Opportunistic detection of type 2 diabetes using deep learning from frontal chest radiographs.

Deep learning (DL) models can harness electronic health records (EHRs) to predict diseases and extract radiologic findings for diagnosis. With ambulatory chest radiographs (CXRs) frequently ordered, we investigated detecting type 2 diabetes (T2D) by combining radiographic and EHR data using a DL model. Our model, developed from 271,065 CXRs and 160,244 patients, was tested on a prospective dataset of 9,943 CXRs. Here we show the model effectively detected T2D with a ROC AUC of 0.84 and a 16% prevalence. The algorithm flagged 1,381 cases (14%) as suspicious for T2D. External validation at a distinct institution yielded a ROC AUC of 0.77, with 5% of patients subsequently diagnosed with T2D. Explainable AI techniques revealed correlations between specific adiposity measures and high predictivity, suggesting CXRs' potential for enhanced T2D screening.

Incidence of tissue coring during transseptal catheterization when using electrocautery and a standard transseptal needle.

BACKGROUND: The application of radiofrequency electrocautery to a standard, open-ended transseptal needle has been used to facilitate transseptal puncture (TSP). The purpose of this study was to determine the incidence of cardiac tissue coring when this technique is used. METHODS AND RESULTS: A model using excised swine hearts submerged in a saline-filled basin was developed to simulate TSP with electrocautery and a standard transseptal needle. Punctures were performed without the use of electrocautery and by delivering radiofrequency energy to the transseptal needle using a standard electrocautery pen at 3 target sites (fossa ovalis, non-fossa ovalis septum, and aorta). The tissue of the submerged heart was gently tented, and the needle was advanced on delivery of radiofrequency. The devices were retracted, and the needle was flushed in a collection basin. None of the TSPs without cautery caused tissue coring. For TSPs using electrocautery, the frequency of coring was at least 21% for any puncture permutation used in the study and averaged 37% at septal sites (P<0.001 compared with punctures without cautery). Tissue coring occurred in 33 of 96 (35%) punctures through the fossa ovalis and in 38 of 96 (40%) punctures through non-fossa ovalis septum. The frequency of tissue coring at aortic sites was 62 of 96 (65%), which was significantly higher than at the septal sites (P<0.001). CONCLUSIONS: In an animal preparation, TSP at the level of the fossa ovalis using electrocautery and a standard open-ended Brockenbrough needle resulted in coring of the septal tissue in 35% of cases (33 of 96 punctures).

Implications of progressive aberrancy versus true fusion for diagnosis of wide complex tachycardia.

At the onset of wide complex tachycardia, beats with intermediate morphologies sometimes occur between the normally conducted beats and the wide complex tachycardia QRS. Intermediate beats could be true fusion; however, progressive aberrancy has been reported to mimic true fusion. To evaluate the incidence of progressive aberrancy, wide complex tachycardia tracings were collected in which an intermediate beat was noted at the onset. When the associated electrocardiographic findings were diagnosed as supraventricular tachycardia, the beat was identified as progressive aberrancy. When diagnosed as ventricular tachycardia, the intermediate beat was identified as true fusion. Electrocardiographic criteria were then identified from this cohort to identify the distinguishing features between progressive aberrancy and true fusion. Of 24 episodes of wide complex tachycardia, 17 (71%) were identified as true fusion and 7 (29%) as progressive aberrancy. The QRS duration of the intermediate and wide complex tachycardia beats were shorter with progressive aberrancy than with true fusion (109 ± 23 ms vs 131 ± 20 ms, p <0.023; and 139 ± 21 ms vs 177 ± 24 ms, p <0.001, respectively). In progressive aberrancy (n = 3), the PR interval of the intermediate beat was always greater than the PR interval of the normally conducted beat. In contrast, in true fusion (n = 11), the PR interval of the intermediate beat was always less than the PR interval of the normally conducted beat. Multiple intermediate beats were present in 4 of 7 cases of progressive aberrancy and in 0 of 17 cases of true fusion. In conclusion, true fusion is the most common explanation for intermediate beats, but progressive aberrancy occurs a significant proportion of the time (29%). The identified criteria will be helpful in differentiating ventricular tachycardia from supraventricular tachycardia with aberrancy as a cause of wide complex tachycardia.

Head CT is of limited diagnostic value in critically ill patients who remain unresponsive after discontinuation of sedation.

BACKGROUND: Prolonged sedation is common in mechanically ventilated patients and is associated with increased morbidity and mortality. We sought to determine the diagnostic value of head computed tomography (CT) in mechanically ventilated patients who remain unresponsive after discontinuation of sedation. METHODS: A retrospective review of adult (age >18 years of age) patients consecutively admitted to the medical intensive care unit of a tertiary care medical center. Patients requiring mechanical ventilation for management of respiratory failure for longer than 72 hours were included in the study group. A group that did not have difficulty with awakening was included as a control. RESULTS: The median time after sedation was discontinued until a head CT was performed was 2 days (interquartile range 1.375-2 days). Majority (80%) of patients underwent head CT evaluation within the first 48 hours after discontinuation of sedation. Head CT was non-diagnostic in all but one patient who had a small subarachnoid hemorrhage. Twenty-five patients (60%) had a normal head CT. Head CT findings did not alter the management of any of the patients. The control group was similar to the experimental group with respect to demographics, etiology of respiratory failure and type of sedation used. However, while 37% of subjects in the control group had daily interruption of sedation, only 19% in the patient group had daily interruption of sedation (p < 0.05). CONCLUSION: In patients on mechanical ventilation for at least 72 hours and who remain unresponsive after sedative discontinuation and with a non-focal neurologic examination, head CT is performed early and is of very limited diagnostic utility. Routine use of daily interruption of sedation is used in a minority of patients outside of a clinical trial setting though it may decrease the frequency of unresponsiveness from prolonged sedation and the need for head CT in patients mechanically ventilated for a prolonged period.

Are implantable cardioverter defibrillator shocks a surrogate for sudden cardiac death in patients with nonischemic cardiomyopathy?

BACKGROUND: Ventricular tachyarrhythmias long enough to cause implantable cardioverter defibrillator (ICD) shocks are generally thought to progress to cardiac arrest. In previous ICD trials, shocks have been considered an appropriate surrogate for sudden cardiac death (SCD) because the number of shocks has been thought to be equivalent to the mortality excess in patients without ICDs. The practice of equating ICD shocks with mortality is controversial and has not been validated critically. METHODS AND RESULTS: The Defibrillators in Non-Ischemic Cardiomyopathy Treatment Evaluation (DEFINITE) trial was a prospective, randomized, multicenter trial of ICD therapy in 458 patients with nonischemic cardiomyopathy. Patients were randomized to receive standard medical therapy (STD) or STD plus an ICD. Shock electrograms were reviewed, and the cause of death was evaluated by a separate blinded events committee. There were 15 SCD or cardiac arrests in the STD group and only 3 in the ICD arm. In contrast, of the 229 patients randomized to an ICD, 33 received 70 appropriate ICD shocks. Patients in the ICD arm were more likely to have an arrhythmic event (ICD shock plus SCD) than patients in the STD arm (hazard ratio 2.12, 95% CI 1.153 to 3.893, P=0.013). The number of arrhythmic events when one includes syncope as a potential arrhythmic event was similar in both groups (hazard ratio 1.20, 95% CI 0.774 to 1.865, P=0.414). Approximately the same number of total events was noted in each arm when we compared syncope plus SCD/cardiac arrest in the STD arm with SCD plus ICD shocks plus syncope in the ICD arm. CONCLUSIONS: Appropriate ICD shocks occur more frequently than SCD in patients with nonischemic cardiomyopathy. This suggests that episodes of nonsustained ventricular tachycardia frequently terminate spontaneously in such patients.