Deep neural networks detect regional wall motion abnormalities and preclinical cardiovascular disease from 12-lead ECGs.

Background: Identifying regional wall motion abnormalities (RWMAs) is critical for diagnosing and risk stratifying patients with cardiovascular disease, particularly ischemic heart disease. We hypothesized that a deep neural network could accurately identify patients with regional wall motion abnormalities from a readily available standard 12-lead electrocardiogram (ECG). Methods: This observational, retrospective study included patients who were treated at Beth Israel Deaconess Medical Center and had an ECG and echocardiogram performed within 14 days of each other between 2008 and 2019. We trained a convolutional neural network to detect the presence of RWMAs, qualitative global right ventricular (RV) hypokinesis, and varying degrees of left ventricular dysfunction (left ventricular ejection fraction [LVEF] ≤50%, LVEF ≤40%, and LVEF ≤35%) identified by echocardiography, using ECG data alone. Patients were randomly split into development (80%) and test sets (20%). Model performance was assessed using area under the receiver operating characteristic curve (AUC). Cox proportional hazard models adjusted for age and sex were performed to estimate the risk of future acute coronary events. Results: The development set consisted of 19,837 patients (mean age 66.7±16.4; 46.7% female) and the test set comprised of 4,953 patients (mean age 67.5±15.8 years; 46.5% female). On the test dataset, the model accurately identified the presence of RWMA, RV hypokinesis, LVEF ≤50%, LVEF ≤40%, and LVEF ≤35% with AUCs of 0.87 (95% CI 0.858-0.882), 0.888 (95% CI 0.878-0.899), 0.923 (95% CI 0.914-0.933), 0.93 (95% CI 0.921-0.939), and 0.876 (95% CI 0.858-0.896), respectively. Among patients with normal biventricular function at the time of the index ECG, those classified as having RMWA by the model were 3 times the risk (age- and sex-adjusted hazard ratio, 2.8; 95% CI 1.9-3.9) for future acute coronary events compared to those classified as negative. Conclusions: We demonstrate that a deep neural network can help identify regional wall motion abnormalities and reduced LV function from a 12-lead ECG and could potentially be used as a screening tool for triaging patients who need either initial or repeat echocardiographic imaging.

INSPIRE, a publicly available research dataset for perioperative medicine.

We present the INSPIRE dataset, a publicly available research dataset in perioperative medicine, which includes approximately 130,000 surgical operations at an academic institution in South Korea over a ten-year period between 2011 and 2020. This comprehensive dataset includes patient characteristics such as age, sex, American Society of Anesthesiologists physical status classification, diagnosis, surgical procedure code, department, and type of anaesthesia. The dataset also includes vital signs in the operating theatre, general wards, and intensive care units (ICUs), laboratory results from six months before admission to six months after discharge, and medication during hospitalisation. Complications include total hospital and ICU length of stay and in-hospital death. We hope this dataset will inspire collaborative research and development in perioperative medicine and serve as a reproducible external validation dataset to improve surgical outcomes.

Surgical complications after fixation of minimally displaced lateral compression type 1 pelvic ring injuries.

PURPOSE: To review surgical complications after fixation of stress-positive minimally displaced (< 1 cm) lateral compression type 1 (LC1) pelvic ring injuries. METHODS: A retrospective study at a level one trauma center identified patients who received surgical fixation of isolated LC1 pelvic ring injuries. Surgical complications and additional procedures were reviewed. RESULTS: Sixty patients were included. The median age was 61 years (Interquartile range 40-70), 65% (n = 39) were women, and 57% (n = 34) had high-energy mechanisms. Anterior-posterior, posterior-only, and anterior-only fixation constructs were used in 77% (n = 46), 15% (n = 9), and 8% (n = 5) of patients. Anterior fixation was performed with rami screw fixation in 82% (49/60), external fixation in 2% (1/60), and open reduction and plate fixation in 2% (1/60). There were 15 surgical complications in 23% (14/60), and 12 additional procedures in 17% (10/60). Complications included loss of reduction ≥ 1 cm (8%), symptomatic hematomas (8%), symptomatic backout of unicortical retrograde rami screws (5%), deep infection of the pelvic space after a retrograde rami screw (1.6%), and iatrogenic L5 nerve injury (1.6%). All losses of reduction involved geriatric females with distal rami fractures sustained in ground-level falls. Loss of reduction was found to be more likely in patients with low energy mechanisms (proportional difference (PD) 62%, 95% confidence interval (CI) 18% to 76%; p = 0.01) and 2 versus 1 posterior pelvic screws (PD 36%; CI 0.4% to 75%; p = 0.03). CONCLUSIONS: Surgical complications and additional procedures routinely occurred after fixation of LC1 injuries. Patients should be appropriately counseled on the risks of surgical fixation of these controversial injuries. LEVEL OF EVIDENCE: Diagnostic, Level III.

The Effect of Steroid Use on Complications after Distal Radius Fracture Repair.

Background Distal radius fractures (DRFs) are the most common fracture of the upper extremity. Given that steroids are one of the most commonly prescribed drugs and are usually prescribed for chronic conditions, steroid use represents a key factor to consider in how to optimize perioperative outcomes. Questions/Purposes The purpose of this study was to investigate if there are differences in perioperative outcomes for patients undergoing DRF open reduction and internal fixation based on preoperative steroid use. Patients and Methods Adult patients who underwent operative treatment for DRF from 2007 to 2018 were identified in a national database. Patients were divided into two cohorts as follows: (1) no steroid usage and (2) preoperative steroid usage. In this analysis, various postoperative complications, as well as extended length of stay and reoperation, were assessed. Bivariate analyses and multivariable logistical regression were performed. Results Among a total of 16,505 patients undergoing operative treatment for DRF, 16,145 patients (97.8%) did not have steroid usage and 360 (2.2%) had steroid usage. Following adjustment, an increased risk of extended length of hospital stay greater than 3 days (odds ratio [OR] = 1.646; p = 0.012) was seen in the steroid usage group compared with those who did not use steroids within 30 days of surgery. Conclusion Preoperative steroid use is associated with increased length of stay over 3 days after DRF open reduction and internal fixation surgery but is not associated with any of the other complications that were assessed in this study. Level of Evidence This is a Level III, retrospective study.

Evaluation of evolving sepsis screening criteria in discriminating suspected sepsis and mortality among adult patients admitted to the intensive care unit.

BACKGROUND: Institutions struggle with successful use of sepsis alerts within electronic health records. OBJECTIVE: Test the association of sepsis screening measurement criteria in discrimination of mortality and detection of sepsis in a large dataset. DESIGN: Retrospective, cohort study using a large United States (U.S.) intensive care database. The Institutional Review Board exempt status was obtained from Kansas University Medical Center Human Research Protection Program (10-1-2015). SETTING: 334 U.S. hospitals participating in the eICU Research Institute. PARTICIPANTS: Nine hundred twelve thousand five hundred and nine adult intensive care admissions from 183 hospitals. METHODS: Exposures included: systemic inflammatory response syndrome criteria ≥ 2 (Sepsis-1); systemic inflammatory response syndrome criteria with organ failure criteria ≥ 3.5 points (Sepsis-2); and sepsis-related organ failure assessment score ≥ 2 and quick score ≥ 2 (Sepsis-3). Discrimination of outcomes was determined with/without (adjusted/unadjusted) baseline risk exposure to a model. The receiver operating characteristic curve (AUROC) and odds ratios (ORs) for each decile of baseline risk of sepsis or death were assessed. RESULTS: Within the eligible cohort of 912,509, a total of 86,219 (9.4 %) patients did not survive their hospital stay and 186,870 (20.5 %) met the definition of suspected sepsis. For suspected sepsis discrimination, Sepsis-2 (unadjusted AUROC 0.67, 99 % CI: 0.66-0.67 and adjusted AUROC 0.77, 99 % CI: 0.77-0.77) outperformed Sepsis-3 (SOFA unadjusted AUROC 0.61, 99 % CI: 0.61-0.61 and adjusted AUROC 0.74, 99 % CI: 0.74-0.74) (qSOFA unadjusted AUROC 0.59, 99 % CI: 0.59-0.60 and adjusted AUROC 0.73, 99 % CI: 0.73-0.73). Sepsis-2 also outperformed Sepsis-1 (unadjusted AUROC 0.58, 99 % CI: 0.58-0.58 and adjusted AUROC 0.73, 99 % CI: 0.73-0.73). In between differences of AUROCs were statistically significantly different. Sepsis-2 ORs were higher for the outcome of suspected sepsis when considering deciles of risk than the other measurement systems. CONCLUSIONS AND RELEVANCE: Sepsis-2 outperformed other systems in suspected sepsis detection and was comparable to SOFA in prognostic accuracy of mortality in adult intensive care patients.

MIMIC-IV, a freely accessible electronic health record dataset.

Digital data collection during routine clinical practice is now ubiquitous within hospitals. The data contains valuable information on the care of patients and their response to treatments, offering exciting opportunities for research. Typically, data are stored within archival systems that are not intended to support research. These systems are often inaccessible to researchers and structured for optimal storage, rather than interpretability and analysis. Here we present MIMIC-IV, a publicly available database sourced from the electronic health record of the Beth Israel Deaconess Medical Center. Information available includes patient measurements, orders, diagnoses, procedures, treatments, and deidentified free-text clinical notes. MIMIC-IV is intended to support a wide array of research studies and educational material, helping to reduce barriers to conducting clinical research.

Mortality and morbidity following operative management of tibial shaft fractures in octogenarians.

PURPOSE: As the geriatric population continues to grow, the incidence of tibial shaft fractures in octogenarians is projected to increase. There is significant variation in the functional and physiologic status within the geriatric population. The purpose of this study is to compare the complications following operative treatment of tibial shaft fractures for patients who are 65- to79-year-old compared to patients who are 80- to 89-year-old. METHODS: Data were collected through the National Surgical Quality Improvement Program database for the years 2007-2018. All isolated tibial shaft fractures that were treated with open reduction internal fixation (ORIF) or intramedullary nail (IMN) were identified. Patients were divided into a 65- to 79-year-old group and an 80-to 89-year-old group. Primary and secondary outcomes were studied and included 30-day mortality. Univariate and multivariate analyses were performed with a significance set at p < 0.05. RESULTS: In total, 434 patients with tibial shaft fractures were included in the study. Of these, 333 were 65- to 79-year-old and 101 were 80- to 89-year-old (Table 1). On multivariate analysis, there was no significant difference in complication rates between the two cohorts. CONCLUSION: After controlling for demographics and comorbidities, age was not independently associated with 30-day mortality or any other peri-operative complications between patients aged 80 to 89 and patients aged 65 to 79 following operative management of tibial shaft fractures. In appropriately selected octogenarian patients, operative management of tibial shaft fractures represents a relatively safe treatment modality that may promote early rehabilitation.

Impact of sickle cell disease on postoperative outcomes following total hip arthroplasty.

INTRODUCTION: Osteonecrosis (ON) of the femoral head is a common complication of sickle cell disease (SCD), frequently necessitating total hip arthroplasty (THA). Although THA is a common procedure with few complications when indicated for osteoarthritis (OA), patients with SCD have increased rates of complications. The purpose of this study is to determine the impact of SCD on outcomes and complications following THA. METHODS: Subjects were retrospectively identified using a national insurance claims database (PearlDiver Technologies) using CPT and ICD-9/10. Patients were included if they underwent THA with at least 2-year follow-up and were diagnosed with SCD and ON, ON without SCD, or OA without SCD. The SCD cohort was matched based on age, gender, Charlson Comorbidity Index, and obesity to the other 2 cohorts. 2-year revision rate and 90-day complication rates were analyzed using chi-square tests. RESULTS: Each cohort had 881 patients. The SCD cohort had significantly higher 90-day medical complications when compared to the ON without SCD and OA cohorts (p < 0.001). The SCD cohort had a higher rate of 2-year revision for PJI (5.0%) compared to the ON without SCD (2.8%) and OA (2.5%) groups (p = 0.019 and 0.005 respectively) and a higher rate of aseptic loosening (1.94%) compared to the ON without SCD cohort (0.68%; p = 0.021). CONCLUSIONS: Patients with SCD who undergo THA have an increased risk for short-term postoperative medical complications and 2-year aseptic loosening and PJI compared to ON patients without SCD and patients with OA. Given the magnitude of these risks, patient counseling and optimised perioperative care are essential.

Comparison of 30-day complications between reverse shoulder arthroplasty and open reduction internal fixation for the treatment of proximal humerus fractures.

PURPOSE: While the use of open reduction internal fixation (ORIF) has remained stable over the last decade, there has been a significant increase in the use of reverse total shoulder arthroplasty (RTSA) for proximal humerus fractures (PHFs). This study sought to compare the complication profiles of RTSA to ORIF in a large, validated, retrospective cohort. METHODS: Patients who underwent surgical treatment for PHFs with RTSA or ORIF were identified in a national database (NSQIP) using CPT and ICD codes. Demographics and comorbidities were identified for each cohort of patients. Thirty-day complications were analyzed with univariate and multivariate analyses using Chi-square, Fischer's exact and analysis of variance testing. RESULTS: The total number of patients included in this study was 2157.522 (24.2%) underwent RTSA and 1635 (75.8%) underwent ORIF. Patients undergoing RTSA were older with an average age of 73.52 years compared with 63.84 years in those undergoing ORIF (p < 0.001). Patients with RTSA were more likely to experience any complications (p < 0.001), pulmonary complications (p = 0.029), extended length of stay > 3 days (p < 0.001), and perioperative transfusion requirement (p < 0.001) after univariate analysis. After controlling for demographic differences, the only statistically significant complication was perioperative transfusion requirement (OR 1.383). CONCLUSION: After controlling for demographic variables and comorbidities, RTSA placed patients at increased risk for perioperative blood transfusion. Patients undergoing RTSA should be counseled prior to surgery regarding the risk for transfusion and potentially optimized medically through multidisciplinary care if the surgeon elects to proceed with RTSA versus ORIF for the treatment of PHFs.

Timing and safety of hip fracture surgery in patients on direct-acting oral anticoagulants.

Background: Many geriatric patients presenting for emergency hip fracture surgery are on direct oral anticoagulants (DOACs) most of which are not easily reversible. A safe policy was required to reduce delays to surgery. Prior to institution of our hospital's protocol in January 2021, most of these patients had surgery after 48 h following the last dose of DOAC due to concerns about increased perioperative blood loss. Methods: This was a prospective closed loop audit of the protocol-surgery within 24 h from last dose of DOAC (if creatinine clearance >50 ml/min) with administration of 1-g of tranexamic acid at anesthesia induction. 131 eligible patients (DOAC, n = 22; no anticoagulation, n = 109) between January-June 2021 who had emergency hip fracture surgery were identified. Primary outcome measures were peri-operative blood loss, transfusion requirements and policy compliance. Secondary outcome measures were 30-day mortality, thrombotic complications and wound bleeding. Results: Compliance with surgical timing and tranexamic acid administration were 55% and 81% respectively after the second audit cycle. The mean estimated blood loss (EBL) in the DOAC group versus the non-anticoagulated control group was 500 ml and 330 ml respectively. The difference between these groups was statistically significant at an alpha level of 5% (P = 0.0115, 95% CI 38.48-299.16). The difference for intra-operative (RR 3.43; 95% CI 1.68-7.01) and post-operative blood transfusion (RR 2.10; 95% CI 1.23-3.58) for the 2 groups was also statistically significant. However, there was no case of massive blood transfusion in both groups. The DOAC group had a lower risk for 30-day mortality (RR 0.71; 95% CI 0.09-5.46). There was no major thrombotic complication in the DOAC group. Conclusion: This audit has shown that this protocol is safe although clinicians should anticipate some degree of increased intra-operative blood loss. We will recommend continuation of this policy with sustained safety monitoring in order to reduce delays to surgery.

Tibial derotation osteotomies are effective in improving pain and function and avoiding hip arthroscopy in patients with hip pain-a short-term follow-up.

The primary objective was to determine short-term clinical outcomes following distal tibial derotation osteotomy (DTDO) performed to manage hip pain in the presence of tibial maltorsion and to review how co-existing pathomorphology affected the management. All patients undergoing DTDO for hip pain with tibial rotational deformities recognized as the predominant aetiology were included. Normal tibial torsion range was assumed as 0-40°, measured by trans-malleolar line relative to femoral posterior condyles. All patients had a positive hip impingement test Flexion Adduction Internal Rotation test (FADIR). The patients older than 50 years or presenting with degenerative joint changes and neuromuscular conditions were excluded. Associated ipsilateral MRI-defined intra-articular pathomorphology (cam/pincer), non-cam/pincer-related labral tears and abnormal combined femoral/acetabular version (McKibbin index) were noted. Pre-operative and post-operative functional outcomes were analysed. Thirty-two patients underwent DTDO. Mean tibial torsion was 48.8° (41-63°), average age was 27 years (18-44), and average follow-up was 30 months (16-45). Nine patients (28%) had a co-existing cam/pincer, and eight patients (25%) had an excessive McKibbin index (51-76°). Overall, 63% of all patients (including 54% of patients with co-existing pathology) experienced significant hip functional improvement following DTDO alone. Pre-operative vs 12 months post-operative scores were calculated as follows: International Hip Outcome Tool-12-41 vs 67 (P < 0.01); Hip Outcome Score Activities of Daily Living Scale-47 vs 70 (P < 0.05); and Hip Outcome Score Sport Scale-36 vs 64 (P < 0.05). Patients with hip pain frequently present with a combination of tibial and/or femoral rotational deformity and cam/pincer lesions. It is important to consider tibial maltorsion as an aetiology of hip pain. Tibial derotation with DTDO results in significant clinical and functional recovery within 12 months in symptomatic hip impingement patients even in the presence of co-existing pathomorphology.

BRAX, Brazilian labeled chest x-ray dataset.

Chest radiographs allow for the meticulous examination of a patient's chest but demands specialized training for proper interpretation. Automated analysis of medical imaging has become increasingly accessible with the advent of machine learning (ML) algorithms. Large labeled datasets are key elements for training and validation of these ML solutions. In this paper we describe the Brazilian labeled chest x-ray dataset, BRAX: an automatically labeled dataset designed to assist researchers in the validation of ML models. The dataset contains 24,959 chest radiography studies from patients presenting to a large general Brazilian hospital. A total of 40,967 images are available in the BRAX dataset. All images have been verified by trained radiologists and de-identified to protect patient privacy. Fourteen labels were derived from free-text radiology reports written in Brazilian Portuguese using Natural Language Processing.

Erratum to 'Total Hip Arthroplasty in An Adult Patient With Pelvic Dysmorphism, Unilateral Sacroiliac Joint Autofusion, and Developmental Hip Dysplasia' [Arthroplasty Today 6 (2020) 41-47].

[This corrects the article DOI: 10.1016/j.artd.2019.10.006.].

The Global Open Source Severity of Illness Score (GOSSIS).

OBJECTIVES: To develop and demonstrate the feasibility of a Global Open Source Severity of Illness Score (GOSSIS)-1 for critical care patients, which generalizes across healthcare systems and countries. DESIGN: A merger of several critical care multicenter cohorts derived from registry and electronic health record data. Data were split into training (70%) and test (30%) sets, using each set exclusively for development and evaluation, respectively. Missing data were imputed when not available. SETTING/PATIENTS: Two large multicenter datasets from Australia and New Zealand (Australian and New Zealand Intensive Care Society Adult Patient Database [ANZICS-APD]) and the United States (eICU Collaborative Research Database [eICU-CRD]) representing 249,229 and 131,051 patients, respectively. ANZICS-APD and eICU-CRD contributed data from 162 and 204 hospitals, respectively. The cohort included all ICU admissions discharged in 2014-2015, excluding patients less than 16 years old, admissions less than 6 hours, and those with a previous ICU stay. INTERVENTIONS: Not applicable. MEASUREMENTS AND MAIN RESULTS: GOSSIS-1 uses data collected during the ICU stay's first 24 hours, including extrema values for vital signs and laboratory results, admission diagnosis, the Glasgow Coma Scale, chronic comorbidities, and admission/demographic variables. The datasets showed significant variation in admission-related variables, case-mix, and average physiologic state. Despite this heterogeneity, test set discrimination of GOSSIS-1 was high (area under the receiver operator characteristic curve [AUROC], 0.918; 95% CI, 0.915-0.921) and calibration was excellent (standardized mortality ratio [SMR], 0.986; 95% CI, 0.966-1.005; Brier score, 0.050). Performance was held within ANZICS-APD (AUROC, 0.925; SMR, 0.982; Brier score, 0.047) and eICU-CRD (AUROC, 0.904; SMR, 0.992; Brier score, 0.055). Compared with GOSSIS-1, Acute Physiology and Chronic Health Evaluation (APACHE)-IIIj (ANZICS-APD) and APACHE-IVa (eICU-CRD), had worse discrimination with AUROCs of 0.904 and 0.869, and poorer calibration with SMRs of 0.594 and 0.770, and Brier scores of 0.059 and 0.063, respectively. CONCLUSIONS: GOSSIS-1 is a modern, free, open-source inhospital mortality prediction algorithm for critical care patients, achieving excellent discrimination and calibration across three countries.