OS improvement [6, 7]. In addition, combination therapy is associated with increased hematologic toxicity, raising concerns regarding overtreatment in biologically less responsive subgroups. Taken together, current data support a biomarker-driven approach, positioning PARPi plus ARSI as a standard option for HRR-mutated mCRPC, while a generalized treatment strategy for all patients remains uncertain.
BACKGROUND: Short dual antiplatelet therapy (DAPT) followed by ticagrelor monotherapy may be a valuable therapeutic option for patients with chronic coronary syndrome (CCS) and high ischaemic risk (HIR) undergoing percutaneous coronary intervention (PCI). AIMS: We aimed to compare ticagrelor monotherapy with ticagrelor-based DAPT in CCS patients with and without HIR undergoing PCI. METHODS: The present analysis included the CCS cohort of the TWILIGHT trial, which randomised PCI patients to ticagrelor alone or in combination with aspirin for 12 months after 3 months of ticagrelor-based DAPT. Patients were stratified into HIR and non-HIR based on the 2019 European Society of Cardiology (ESC) CCS guidelines definition. Outcomes of interest were major adverse cardiac and cerebrovascular events (MACCE), a composite of death, myocardial infarction or stroke, and Bleeding Academic Research Consortium (BARC) Type 2-5 bleeding at 1 year. RESULTS: Of the 2,503 CCS patients who underwent randomisation, the ESC definition classified 1,264 (50.5%) as HIR and 1,239 (49.5%) as non-HIR. HIR patients displayed a higher risk of MACCE (3.9% vs 2.3%; p=0.015) and similar rates of BARC Type 2-5 bleeding (5.1% vs 5.7%; p=0.455) as compared to non-HIR patients. Ticagrelor monotherapy and ticagrelor-based DAPT were associated with similar risks of MACCE (HIR: 4.0% vs 3.8%, hazard ratio [HR] 1.06, 95% confidence interval [CI]: 0.60-1.85; non-HIR: 2.1% vs 2.6%, HR 0.80, 95% CI: 0.38-1.66, pinteraction=0.553) and bleeding (HIR: 4.7% vs 5.7%, HR 0.82, 95% CI: 0.50-1.33; non-HIR: 4.9% vs 6.7%, HR 0.71, 95% CI: 0.44-1.14; pinteraction=0.684) in both the HIR and non-HIR groups. CONCLUSIONS: In a post hoc analysis of the TWILIGHT trial that included CCS patients undergoing PCI, ticagrelor monotherapy after 3 months of DAPT appeared to be safe and was not associated with increased risks of ischaemic or bleeding events, regardless of baseline HIR status, compared with standard ticagrelor-based DAPT. These findings suggest the potential to expand guideline recommendations for ticagrelor monotherapy in CCS.
Breast reconstruction is an option for women after breast cancer surgery to improve the quality of life. While data about satisfaction after reconstruction are available, little is known about the decision process and about factors shaping this process. From 100 selected women, 72 women between 30 and 65 years of age (median 50.3 years, interquartile range 44–57 years) with breast reconstruction conducted in a single center in Vienna (Austria) consented to take part in this study. The role of family, social environment and healthcare providers during decision making, body image, thoughts about hospital stay and potential complications were assessed by a questionnaire. The decision for autologous tissue versus silicone implants was analyzed by structural equation modelling. Overall, 69
Aims Cardiogenic shock (CS) is a severe complication of acute coronary syndrome (ACS) with mortality rates approaching 50%. The ability to identify high-risk patients prior to the development of CS may allow for pre-emptive measures to prevent the development of CS. The objective was to derive and externally validate a simple, machine learning (ML)-based scoring system using variables readily available at first medical contact to predict the risk of developing CS during hospitalization in patients with ACS.Methods and results Observational multicentre study on ACS patients hospitalized at intensive care units. Derivation cohort included over 40 000 patients from Beth Israel Deaconess Medical Center, Boston, USA. Validation cohort included 5123 patients from the Sheba Medical Center, Ramat Gan, Israel. The final derivation cohort consisted of 3228 and the final validation cohort of 4904 ACS patients without CS at hospital admission. Development of CS was adjudicated manually based on the patients' reports. From nine ML models based on 13 variables (heart rate, respiratory rate, oxygen saturation, blood glucose level, systolic blood pressure, age, sex, shock index, heart rhythm, type of ACS, history of hypertension, congestive heart failure, and hypercholesterolaemia), logistic regression with elastic net regularization had the highest externally validated predictive performance (c-statistics: 0.844, 95% CI, 0.841-0.847).Conclusion STOP SHOCK score is a simple ML-based tool available at first medical contact showing high performance for prediction of developing CS during hospitalization in ACS patients. The web application is available at https://stopshock.org/#calculator.
