From bimodal to unimodal: The transformed incidence of osteosarcoma in the United States.

Background: Osteosarcoma is the most common primary bone malignancy. It has classically been described as having a bimodal incidence by age. We sought to identify whether the bimodal incidence distribution still exists for osteosarcoma using the SEER and NIS databases. Methods: Incidence rates of primary osteosarcoma between 2000-2021 were analyzed by age at diagnosis, year of occurrence, sex, and tumor site from the SEER Research Data, 17 Registries, Nov 2023 Sub (2000-2021). The incidence of cases in 35-64 year-olds and 65 and above was compared statistically to determine if there is an increased incidence in the later ages. Incidence of tumors of the long bones of the lower limbs from the NIS discharge database 2012-2019 was also analyzed for comparison. Results: Overall, 5,129 cases of osteosarcoma were reported in the SEER database. Across the 22 calendar year span, a consistent first peak appeared in the second decade of life. There was no consistent second peak in the 35+ age group. There were 86,100 discharges with long bone tumors analyzed in the NIS data which exhibited nearly identical patterns. Conclusions: Our analysis shows that the incidence of osteosarcoma is no longer bimodally distributed but rather unimodally distributed.

Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health records.

Methicillin-resistant Staphylococcus aureus (MRSA) poses significant morbidity and mortality in hospitals. Rapid, accurate risk stratification of MRSA is crucial for optimizing antibiotic therapy. Our study introduced a deep learning model, PyTorch_EHR, which leverages electronic health record (EHR) time-series data, including wide-variety patient specific data, to predict MRSA culture positivity within two weeks. 8,164 MRSA and 22,393 non-MRSA patient events from Memorial Hermann Hospital System, Houston, Texas are used for model development. PyTorch_EHR outperforms logistic regression (LR) and light gradient boost machine (LGBM) models in accuracy (AUROCPyTorch_EHR = 0.911, AUROCLR = 0.857, AUROCLGBM = 0.892). External validation with 393,713 patient events from the Medical Information Mart for Intensive Care (MIMIC)-IV dataset in Boston confirms its superior accuracy (AUROCPyTorch_EHR = 0.859, AUROCLR = 0.816, AUROCLGBM = 0.838). Our model effectively stratifies patients into high-, medium-, and low-risk categories, potentially optimizing antimicrobial therapy and reducing unnecessary MRSA-specific antimicrobials. This highlights the advantage of deep learning models in predicting MRSA positive cultures, surpassing traditional machine learning models and supporting clinicians' judgments.

Recurrent neural network models (CovRNN) for predicting outcomes of patients with COVID-19 on admission to hospital: model development and validation using electronic health record data.

BACKGROUND: Predicting outcomes of patients with COVID-19 at an early stage is crucial for optimised clinical care and resource management, especially during a pandemic. Although multiple machine learning models have been proposed to address this issue, because of their requirements for extensive data preprocessing and feature engineering, they have not been validated or implemented outside of their original study site. Therefore, we aimed to develop accurate and transferrable predictive models of outcomes on hospital admission for patients with COVID-19. METHODS: In this study, we developed recurrent neural network-based models (CovRNN) to predict the outcomes of patients with COVID-19 by use of available electronic health record data on admission to hospital, without the need for specific feature selection or missing data imputation. CovRNN was designed to predict three outcomes: in-hospital mortality, need for mechanical ventilation, and prolonged hospital stay (>7 days). For in-hospital mortality and mechanical ventilation, CovRNN produced time-to-event risk scores (survival prediction; evaluated by the concordance index) and all-time risk scores (binary prediction; area under the receiver operating characteristic curve [AUROC] was the main metric); we only trained a binary classification model for prolonged hospital stay. For binary classification tasks, we compared CovRNN against traditional machine learning algorithms: logistic regression and light gradient boost machine. Our models were trained and validated on the heterogeneous, deidentified data of 247 960 patients with COVID-19 from 87 US health-care systems derived from the Cerner Real-World COVID-19 Q3 Dataset up to September 2020. We held out the data of 4175 patients from two hospitals for external validation. The remaining 243 785 patients from the 85 health systems were grouped into training (n=170 626), validation (n=24 378), and multi-hospital test (n=48 781) sets. Model performance was evaluated in the multi-hospital test set. The transferability of CovRNN was externally validated by use of deidentified data from 36 140 patients derived from the US-based Optum deidentified COVID-19 electronic health record dataset (version 1015; from January, 2007, to Oct 15, 2020). Exact dates of data extraction were masked by the databases to ensure patient data safety. FINDINGS: CovRNN binary models achieved AUROCs of 93·0% (95% CI 92·6-93·4) for the prediction of in-hospital mortality, 92·9% (92·6-93·2) for the prediction of mechanical ventilation, and 86·5% (86·2-86·9) for the prediction of a prolonged hospital stay, outperforming light gradient boost machine and logistic regression algorithms. External validation confirmed AUROCs in similar ranges (91·3-97·0% for in-hospital mortality prediction, 91·5-96·0% for the prediction of mechanical ventilation, and 81·0-88·3% for the prediction of prolonged hospital stay). For survival prediction, CovRNN achieved a concordance index of 86·0% (95% CI 85·1-86·9) for in-hospital mortality and 92·6% (92·2-93·0) for mechanical ventilation. INTERPRETATION: Trained on a large, heterogeneous, real-world dataset, our CovRNN models showed high prediction accuracy and transferability through consistently good performances on multiple external datasets. Our results show the feasibility of a COVID-19 predictive model that delivers high accuracy without the need for complex feature engineering. FUNDING: Cancer Prevention and Research Institute of Texas.

The learning curve for transoral incisionless fundoplication.

Background and study aims Transoral incisionless fundoplication (TIF) is a safe and effective minimally invasive endoscopic technique for treating gastroesophageal reflux disease (GERD). The learning curve for this technique has not been reported. We studied the learning curve for TIF when performed by a gastroenterologist by identifying the threshold number of procedures needed to achieve consistent technical success or proficiency (consistent creation of TIF valve ≥ 270 degrees in circumference, ≥ 2 cm long) and efficiency after didactic, hands-on and case observation experience. Patients and methods We analyzed prospectively collected data from patients who had TIF performed by a single therapeutic endoscopist within 17 months after basic training. We determined thresholds for procedural learning using cumulative sum of means (CUSUM) analysis to detect changes in achievement rates over time. We used breakpoint analysis to calculate procedure metrics related to proficiency and efficiency. Results A total of 69 patients had 72 TIFs. The most common indications were refractory GERD (44.7 %) and proton pump inhbitor intolerance (23.6 %). Proficiency was achieved at the 18 th to 20 th procedure. The maximum efficiency for performing a plication was achieved after the 26 th procedure, when mean time per plication decreased to 2.7 from 5.1 minutes (P < 0.0001). TIF procedures time varied until the 44 th procedure, after which it decreased significantly from 53.7 minutes to 39.4 minutes (P < 0.0001). Conclusions TIF can be safely, successfully, and efficiently performed in the endoscopy suite by a therapeutic endoscopist. The TIF learning curve is steep but proficiency can be achieved after a basic training experience and 18 to 20 independently performed procedures.

Real World Long-term Assessment of The Efficacy of Tocilizumab in Patients with COVID-19: Results From A Large De-identified Multicenter Electronic Health Record Dataset in the United States.

BACKGROUND: Studies have shown conflicting results on the efficacy of tocilizumab (TCZ) for patients with COVID-19, with many confounders of clinical status and limited duration of the observation. Here, we evaluate the real-world long-term efficacy of TCZ in COVID-19 patients. METHODS: We conducted a retrospective study of hospitalized adult patients with COVID-19 using a large US-based multicenter COVID-19 database (Cerner Real-World Data; updated in September, 2020). The TCZ group was defined as patients who received at least one dose of the drug. Matching weight (MW) and a propensity score weighting method were used to balance confounding factors. RESULTS: A total of 20,399 patients were identified. 1,510 and 18,899 were in the TCZ and control groups, respectively. After MW adjustment, no statistically significant differences in all-cause mortality were found for the TCZ vs. control group (Hazard Ratio [HR]:0.76, p=0.06). Survival curves suggested a better trend in short-term observation, driven from a subgroup of patients requiring oxygen masks, BIPAP or CPAP. CONCLUSION: We observed a temporal (early) benefit of TCZ, especially in patients on non-invasive high-flow supplemental oxygen. However, the benefit effects faded with longer observation. The long-term benefits and risks of TCZ should be carefully evaluated with follow-up studies.

Bleeding Risk and Mortality Associated With Uninterrupted Antithrombotic Therapy During Percutaneous Endoscopic Gastrostomy Tube Placement.

INTRODUCTION: Antithrombotic therapy is often interrupted before the placement of a percutaneous endoscopic gastrostomy (PEG) tube because of potentially increased risk of hemorrhagic events. The aim of our study was to evaluate the risk of bleeding events and overall complication rates after PEG in patients on uninterrupted antiplatelet and anticoagulation therapy in a high-volume center. METHODS: Data regarding demographics, diagnoses, comorbidities, and clinical outcomes pertinent to PEG were collected from 2010 to 2016. Furthermore, data regarding antithrombotic therapy along with the rate of minor or major complications including bleeding associated with this procedure were analyzed. Significant bleeding was defined as postprocedure bleeding from PEG site requiring a blood transfusion and/or surgical/endoscopic intervention. RESULTS: We included 1,613 consecutive PEG procedures in this study, of which 1,540 patients (95.5%) received some form of uninterrupted antithrombotic therapy. Of those patients, 535 (34.7%) were on aspirin, 256 (16.6%) on clopidogrel, and 119 (7.7%) on both aspirin and clopidogrel. Subcutaneous heparin was uninterrupted in 980 (63.6%), intravenous heparin in 34 (2.1%), warfarin in 168 (10.9%), and direct-acting oral anticoagulation in 82 (5.3%) patients who overlapped on multiple drugs. We observed 6 significant bleeding events in the entire cohort (0.39%), and all were in subcutaneous heparin groups either alone or in combination with aspirin. No clinically significant bleeding was noted in patients on uninterrupted aspirin, warfarin, clopidogrel, or direct-acting oral anticoagulation groups. Only 5 patients (0.31%) had PEG-related mortality. DISCUSSION: The risk of significant bleeding associated with the PEG placement was minimal in patients on uninterrupted periprocedural antithrombotic therapy.

ASGE guideline on the management of achalasia.

Achalasia is a primary esophageal motor disorder of unknown etiology characterized by degeneration of the myenteric plexus, which results in impaired relaxation of the esophagogastric junction (EGJ), along with the loss of organized peristalsis in the esophageal body. The criterion standard for diagnosing achalasia is high-resolution esophageal manometry showing incomplete relaxation of the EGJ coupled with the absence of organized peristalsis. Three achalasia subtypes have been defined based on high-resolution manometry findings in the esophageal body. Treatment of patients with achalasia has evolved in recent years with the introduction of peroral endoscopic myotomy. Other treatment options include botulinum toxin injection, pneumatic dilation, and Heller myotomy. This American Society for Gastrointestinal Endoscopy Standards of Practice Guideline provides evidence-based recommendations for the treatment of achalasia, based on an updated assessment of the individual and comparative effectiveness, adverse effects, and cost of the 4 aforementioned achalasia therapies.

Semimembranosus ganglion cyst.

Ganglion cysts are tumor-like lesions in the soft tissues, generated by mucoid degeneration of the joint capsule, tendon or tendon sheaths on the dorsum of hand, wrist and foot. However, an intratendinous origin for a ganglion cyst is extremely rare. During dissection of the popliteal fossa, a cyst of 2.5 cm×2 cm×0.5 cm was observed in the tendon of right semimembranosus, 3.5 cm above the insertion of the muscle. Contrast X-ray revealed the cyst as not communicating with the knee joint or any adjacent bursae. Histopathological examination confirmed the diagnosis of ganglion cyst.