Citations

Abstract Aims Left ventricular hypertrophy (LVH) is a strong predictor of cardiovascular disease. We previously compared supervised machine learning techniques to classify cardiac magnetic resonance (CMR)-derived LVH using electrocardiogram (ECG) and clinical variables in 37 534 UK Biobank participants, obtaining an area under the receiving operating curve (AUROC) of 0.85, but with limited specificity and requiring external validation. In this study, we develop a deep learning (DL) model to improve classification with external evaluation in the Study of Health in Pomerania (SHIP). Methods and results We analysed 12-lead ECGs of 48 835 participants from the UK Biobank imaging study. The dataset was split into a training set (70%), validation set (15%), and test set (15%) for performance evaluation. The model architecture was a fully convolutional network, for which the input was the participants’ median ECG and clinical variables and the predicted indexed left ventricular mass (iLVM) as the output. A subsequent logistic regression model was used to recalibrate iLVM predictions. In UK Biobank, 717 (1.5%) participants had CMR-derived LVH and the AUROC for the DL model was 0.97. The ECG components most predictive of LVH were the QRS complex and ventricular rate. The DL model outperformed our supervised algorithms, previous DL modelling efforts and clinical ECG benchmarks. There was modest generalizability of the DL model to 1423 participants in SHIP (AUROC 0.78), with differences in clinical profile, ECG acquisition, and CMR labelling as important factors. Conclusion Our findings support the feasibility of scalable DL-based screening tools for the prediction of LVH from the ECG, whilst highlighting the need for model development using larger datasets with greater diversity to ensure generalizability.

Background: For women in the United States desiring implant-based breast reconstruction, the maximum volume of commercially available silicone breast implants has, to date, been 800 cc. The authors evaluated the safety of Mentor larger-size MemoryGel Ultra-High Profile breast implants (≥930 cc) in women undergoing postmastectomy breast reconstruction. Methods: This 10-year, multicenter, open-label, prospective, investigational study assessed the safety and effectiveness of larger-volume implants in women undergoing postmastectomy 2-stage primary or revision reconstruction. Three-year Kaplan-Meier curves and multivariable Cox regression analyzed the association between patient and treatment characteristics and surgical outcomes. The BREAST-Q was used to assess effectiveness at 3 years. Results: A total of 400 women were enrolled (225 primary and 175 revision reconstruction). Mean body mass index was 35.8 kg/m 2 ; 81% had a body mass index greater than or equal to 30 kg/m 2 . At 3 years, the cumulative incidence of postoperative complications (excluding rupture) was 63.0% (95% confidence interval, 58.1% to 67.9%). The reoperation rate was 24.5% (95% CI, 20.4% to 29.1%), and the explantation rate was 15.8% (95% CI, 23.5% to 19.9%). Independent predictors of complications included radiation therapy and a history of smoking. There were no significant associations between postoperative complications and implant volume greater than or equal to 1135 cc or less than 1135 cc. BREAST-Q scores at year 3 showed significant improvements from baseline in Satisfaction with Breasts, Psychosocial Well-Being, Sexual Well-Being, and Physical Well-Being (all P < 0.0001). The mean score for Satisfaction with Outcome was 79.9. Conclusions: These 3-year results demonstrate that larger-volume silicone breast implants represent a safe and effective option for patients with larger breasts who are requesting postmastectomy implant-based reconstruction.

OBJECTIVE Brain metastases significantly impact neurocognitive function and overall survival. Stereotactic radiosurgery (SRS) is a cornerstone of treatment for patients with limited metastases and expected survival beyond 3 months. Despite current guidelines, up to 20% of patients with brain metastases undergoing SRS have been reported to die within 90 days. This study retrospectively evaluated prognostic factors associated with 90-day survival after SRS, aiming to improve patient selection. METHODS The authors retrospectively analyzed a cohort of 1546 patients who underwent Gamma Knife SRS for brain metastases at their institution between 2015 and 2023. One hundred seventy patients who survived less than 90 days after SRS were identified and case matched to 170 patients who survived over 90 days. Measured variables included patient demographic characteristics, tumor characteristics, treatment history, functional status, and control of the primary cancer. The authors modeled post-SRS 90-day survival using binomial and multivariate logistic regression. RESULTS Multivariate analysis highlighted Karnofsky Performance Score (KPS) < 70 (OR 17.4, p < 0.001), prior whole-brain radiation (OR 6, p = 0.004), and focal neurological deficits (OR 3.02, p = 0.003) as significant predictors of poor survival, whereas CNS progression before SRS (OR 0.22, p < 0.001) and control of systemic cancer (OR 0.556, p = 0.002) were associated with survival < 90 days. The predictive model demonstrated acceptable performance with an area under the curve (AUC) of 0.85, accuracy of 80%, sensitivity of 87%, and specificity of 71%. CONCLUSIONS Key predictors of 90-day survival after SRS for brain metastases include functional status (KPS), control of systemic cancer, CNS progression status, and focal neurological deficits. These findings are complementary factors that can assist in making decisions and SRS patient selection.

Coronary artery spasm (CAS) is a dynamic vasomotor disorder characterized by transient, intense constriction of epicardial coronary arteries, leading to myocardial ischemia in patients with and without obstructive coronary artery disease. CAS plays a central role in vasospastic angina, ischemia with nonobstructive coronary arteries and myocardial infarction with nonobstructive coronary arteries, malignant arrhythmias, and sudden cardiac death. Its pathophysiology is multifactorial, involving endothelial dysfunction, vascular smooth muscle hyperreactivity, inflammation, oxidative stress, autonomic imbalance, and genetic susceptibility, with notable ethnic and sex-related differences. Diagnosis relies on integration of clinical features, electrocardiographic changes, and invasive coronary provocation testing using acetylcholine or ergonovine, supported by advanced imaging and functional assessment when microvascular involvement is suspected. Management is centered on calcium channel blockers and nitrates, aggressive risk factor modification, particularly smoking cessation, and individualized strategies for refractory or high-risk patients. Improved recognition and standardized diagnostic pathways are essential to optimize outcomes and reduce life-threatening complications associated with CAS.

Shock is a life-threatening state of circulatory failure characterized by inadequate tissue oxygen delivery and cellular hypoxia. Lactate has emerged as a central biomarker in the diagnosis, risk stratification, and management of shock, yet its interpretation is complex and context dependent. Although traditionally viewed as a marker of anaerobic metabolism and tissue hypoperfusion, hyperlactatemia in distributive shock, particularly sepsis, frequently reflects multifactorial mechanisms, including increased aerobic glycolysis, adrenergic stimulation, mitochondrial dysfunction, and impaired hepatic clearance. This review examines the pathophysiology and classification of shock, the biochemical basis of lactate production and clearance, and the prognostic significance of both static lactate levels and lactate kinetics. We synthesize evidence supporting lactate as a robust prognostic marker while highlighting limitations of lactate-targeted resuscitation strategies. Emerging data favor multimodal approaches integrating lactate trends with complementary perfusion markers such as capillary refill time and central venous oxygen saturation. Lactate should be interpreted as one component of a comprehensive physiological assessment rather than an isolated therapeutic target.

INTRODUCTION: Clostridioides difficile infection (CDI) presents a significant challenge in patients with inflammatory bowel disease (IBD), with high recurrence rates and complications. Predicting recurrent CDI (rCDI) in patients with IBD is crucial for implementing targeted interventions to improve patient outcomes. This study aimed to develop and validate a predictive model (RecurCDI-IBD) using supervised machine learning to identify patients with IBD at high risk of developing rCDI. METHODS: Data were collected from adult patients with IBD diagnosed with CDI between 2013 and 2021. Inclusion criteria included adult patients with a confirmed diagnosis of CDI and a history of IBD. The Gradient Boosting Machine learning model (XGBoost) was used to train a binary classification model. Feature engineering included demographic data (age and sex), clinical data (IBD subtype, medication use, and comorbidities), and laboratory data. The primary outcome was the occurrence of rCDI within 60 days of the initial CDI episode. RESULTS: The RecurCDI-IBD model achieved an accuracy of 80.05% and an Area Under the Curve of 0.88 for predicting rCDI. Key predictive features included IBD subtype, sex, specific medications (such as steroids and anti-TNF agents), and comorbidities (such as chronic pulmonary and renal disease). DISCUSSION: The RecurCDI-IBD model demonstrates good discriminatory ability with balanced precision and recall in identifying patients with IBD at higher risk for rCDI. These findings highlight the potential of data-driven approaches to support clinical risk assessment. Further studies incorporating larger and more diverse cohorts and prospective external validation are needed to confirm generalizability and optimize clinical applicability.

Ameloblastomas are locally aggressive odontogenic tumors that most commonly arise in the mandible and maxilla and often harbor BRAF V600E mutations. While rare extragnathic ameloblastomas have been reported, primary pulmonary cases have not been documented. We identified 3 pulmonary neoplasms with features of ameloblastoma that were submitted for consultation between 2022 and 2025 at 3 academic institutions and performed detailed clinicopathologic and molecular analysis. The tumors presented as 5.4 to 7.3 cm peribronchial solitary lung masses. All resected tumors exhibited a predominant stellate reticulum-like component composed of loosely arranged p40-reactive bland squamoid-to-spindled cells with long intercellular bridges, and streaming and swirling architecture, surrounded by palisaded columnar cells with focal reverse nuclear polarity at the interface with myxoid stroma. All tumors were immunoreactive for BRAF V600E IHC, and BRAF V600E mutations were confirmed by molecular assays, including broad next-generation sequencing on 2 cases. Florid hyperplasia of entrapped pneumocytes initially suggested a biphasic neoplasm, but the absence of BRAF V600E IHC labeling confirmed pneumocyte entrapment. Occult gnathic primary tumors were excluded by subsequent clinical examination, including negative panoramic dental x-rays. No recurrences or metastases have been observed to date. This first series of primary pulmonary ameloblastomas highlights a distinctive tumor with histologic and molecular features identical to gnathic counterparts. We discuss the potential histogenesis of these unusual tumors.

OBJECTIVE: Volatile anesthetics (VAs) are gaining renewed interest as a sedation strategy in the intensive care, offering an alternative to traditional IV agents. VAs provide several pharmacologic advantages, including rapid onset and offset, minimal systemic metabolism, and favorable recovery profiles. Advances in delivery systems enabled the safe and practical administration of volatile agents in the ICU. Thus, we aimed to describe the pharmacology and safety aspects of inhaled agents as well as the systems designed to deliver VAs in the ICU. DATA SOURCES: Relevant literature was identified through PubMed and MEDLINE databases. STUDY SELECTION: Original research, review articles, commentaries, and guidelines addressing safety, efficacy, and use of VAs in adult ICU patients were included. DATA EXTRACTION: Studies were reviewed by the authors, with key findings summarized and organized by pharmacologic properties, delivery systems, and safety domains. DATA SYNTHESIS: VAs are halogenated hydrocarbons whose mechanism of action is not fully understood. Although the CNS is the primary site of action, the end-tidal concentration of exhaled anesthetic is used to monitor clinical effects such as immobility to a noxious stimulus. Inhaled agents have unique pharmacokinetics, minimal metabolisms, and distinct recovery. The side effect profile is also unique, with malignant hyperthermia being the most feared, yet rare complication. Two systems for inhalational sedation delivery are available internationally, with one currently under evaluation in the United States. The systems are composed of a miniature vaporizer, delivery controller, and a monitor. The systems have distinct safety considerations, such as tidal volume limits. CONCLUSIONS: VAs can be used as sedative agents in the ICU. This article comprehensively reviews the pharmacology of VAs along with their safety profile and describes the structure and function of miniature vaporizers currently available on the world market.

Abstract Objective To measure the relative levels of signal and noise in expert diagnosis of epilepsy. Methods Twenty multinational epileptologists independently reviewed 50 vignettes of adult and pediatric patients presenting with suspected seizure(s) on two separate occasions with a ≥30‐day washout period. Experts provided a diagnosis of epilepsy or non‐epilepsy based on clinical information and, if requested, routine EEG and neuroimaging data. Cases had an established clinical diagnosis of epilepsy or non‐epilepsy based on capture of habitual paroxysmal events on video‐EEG or long‐term clinical follow‐up. Experts' judgments were analyzed to decompose variability into different sources: signal (objective differences between cases), level noise (experts' bias toward over/under‐diagnosis), pattern noise (experts' idiosyncratic reactions to specific case features), and occasion noise (inconsistency across occasions). Results The probability of an expert making a different diagnosis for a given case on two different occasions was 16%. The probability of two different experts making a different diagnosis for the same case was 26%. Signal (case “difficulty”) accounted for 66–69% of total variation, with 31–34% attributable to noise. Level noise was the largest contributor in the absence of EEG/neuroimaging results (23%), while pattern noise dominated when test results were available (24%). Occasion noise contributed relatively little (1%) but was still sufficient to cause diagnostic reversals in 16–22% between occasions. Significance The degree of noise in expert diagnosis of epilepsy is substantial, stemming primarily from physicians' idiosyncratic interpretations of case features and variable dispositions toward over‐ or under‐diagnosis. Strategies to improve reliability are needed, including standardized data collection protocols and structured decision algorithms. For “difficult cases,” where expert reliability and accuracy are lowest, our findings support current clinical practice which favors early referral for video‐EEG monitoring over reliance on diagnostic anchoring. This diagnostic pathway may become more accessible with advances in EEG technology (e.g., wearable devices) and artificial intelligence.