QTNet: Predicting Drug-Induced QT Prolongation With Artificial Intelligence-Enabled Electrocardiograms.

BACKGROUND: Prediction of drug-induced long QT syndrome (diLQTS) is of critical importance given its association with torsades de pointes. There is no reliable method for the outpatient prediction of diLQTS. OBJECTIVES: This study sought to evaluate the use of a convolutional neural network (CNN) applied to electrocardiograms (ECGs) to predict diLQTS in an outpatient population. METHODS: We identified all adult outpatients newly prescribed a QT-prolonging medication between January 1, 2003, and March 31, 2022, who had a 12-lead sinus ECG in the preceding 6 months. Using risk factor data and the ECG signal as inputs, the CNN QTNet was implemented in TensorFlow to predict diLQTS. RESULTS: Models were evaluated in a held-out test dataset of 44,386 patients (57% female) with a median age of 62 years. Compared with 3 other models relying on risk factors or ECG signal or baseline QTc alone, QTNet achieved the best (P < 0.001) performance with a mean area under the curve of 0.802 (95% CI: 0.786-0.818). In a survival analysis, QTNet also had the highest inverse probability of censorship-weighted area under the receiver-operating characteristic curve at day 2 (0.875; 95% CI: 0.848-0.904) and up to 6 months. In a subgroup analysis, QTNet performed best among males and patients ≤50 years or with baseline QTc <450 ms. In an external validation cohort of solely suburban outpatient practices, QTNet similarly maintained the highest predictive performance. CONCLUSIONS: An ECG-based CNN can accurately predict diLQTS in the outpatient setting while maintaining its predictive performance over time. In the outpatient setting, our model could identify higher-risk individuals who would benefit from closer monitoring.

A case report of sodium azide-induced myopericarditis.

Background: Sodium azide exposures are rare but can be lethal as the substance inhibits complex IV in the electron transport chain, blocking adenosine-triphosphate (ATP) synthesis. Sodium azide is mostly used as a propellant in vehicular airbags but is also used in laboratory, pharmacy, and industrial settings. No known antidote exists and its cardiotoxic effects are poorly described in the literature. Case summary: We describe the case of a 31-year-old patient with major depressive disorder presenting with altered mental status after ingestion of an unknown amount of sodium azide. Although initially chest pain free, she developed pleuritic chest pain 48 h after ingestion. This was accompanied by new diffuse ST elevations on the electrocardiogram and serum troponin elevations concerning for myopericarditis. Treatment was pursued with a 14-day course of colchicine resulting in complete symptom resolution within 4 days of treatment initiation. The patient's transthoracic echocardiogram was only notable for a preserved left ventricular ejection fraction (LVEF). Discussion: Cardiac toxicity after sodium azide ingestion usually occurs days after ingestion and has been previously described in the forms of heart failure with reduced ejection fraction complicated by cardiogenic shock. We describe the first case of sodium azide-induced myopericarditis with a preserved LVEF treated with colchicine. Colchicine is an established treatment for pericarditis, but its inhibition of endocytosis, an ATP-dependent cellular function, could be mechanistically relevant to this case.

Conduction velocity is reduced in the posterior wall of hypertrophic cardiomyopathy patients with normal bipolar voltage undergoing ablation for paroxysmal atrial fibrillation.

OBJECTIVES: We investigated characteristics of left atrial conduction in patients with HCM, paroxysmal AF and normal bipolar voltage. BACKGROUND: Patients with hypertrophic cardiomyopathy (HCM) exhibit abnormal cardiac tissue arrangement. The incidence of atrial fibrillation (AF) is increased fourfold in patients with HCM and confers a fourfold increased risk of death. Catheter ablation is less effective in HCM, with twofold increased risk of AF recurrence. The mechanisms of AF perpetuation in HCM are poorly understood. METHODS: We analyzed 20 patients with HCM and 20 controls presenting for radiofrequency ablation of paroxysmal AF normal left atrial voltage(> 0.5 mV). Intracardiac electrograms were extracted from the CARTO mapping system and analyzed using Matlab/Python code interfacing with Core OpenEP software. Conduction velocity maps were calculated using local activation time gradients. RESULTS: There were no differences in baseline demographics, atrial size, or valvular disease between HCM and control patients. Patients with HCM had significantly reduced atrial conduction velocity compared to controls (0.44 ± 0.17 vs 0.56 ± 0.10 m/s, p = 0.01), despite no significant differences in bipolar voltage amplitude (1.23 ± 0.38 vs 1.20 ± 0.41 mV, p = 0.76). There was a statistically significant reduction in conduction velocity in the posterior left atrium in HCM patients relative to controls (0.43 ± 0.18 vs 0.58 ± 0.10 m/s, p = 0.003), but not in the anterior left atrium (0.46 ± 0.17 vs 0.55 ± 0.10 m/s, p = 0.05). There was a significant association between conduction velocity and interventricular septal thickness (slope = -0.013, R2 = 0.13, p = 0.03). CONCLUSIONS: Atrial conduction velocity is significantly reduced in patients with HCM and paroxysmal AF, possibly contributing to arrhythmia persistence after catheter ablation.

RoBERTa-Assisted Outcome Prediction in Ovarian Cancer Cytoreductive Surgery Using Operative Notes.

INTRODUCTION: Contemporary efforts to predict surgical outcomes focus on the associations between traditional discrete surgical risk factors. We aimed to determine whether natural language processing (NLP) of unstructured operative notes improves the prediction of residual disease in women with advanced epithelial ovarian cancer (EOC) following cytoreductive surgery. METHODS: Electronic Health Records were queried to identify women with advanced EOC including their operative notes. The Term Frequency - Inverse Document Frequency (TF-IDF) score was used to quantify the discrimination capacity of sequences of words (n-grams) regarding the existence of residual disease. We employed the state-of-the-art RoBERTa-based classifier to process unstructured surgical notes. Discrimination was measured using standard performance metrics. An XGBoost model was then trained on the same dataset using both discrete and engineered clinical features along with the probabilities outputted by the RoBERTa classifier. RESULTS: The cohort consisted of 555 cases of EOC cytoreduction performed by eight surgeons between January 2014 and December 2019. Discrete word clouds weighted by n-gram TF-IDF score difference between R0 and non-R0 resection were identified. The words 'adherent' and 'miliary disease' best discriminated between the two groups. The RoBERTa model reached high evaluation metrics (AUROC .86; AUPRC .87, precision, recall, and F1 score of .77 and accuracy of .81). Equally, it outperformed models that used discrete clinical and engineered features and outplayed the performance of other state-of-the-art NLP tools. When the probabilities from the RoBERTa classifier were combined with commonly used predictors in the XGBoost model, a marginal improvement in the overall model's performance was observed (AUROC and AUPRC of .91, with all other metrics the same). CONCLUSION/IMPLICATIONS: We applied a sui generis approach to extract information from the abundant textual surgical data and demonstrated how it can be effectively used for classification prediction, outperforming models relying on conventional structured data. State-of-art NLP applications in biomedical texts can improve modern EOC care.

Reviewing the cardiovascular and other health effects of olive oil: Limitations and future directions of current supplement formulations.

AIMS: We reviewed the literature to date for high-level evidence on the cardiovascular and other health effects of olive oil with a focus on the amount, frequency of use and type of olive oil consumed in prior studies. A total of twelve prospective cohort studies with sample sizes of at least 4000 individuals and one meta-analysis were identified. DATA SYNTHESIS: The majority of cohorts followed individuals aged ≥55 years old, free of cardiovascular disease (CVD) at baseline but at high risk, over periods of 4-10 years and with daily consumption amounts of 10-35 g/day. With the exception of the PREDIMED cohort that employed extra virgin olive oil, most remaining studies did not differentiate between different types of olive oil. Taken together, the data suggests an association between greater olive oil consumption and a lower CVD incidence/mortality and stroke risk. We use this information to evaluate the use of commercially available, capsule-based olive oil dietary supplements and suggest future directions. Notably, achieving minimum total daily doses described in the aforementioned studies would be challenging with current market formulations of olive oil supplements dosed at 1-1.25 g/capsule. CONCLUSIONS: Outside of mechanistic studies, little progress has been made in determining the olive oil component(s) underlying the observed health effects given the lack of compositional reporting and consistency across large scale human studies. We propose the use of supplements of varying composition, such as varying total phenolic content, in pragmatic trial designs focused on low-cost methodologies to address this question.

Explainable SHAP-XGBoost models for in-hospital mortality after myocardial infarction.

Background: A lack of explainability in published machine learning (ML) models limits clinicians' understanding of how predictions are made, in turn undermining uptake of the models into clinical practice. Objective: The purpose of this study was to develop explainable ML models to predict in-hospital mortality in patients hospitalized for myocardial infarction (MI). Methods: Adult patients hospitalized for an MI were identified in the National Inpatient Sample between January 1, 2012, and September 30, 2015. The resulting cohort comprised 457,096 patients described by 64 predictor variables relating to demographic/comorbidity characteristics and in-hospital complications. The gradient boosting algorithm eXtreme Gradient Boosting (XGBoost) was used to develop explainable models for in-hospital mortality prediction in the overall cohort and patient subgroups based on MI type and/or sex. Results: The resulting models exhibited an area under the receiver operating characteristic curve (AUC) ranging from 0.876 to 0.942, specificity 82% to 87%, and sensitivity 75% to 87%. All models exhibited high negative predictive value ≥0.974. The SHapley Additive exPlanation (SHAP) framework was applied to explain the models. The top predictor variables of increasing and decreasing mortality were age and undergoing percutaneous coronary intervention, respectively. Other notable findings included a decreased mortality risk associated with certain patient subpopulations with hyperlipidemia and a comparatively greater risk of death among women below age 55 years. Conclusion: The literature lacks explainable ML models predicting in-hospital mortality after an MI. In a national registry, explainable ML models performed best in ruling out in-hospital death post-MI, and their explanation illustrated their potential for guiding hypothesis generation and future study design.

Development of an AI-Driven QT Correction Algorithm for Patients in Atrial Fibrillation.

BACKGROUND: Prolongation of the QTc interval is associated with the risk of torsades de pointes. Determination of the QTc interval is therefore of critical importance. There is no reliable method for measuring or correcting the QT interval in atrial fibrillation (AF). OBJECTIVES: The authors sought to evaluate the use of a convolutional neural network (CNN) applied to AF electrocardiograms (ECGs) for accurately estimating the QTc interval and ruling out prolongation of the QTc interval. METHODS: The authors identified patients with a 12-lead ECG in AF within 10 days of a sinus ECG, with similar (±10 ms) QRS durations, between October 23, 2001, and November 5, 2021. A multilayered deep CNN was implemented in TensorFlow 2.5 (Google) to predict the MUSE (GE Healthcare) software-generated sinus QTc value from an AF ECG waveform, demographic characteristics, and software-generated features. RESULTS: The study identified 6,432 patients (44% female) with an average age of 71 years. The CNN predicted sinus QTc values with a mean absolute error of 22.2 ms and root mean squared error of 30.6 ms, similar to the intrinsic variability of the sinus QTc interval. Approximately 84% and 97% of the model's predictions were contained within 1 SD (±30.6 ms) and 2 SD (±61.2 ms) from the sinus QTc interval. The model outperformed the AFQTc method, exhibiting narrower error ranges (mean absolute error comparison P < 0.0001). The model performed best for ruling out QTc prolongation (negative predictive value 0.82 male, 0.92 female; specificity 0.92 male, 0.97 female). CONCLUSIONS: A CNN model applied to AF ECGs accurately predicted the sinus QTc interval, outperforming current alternatives and exhibiting a high negative predictive value.

Temporal Trends and Sex Differences in Patients With Cardiac Amyloidosis and Heart Failure With Preserved Ejection Fraction: Retrospective Analysis of 22,015 Admissions From the National Inpatient Sample.

Cardiac amyloidosis (CA) often goes unrecognized as a cause of heart failure with preserved ejection fraction (HFpEF). There is paucity of contemporary data evaluating the trends of CA diagnosis and associated sex differences. Adult heart failure hospitalizations were identified from the National Inpatient Sample between 2016 and 2019. Hospitalizations with heart failure other than HFpEF were excluded. Hospitalizations with a diagnosis of CA were identified. A Linear regression was utilized to calculate the trend of CA diagnosis over time. A multivariate logistic regressions analysis was performed to analyze sex differences. There was an increasing trend of CA from 1.2 to 2.3 per 1000 HFpEF admission in the first quarter of 2016 to the fourth quarter of 2019 (Ptrend <0.001). In females, as compared to males, there was an increased risk of AIS (6% vs 3%, aOR: 1.68[1.24-2.27], P=0.001) and major bleeding events (10% vs 5%, aOR: 1.97[1.53-2.52], P<0.001). No difference was observed in the in-hospital mortality outcome (8% vs 7%, aOR: 1.2[0.95-1.53], P=0.12) between both groups. Our real-world contemporary analysis showed an increase in CA diagnosis from 2016 to 2019. Despite similar in-hospital mortality, females were associated with higher AIS and major bleeding events rates. Further prospective studies are needed to validate these results.

A case report of Enterobacter cloacae endocarditis in a patient with a history of cotton fever.

Background: Cotton fever is a self-limited, febrile syndrome occurring after the injection of trace amounts of drugs, in particular heroin, extracted from reused cotton filters. It is characterized by non-specific findings, such as fever, tachycardia, and leucocytosis. The leading pathophysiologic explanation suggests it is the result of direct inoculation of the bloodstream with endotoxins from Gram-negative bacilli of the genus Enterobacter, known to colonize all parts of the cotton plant. Only one prior case report has suggested cotton fever as a potential risk factor of infective endocarditis (IE). Case summary: We describe a case of a 57-year-old patient with a history of intravenous heroin use complicated by self-reported episodes of cotton fever. His presentation was notable for Enterobacter cloacae IE with bilateral septic pulmonary emboli. Transthoracic echocardiography findings included new tricuspid regurgitation and two mobile echodensities on the right atrial implantable cardioverter defibrillator (ICD) lead. Despite broad antibiotic coverage and extraction of the ICD leads, the patient passed away from septic shock. Discussion: The present case report is only the second published report of endocarditis in a patient with a history of cotton fever. In both cases, bacteria of the Enterobacter genus were isolated in patients' blood cultures. This evidence supports the endotoxin theory as the leading pathophysiologic explanation for cotton fever and suggests cotton fever as a risk factor for Gram-negative IE. In the inpatient setting it informs proper antibiotic coverage, whereas in the outpatient setting it supports harm reduction interventions in the form of sterile cotton balls.

A systematic review of the use of 3D printing in left atrial appendage occlusion procedures.

The placement of a left atrial appendage occlusion (LAAO) device can be a technically challenging transcatheter-based procedure. Key challenges include accurate pre-procedural device sizing and proper device positioning at the LAA ostium to ensure sufficient device anchoring and avoid peri-device leaks. To address these challenges, 3D printing (3DP) of LAA models has recently emerged in the literature, first being described in 2015. We present a review of the benefits and drawbacks of employing this technology for LAAO procedures. Pre-procedurally the use of 3DP can consistently and accurately determine LAAO device size over standard of care approaches. Intra-procedurally 3DP's impact entailed a statistically significant decrease in the number of devices used per procedure, as well as in the fluoroscopic time and dose. Post-procedurally, there is some evidence that 3DP could reduce the rate of peri-device leaks, with limited data on its effect on complication rates. Based on existing evidence, we recommend the focused application of 3DP to cases of complex LAA anatomy and for the training of proceduralists. Lastly, we address the emergence of next generation LAAO devices and AR/VR systems that could limit even this narrow window of clinical benefit afforded by 3DP.

Explainable Artificial Intelligence for Prediction of Complete Surgical Cytoreduction in Advanced-Stage Epithelial Ovarian Cancer.

Complete surgical cytoreduction (R0 resection) is the single most important prognosticator in epithelial ovarian cancer (EOC). Explainable Artificial Intelligence (XAI) could clarify the influence of static and real-time features in the R0 resection prediction. We aimed to develop an AI-based predictive model for the R0 resection outcome, apply a methodology to explain the prediction, and evaluate the interpretability by analysing feature interactions. The retrospective cohort finally assessed 571 consecutive advanced-stage EOC patients who underwent cytoreductive surgery. An eXtreme Gradient Boosting (XGBoost) algorithm was employed to develop the predictive model including mostly patient- and surgery-specific variables. The Shapley Additive explanations (SHAP) framework was used to provide global and local explainability for the predictive model. The XGBoost accurately predicted R0 resection (area under curve [AUC] = 0.866; 95% confidence interval [CI] = 0.8−0.93). We identified "turning points" that increased the probability of complete cytoreduction including Intraoperative Mapping of Ovarian Cancer Score and Peritoneal Carcinomatosis Index < 4 and <5, respectively, followed by Surgical Complexity Score > 4, patient's age < 60 years, and largest tumour bulk < 5 cm in a surgical environment of optimized infrastructural support. We demonstrated high model accuracy for the R0 resection prediction in EOC patients and provided novel global and local feature explainability that can be used for quality control and internal audit.

Standardized User-Independent Confocal Microscopy Image Acquisition and Analysis for Thickness Measurements of Microscale Collagen Scaffolds.

The ability to accurately and precisely measure the thickness of biomaterial constructs is critical for characterizing both specific dimensional features and related mechanical properties. However, in the absence of a standardized approach for thickness measurements, a variety of imaging modalities have been employed, which have been associated with varying limits of accuracy, particularly for ultrathin hydrated structures. Electron microscopy (EM), a commonly used modality, yields thickness values for extensively processed and nonhydrated constructs, potentially resulting in overestimated mechanical properties, including elastic modulus and ultimate tensile strength. Confocal laser scanning microscopy (CLSM) has often been used as a nondestructive imaging alternative. However, published CLSM-derived image analysis protocols use arbitrary signal intensity cutoffs and provide minimal information regarding thickness variability across imaged surfaces. To address the aforementioned limitations, we present a standardized, user-independent CLSM image acquisition and analysis approach developed as a custom ImageJ macro and validated with collagen-based scaffolds. In the process, we also quantify thickness discrepancies in collagen-based scaffolds between CLSM and EM techniques, further illustrating the need for improved strategies. Employing the same image acquisition protocol, we also demonstrate that this approach can be used to estimate the surface roughness of the same scaffolds without the use of specialized instrumentation.

Preventable Morbidity and Mortality Among Non-trauma Emergency Surgery Patients: The Role of Personal Performance and System Flaws in Adverse Events.

BACKGROUND: Preventable morbidity and mortality among emergency surgery patients is not adequately analyzed. We aim to describe and classify preventable complications and deaths in this population. METHODS: The medical records and quality control documents of patients with emergency, non-trauma, surgical disease admitted between September 1, 2006, and August 31, 2018, and recorded to have a preventable or potentially preventable morbidity and mortality were reviewed. The primary outcome was a classification of the complications and deaths by a panel of experts, as attributable to issues of personal performance or system deficiencies. RESULTS: One hundred and fifty patients were identified (127 complications and 23 deaths). The most commonly encountered preventable complications were surgical-site infection (17%), bleeding (13%), injury to adjacent structures (12%), and anastomotic leak (8%). The majority of complications seemed to stem from personal performance (97%), due to either technical or judgment issues, and only 3% were linked with system flaws, either in the form of communication or inadequate protocols. Alcohol use disorder and duration of operation were different between patients with preventable adverse events related to technical issues and patients related to judgment issues; furthermore, more patients who experienced judgment issues died during hospital stay (p <0.05). CONCLUSION: Among emergency surgery patients, who suffer preventable complications and deaths, issues related to personal performance are more frequent than system flaws. Whereas the effort to improve systems should be unwavering, the emphasis on the surgeon's personal responsibility to avoid preventable complications should not be derailed.

Continuous Formation of Ultrathin, Strong Collagen Sheets with Tunable Anisotropy and Compaction.

The multiscale organization of protein-based fibrillar materials is a hallmark of many organs, but the recapitulation of hierarchal structures down to fibrillar scales, which is a requirement for withstanding physiological loading forces, has been challenging. We present a microfluidic strategy for the continuous, large-scale formation of strong, handleable, free-standing, multicentimeter-wide collagen sheets of unprecedented thinness through the application of hydrodynamic focusing with the simultaneous imposition of strain. Sheets as thin as 1.9 µm displayed tensile strengths of 0.5-2.7 MPa, Young's moduli of 3-36 MPa, and modulated the diffusion of molecules as a function of collagen nanoscale structure. Smooth muscle cells cultured on engineered sheets oriented in the direction of aligned collagen fibrils and generated coordinated vasomotor responses. The described biofabrication approach enables rapid formation of ultrathin collagen sheets that withstand physiologically relevant loads for applications in tissue engineering and regenerative medicine, as well as in organ-on-chip and biohybrid devices.

Preoperative anemia displays a dose-dependent effect on complications in head and neck oncologic surgery.

INTRODUCTION: Anemia's effect on head and neck surgical complications is unknown. METHODS: Head and neck cancer operations were acquired from the 2006 to 2013 American College of Surgeons National Surgical Quality Improvement Program databases. Anemia was defined as <39% or <36% hematocrit in men and women, respectively. Multivariable logistic regression analyses were performed. RESULTS: Major head and neck surgery patients had a 44.2% anemia incidence (n = 527 of 1193). Anemic patients had increased complication rates (27.1%) and mortality (2.1%) vs non-anemic patients at 19.8% (P = .003) and 0.5% (P = .009), respectively. There was a significant difference in morbidity odds with hematocrit >27% (odds ratio [OR] = 1.09) vs <27% (OR = 4.22). Complication odds were further increased with hematocrit between 24% and 27% (OR = 8.94). There were increased rates of wound dehiscence (6.6% vs 2.7%, P < .001), pneumonia (8.5% vs 4.7%, P = .006), and myocardial infarction (1.7% vs 0.3%, P = .01) in anemic vs non-anemic patients. CONCLUSION: Anemia was associated with increased morbidity at hematocrit <27%. An inverse dose-dependent effect of decreasing hematocrit was observed for overall morbidity.

Bilateral mastectomies: can a co-surgeon technique offer improvements over the single-surgeon method?

PURPOSE: Bilateral mastectomy (BM) is traditionally performed using a single-surgeon (SS) technique (SST); a co-surgeon (CS) technique (CST), where each attending surgeon concurrently performs a unilateral mastectomy, offers an alternative approach. We sought to compare the CST and SST for BM with respect to operative times and complications. METHODS: Patients undergoing BM without reconstruction at our institution between 2005 and 2015 were identified using operative caselogs and stratified into CS- and SS-cohorts. Operative time (OT; incision to closure) was calculated. Patient age, cancer presence/stage, hormone receptor/BRCA status, breast weight, axillary procedure, and 30-day complications were extracted. Differences in OT, complications, and demographics between cohorts were assessed with t tests and Chi-square tests. A multivariate linear regression model was fit to identify factors independently associated with OT. RESULTS: Overall, 109 BM cases were identified (CS, n = 58 [53.2%]; SS, n = 51 [46.8%]). Average duration was significantly shorter for the CST by 33 min (21.6% reduction; CS: 120 min vs. SS: 153 min, p < 0.001), with no difference in complication rates (p = 0.65). Demographic characteristics did not differ between cohorts except for total breast weight (TBW) (CS: 1878 g vs. SS: 1452 g, p < 0.05). Adjusting for TBW, CST resulted in a 27.8% reduction in OT (44-min savings, p < 0.001) compared to SST. CONCLUSIONS: The CST significantly reduces OT for BM procedures compared to the SST without increasing complication rates. While time-savings was < 50% and may not be ideal for every patient, the CST offers an alternative BM approach potentially best-suited for large TBW patients and those undergoing axillary procedures.

Intraoperative cardiac arrest etiologies in head and neck surgery: A comprehensive review.

BACKGROUND: The etiologies of intraoperative cardiac arrest within otolaryngology are not well understood as they are rare events. METHODS: A comprehensive review of the etiologies and corresponding pathophysiologic neural mechanisms of intraoperative cardiac arrest in otolaryngologic surgery are examined. RESULTS: The occurrence of this rare complication has been described in a range of head and neck procedures, including but not limited to suspension laryngoscopy and oncologic resections in the neck, maxilla and thyroid. Three anatomically distinct pathways leading to intraoperative cardiac arrest are described: direct vagal stimulation, the trigeminocardiac reflex and the baroreceptor reflex. All three share the final common pathway of parasympathetic signaling to the sinoatrial node via the cardiac fibers of the vagus nerve. CONCLUSION: With a firm understanding of the mechanistic underpinning of this rare phenomenon, otolaryngologic surgeons can be better prepared for its occurrence.