Diseases and Abnormalities at or Before Birth

All Conditions

Neoplasms

Symptoms and General Pathology

Skin and Connective Tissue Diseases

Rare Diseases

Congenital Abnormalities

Teratoma

Cysts

Hemangioma

Hemangioma, Capillary

Port-Wine Stain

Epidermal Cyst

Dermoid Cyst

Thyroglossal Cyst

Pathological Conditions, Anatomical

Neoplasms, Germ Cell and Embryonal

Neoplasms by Histologic Type

Neoplasms, Vascular Tissue

Skin Abnormalities

Skin Diseases

Familial Thyroglossal Duct Cyst

The internal cohort was retrospectively enrolled in West China Hospital, Sichuan University from June 2010 and December 2020. It is a training and internal validation cohort.

The same inclusion/exclusion criteria were applied for the same center prospectively. It is an external validation cohort.

Different machine learning and deep learning computer aided strategies for model construction and validation.

Artificial Intelligence Algorithm

Yuhan Yang, MD

The aim of this study was to evaluate the diagnostic efficacy of computer aided diagnostic tool for neck masses using machine learning and deep learning techniques on clinical information and radiological images in children.

This study is a retrospective-prospective design by West China Hospital, Sichuan University, including clinical data and radiological images. A retrospective database was enrolled for patients with definite histological diagnosis and available radiological images from June 2010 and December 2020. The investigators have constructed deep learning and machine learning diagnostic models on this retrospective cohort and validated it internally. A prospective cohort would recruit patients found neck masses since January 2021. The proposed computer aided diagnostic models would also be validated in this prospective cohort externally. The aim of this study was to evaluate the diagnostic efficacy of computer aided diagnostic tool for neck masses using machine learning and deep learning techniques on clinical data and radiological images in children.

Computer Aided Tool for Diagnosis of Neck Masses in Children

The diagnostic accuracy of neck masses with AI-based screening tools in children.

The diagnostic sensitivity of neck masses with AI-based screening tools in children.

The diagnostic specificity of neck masses with AI-based screening tools in children.

The diagnostic positive predictive value of neck masses with AI-based screening tools in children.

The diagnostic negative predictive value of neck masses with AI-based screening tools in children

West China Hospital

Associate Professor

Digestive System Diseases

Anastomotic Leak

Rectal Neoplasms

Colorectal Neoplasms

Intestinal Neoplasms

Gastrointestinal Neoplasms

Digestive System Neoplasms

Gastrointestinal Diseases

Intestinal Diseases

Rectal Diseases

Whether the patients in the control arm will receive a temporary ileostomy depends on surgeons' experience.

Whether the patients in the intervention arm will receive a temporary ileostomy depends on the risk of anastomotic leakage calculated by the artificial intelligence algorithm.

Temporary ileostomy will be performed in the patients with high-risk of anastomotic leakage and not performed in the patients with low-risk of anastomotic leakage.

Artificial intelligence algorithm

Jichao Qin, MD

This study will evaluate whether artificial intelligence technique reduces the temporary ileostomy rate in patients with rectal cancer who receive anterior resection.

Anastomotic leakage is a serious and life-threatening complication after anterior resection in patients with rectal cancer, and temporary ileostomy was introduced to reduce the serious consequences due to anastomotic leakage. However, whether a temporary ileostomy is applied in the surgery depends on the surgeon's experience, and there are no clinical guidelines to follow. Recently, artificial intelligence has widely been applied in medical field and produced some exciting results, and we have developed a high-performance artificial intelligence model based on 2369 rectal cancer patients, which showed good discrimination of anastomotic leakage and may reduce the temporary ileostomy rate. Hence, this randomized controlled trail will evaluate the artificial intelligence model for guiding surgical decision-making of performing a temporary ileostomy in patients with rectal cancer who receive anterior resection.

Artificial Intelligence Assists Surgeons' Decision Making

Artificial Intelligence-assisted Decision Making for Temporary Ileostomy: A Prospective Randomized Controlled Trail.

The diagnosis of anastomotic leakage is determined when the passage of fecal material from pelvic drainage tube or the water-soluble contrast agent enema and extra-rectal imaging. Alternatively, anastomotic leakage can be diagnosed when the integrity of the anastomosis is interrupted or the appearance of pelvic abscess next to the anastomosis by computerized tomography (CT) examination or secondary surgical exploration.

Study title	NCT ID	Conditions	Interventions	Eligibility	Organization
Computer Aided Tool for Diagnosis of Neck Masses in Children	NCT05187923	Neck Mass Thyroglossal Du... Branchial Cleft... Dermoid and Epi... Infantile Heman... Teratomas	Artificial Inte...	0 Years - 18 Years	West China Hospital
Artificial Intelligence Assists Surgeons' Decision Making	NCT04999007	Rectal Cancer	Artificial inte...	18 Years - 85 Years	Tongji Hospital
Computer Aided Tool for Diagnosis of Neck Masses in Children	NCT05187923	Neck Mass Thyroglossal Du... Branchial Cleft... Dermoid and Epi... Infantile Heman... Teratomas	Artificial Inte...	0 Years - 18 Years	West China Hospital

Spots Global Cancer Trial Database for artificial intelligence algorithm