Clinical Trials Logo

Clinical Trial Summary

Computer-aided diagnostic software has been used to assist physicians in various ways. Text-based prediction algorithms have been trained on past medical records through data mining and feature analysis. Currently, all text-based machine learning prediction problem models have been built on extracted data with no research completed on free text based prediction algorithms. This study aims to determine the accuracy of a free text prediction algorithm in predicting the probability of appendicitis in patients presenting to the Emergency Department with abdominal pain and gastrointestinal symptoms.


Clinical Trial Description

Developing machine learning models that have a strong prediction power for diagnosis of appendicitis from physician entered free text input can improve diagnostic accuracy of doctors. It also offers the possibility of using prediction algorithms to improve routine clinical care. In the future, multiple machine learning models can be combined to increase prediction accuracy and prediction algorithms can be extended to other diagnoses. 18,000 cases of emergency department presentations over 10 years were used as a training and validation dataset. To develop the appendicitis prediction model, deep learning neural networks with a customized medical ontology were used. The diagnostic accuracy of the model is expressed as sensitivity (recall), specificity and F1 score (harmonic mean). The developed diagnosis predictive model shows high sensitivity (86.3%), specificity (91.9%) and F1 score (88.8) in diagnosing appendicitis from patients presenting with abdominal pain. The predictive model algorithm will also highlight words in the free text (entered by the attending physician) that it assigns higher probability for predicting an outcome. The doctors will be instructed to provide a percentage likelihood of appendicitis based on the clinical presentation and any available laboratory investigations. The doctor is then shown the prediction of the algorithm as well as the highlighted words for the patient entered. He/she must then provide another prediction of the likelihood of appendicitis after seeing the algorithm generated prediction. The aim is to evaluate the performance of the algorithm and to assess if usage of the algorithm is able to help emergency doctors improve their diagnosis of appendicitis. The prediction results will be tabulated to assess accuracy of the algorithm, doctors before algorithm input and doctors after receiving algorithm input. The accuracy will be expressed as sensitivity, specificity, accuracy, positive prediction value, F1 score and F0.5 score. Approximately 100 emergency doctors will be recruited over the course of 1 year as participants in the study. The doctors will be split randomly assigned to two groups - the algorithm arm and the no algorithm arm. The randomization will be by time (weekly) using variable block randomization of 4 and 6. The patients will be followed up for the final discharge diagnoses. ;


Study Design


Related Conditions & MeSH terms


NCT number NCT03414853
Study type Observational
Source National University Hospital, Singapore
Contact
Status Completed
Phase
Start date December 4, 2017
Completion date July 1, 2020

See also
  Status Clinical Trial Phase
Completed NCT04682860 - Management of Abdominal Pain in Acute Gastroenteritis Patients With Hyoscine Butylbromide Phase 4
Not yet recruiting NCT05649891 - Checklists Resuscitation Emergency Department N/A
Completed NCT02923245 - POCUS Assessment of Bladder Fullness for Girls Awaiting Radiology-Performed Transabdominal Pelvic Ultrasound N/A
Completed NCT03318614 - Bifidobacterium Infantis M-63 Improves Mental Health in Irritable Bowel Syndrome Developed After a Major Flood Disaster Phase 2/Phase 3
Completed NCT02547857 - Transvaginal Pelvic Ultrasound in the ED N/A
Completed NCT02197780 - Head-to-head Comparison of Two Fecal Biomarkers to Screen Children for IBD N/A
Completed NCT02676232 - DARWeb: an Online Psychosocial Intervention for Children With Recurrent Abdominal Pain and Their Families. N/A
Recruiting NCT00209807 - Effect of Escitalopram vs. Reboxetine on Gastro-intestinal Sensitivity of Patients With Major Depressive Disorder Phase 4
Terminated NCT01410071 - Evaluation of Gastrointestinal Symptoms and Quality of Life in Patients With Sphincter of Oddi Dysfunction N/A
Terminated NCT01736280 - Evaluating and Treating Potential Research Participants With Digestive Disorders N/A
Enrolling by invitation NCT04104867 - Effectiveness of Prokinetic Agents in Improving Abdominal Discomfort at Colonoscopy N/A
Completed NCT03574727 - Abdominal Cutaneous Nerve Entrapment Syndrome
Completed NCT04614649 - Right Iliac Fossa Treatment-Turkey Audit
Completed NCT05438654 - Improvement of Diagnostic Approach Using PoCUS for Right Upper Quadrant Abdominal Pain N/A
Completed NCT06423586 - Effect of Lecithin-based Curcuma and Boswellia on Post-acute COVID-19 IBS N/A
Completed NCT03558009 - Epidemiological Analysis for Hereditary Angioedema Disease
Terminated NCT03148288 - Vitamin D Supplementation in IBS N/A
Completed NCT03708874 - Pain Management of Emergency Laparoscopic Cholecystectomy in Patients With Acute Cholecystitis
Withdrawn NCT04408872 - EUS vs EGD in Emergency Room Patients Referred for EGD N/A
Recruiting NCT02594774 - Efficacy of Osteopathic Treatment in Function Abdominal Pain in Children and Adolescents N/A