Dataset Information

The feasibility of deep learning-based synthetic contrast-enhanced CT from nonenhanced CT in emergency department patients with acute abdominal pain

ABSTRACT: Our objective was to investigate the feasibility of deep learning-based synthetic contrast-enhanced CT (DL-SCE-CT) from nonenhanced CT (NECT) in patients who visited the emergency department (ED) with acute abdominal pain (AAP). We trained an algorithm generating DL-SCE-CT using NECT with paired precontrast/postcontrast images. For clinical application, 353 patients from three institutions who visited the ED with AAP were included. Six reviewers (experienced radiologists, ER1-3; training radiologists, TR1-3) made diagnostic and disposition decisions using NECT alone and then with NECT and DL-SCE-CT together. The radiologists’ confidence in decisions was graded using a 5-point scale. The diagnostic accuracy using DL-SCE-CT improved in three radiologists (50%, P = 0.023, 0.012, < 0.001, especially in 2/3 of TRs). The confidence of diagnosis and disposition improved significantly in five radiologists (83.3%, P < 0.001). Particularly, in subgroups with underlying malignancy and miscellaneous medical conditions (MMCs) and in CT-negative cases, more radiologists reported increased confidence in diagnosis (83.3% [5/6], 100.0% [6/6], and 83.3% [5/6], respectively) and disposition (66.7% [4/6], 83.3% [5/6] and 100% [6/6], respectively). In conclusion, DL-SCE-CT enhances the accuracy and confidence of diagnosis and disposition regarding patients with AAP in the ED, especially for less experienced radiologists, in CT-negative cases, and in certain disease subgroups with underlying malignancy and MMCs.

SUBMITTER: Kim S

PROVIDER: S-EPMC8516935 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundEarly screening and accurately identifying Acute Appendicitis (AA) among patients with undifferentiated symptoms associated with appendicitis during their emergency visit will improve patient safety and health care quality. The aim of the study was to compare models that predict AA among patients with undifferentiated symptoms at emergency visits using both structured data and free-text data from a national survey.MethodsWe performed a secondary data analysis on the 2005-2017 United States National Hospital Ambulatory Medical Care Survey (NHAMCS) data to estimate the association between emergency department (ED) patients with the diagnosis of AA, and the demographic and clinical factors present at ED visits during a patient's ED stay. We used binary logistic regression (LR) and random forest (RF) models incorporating natural language processing (NLP) to predict AA diagnosis among patients with undifferentiated symptoms.ResultsAmong the 40,441 ED patients with assigned International Classification of Diseases (ICD) codes of AA and appendicitis-related symptoms between 2005 and 2017, 655 adults (2.3%) and 256 children (2.2%) had AA. For the LR model identifying AA diagnosis among adult ED patients, the c-statistic was 0.72 (95% CI: 0.69-0.75) for structured variables only, 0.72 (95% CI: 0.69-0.75) for unstructured variables only, and 0.78 (95% CI: 0.76-0.80) when including both structured and unstructured variables. For the LR model identifying AA diagnosis among pediatric ED patients, the c-statistic was 0.84 (95% CI: 0.79-0.89) for including structured variables only, 0.78 (95% CI: 0.72-0.84) for unstructured variables, and 0.87 (95% CI: 0.83-0.91) when including both structured and unstructured variables. The RF method showed similar c-statistic to the corresponding LR model.ConclusionsWe developed predictive models that can predict the AA diagnosis for adult and pediatric ED patients, and the predictive accuracy was improved with the inclusion of NLP elements and approaches.

Project description:INTRODUCTION:Radiologists and other specialty consultants play a role in diagnosing patients with acute abdominal conditions. Numerous Computed Tomography (CT) protocols are available and radiologists' choices are influenced by the clinical history provided. We hypothesize that the quality of the initial communication between referring physicians and radiologists greatly affects the utilization of health resources and subsequent patient care. The purpose of this pilot study was to employ a grading system to quantitatively evaluate a provided history. We also sought to evaluate inter-rater reliability by having radiologists evaluate sample histories and finally, to assess whether the quality of history has an impact on the number of CT protocols radiologists choose as potentially appropriate, with less potential protocols being seen as a positive outcome. METHODS:Four reviewers, (2 attendings and 2 residents) evaluated 350 consecutive clinical histories provided for patients presenting to a tertiary care Emergency Department (ED) between September-October, 2012. Reviewers graded histories on a 5-point scale using 4 categories of criteria. This includes a) presenting complaint, b) relevant past medical history or symptom evolution, c) objective laboratory or prior examination results and d) differential diagnosis. RESULTS:There was substantial agreement among all four reviewers when evaluating the quality of history, ICC 0.61, (95% CI 0.48-0.71). In particular, agreement amongst attending radiologists was substantial, with ICC 0.69 (0.48-0.80). Significant negative correlation was observed between history grade and number of potentially appropriate protocols in 3 of 4 reviewers (Spearman's rho: -0.394, -0.639, -0.864, p <0.0001 for these reviewers). This correlation was significantly stronger for attending radiologists (Spearman's rho: -0.763, 95% CI -0.7933 to -0.731; p<0.0001). Agreement was poor among reviewers when asked exactly how many protocols could potentially be used to answer the clinical question based on provided history, ICC 0.08, (95% -0.03-0.13). CONCLUSION:Although there is still variability in radiologists' approach to protocoling urgent studies, a more comprehensive requisition history narrowed the number of protocols considered.

Project description:STUDY OBJECTIVE:We compare the efficacy and safety of intravenous lidocaine with that of hydromorphone for the treatment of acute abdominal pain in the emergency department (ED). METHODS:This was a randomized, double-blind, clinical trial conducted in 2 EDs in the Bronx, NY. Adults weighing 60 to 120 kg were randomized to receive 120 mg of intravenous lidocaine or 1 mg of intravenous hydromorphone. Thirty minutes after administration of the first dose of the study drug, participants were asked whether they needed a second dose of the investigational medication to which they were randomized. Patients were also stratified according to clinical suspicion of nephrolithiasis. The primary outcome was improvement in pain scores of 0 to 10 between baseline and 90 minutes. An important secondary outcome was need for "off-protocol" parenteral analgesics, including opioids and nonsteroidal anti-inflammatory drugs. RESULTS:We enrolled 154 patients, of whom 77 received lidocaine and 77 received hydromorphone. By 90 minutes, patients randomized to lidocaine improved by a mean of 3.8 points on the 0-to-10 scale, whereas those randomized to hydromorphone improved by a mean of 5.0 points (mean difference 1.2; 95% confidence interval 0.3 to 2.2). Need for off-protocol "rescue" analgesics occurred for 39 of 77 lidocaine patients (51%) and 20 of 77 hydromorphone patients (26%) (difference 25%; 95% confidence interval 10% to 40%). Adverse events were comparable between groups. Among the subset of 22 patients with nephrolithiasis, lidocaine patients reported a mean improvement of 3.4 points on the pain scale, whereas hydromorphone patients reported a mean improvement of 6.4 points (mean difference 3.0; 95% confidence interval 0.5 to 5.5). CONCLUSION:Intravenous hydromorphone was superior to intravenous lidocaine both for general abdominal pain and a subset of patients with nephrolithiasis. A majority of patients randomly allocated to lidocaine required additional analgesics.

Dataset Information

The feasibility of deep learning-based synthetic contrast-enhanced CT from nonenhanced CT in emergency department patients with acute abdominal pain

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure