Hemorrhage Stroke Decision Making Model Based Deep Learning (BrainHemoAI System)

Официальное название

Construction of an Integrated Intelligent Model for Spontaneous Intracerebral Hemorrhage Based on Deep Learning

Обзор

Although hemorrhagic stroke also has the characteristics of high mortality and disability rates, and constitutes a major public health problem worldwide, there is a relative lack of in-depth research teams for hemorrhagic stroke in China. The current preoperative imaging evaluation of spontaneous cerebral hemorrhage is still limited to the traditional Tada formula, and there are subjective differences in diagnosis among different doctors, making it difficult to achieve homogenization in clinical decision-making. Hemorrhagic stroke is a common and frequently occurring disease in Jiangxi Province. Therefore, establishing a new diagnosis and treatment system focused on hemorrhagic stroke can not only fill the research gap in this field in China, improve the accuracy and homogeneity of hemorrhagic stroke diagnosis and treatment, but also promote related research progress to reduce the mortality and disability rates of this disease and improve the clinical prognosis of patients.

Подробное описание

Hemorrhagic stroke is a serious cerebrovascular disease, accounting for about 20% of all strokes. It refers to cerebral hemorrhage and subarachnoid hemorrhage caused by intracranial vascular diseases such as intracranial aneurysms, cerebral and spinal vascular malformations and moyamoya disease under the effect of blood flow. It has the characteristics of high incidence rate, high disability rate and high mortality rate, and has caused huge economic burden to patients, families and society.

Hemorrhagic stroke is one of the high-risk diseases in Jiangxi Province, and has become a major public health challenge and a key social issue that urgently needs to be addressed. On the one hand, the diagnosis and treatment of hemorrhagic stroke have a certain degree of complexity, involving multiple disciplines, especially neurology and endocrinology, which have established multiple diagnostic, evaluation, treatment, and rehabilitation systems. Different systems have different focuses, but limited by the level of understanding of the disease, there have been only basic treatment principles for decades, and there has been no breakthrough in specific treatment plans. On the other hand, with the development of the economy and the improvement of living standards, clinical physicians and patients not only focus on the survival rate after hemorrhagic stroke, but also pay more attention to neurological function recovery and long-term quality of life. Due to the limitations of detection technology in the past, it was difficult to accurately describe diseases and truly develop individualized diagnosis and treatment plans, resulting in significant differences in patient prognosis. How to leverage advances in diagnosis and treatment technology to ultimately achieve precision, individualization, and homogenization in the diagnosis and treatment of hemorrhagic stroke is a key focus for the future.

Although hemorrhagic stroke also has the characteristics of high mortality and disability rates, and constitutes a major public health problem worldwide, there is a relative lack of in-depth research teams for hemorrhagic stroke in China. The current preoperative imaging evaluation of spontaneous cerebral hemorrhage is still limited to the traditional Tada formula, and there are subjective differences in diagnosis among different doctors, making it difficult to achieve homogenization in clinical decision-making. Hemorrhagic stroke is a common and frequently occurring disease in Jiangxi Province. Therefore, establishing a new diagnosis and treatment system focused on hemorrhagic stroke can not only fill the research gap in this field in China, improve the accuracy and homogeneity of hemorrhagic stroke diagnosis and treatment, but also promote related research progress to reduce the mortality and disability rates of this disease and improve the clinical prognosis of patients.

Вмешательства

• Диагностический тест Large language model
  Automatical diagnosis, treatment decision-making, and risk prediction after spontaneous intracerebral hemorrhage via a trained deep learning larger language model.

Первичные конечные точки

• Area Under Curve [Срок оценки: 90-day and 180-day]

Вторичные конечные точки (1)

• Sensitivity ,Specificity,True Positive Rate,False Positive Rate [Срок оценки: Baseline (admission), 24 hours postoperatively, 3 days postoperatively, 7 days postoperatively, discharge, 90-day follow-up, 180-day follow-up]

Критерии участия

Критерии включения

• Age >= 8 years old;
• Patients diagnosed with spontaneous hemorrhagic stroke based on medical history and auxiliary examinations;
• Received non-contrast computed tomography (NCCT) in the outpatient or emergency department;
• Treated in accordance with standard clinical guidelines during hospitalization;
• Have complete clinical data.

Критерии исключения

• Had undergone surgical treatment in another hospital before admission;
• Was in a state of shock upon admission;
• Had severe heart, liver, or kidney dysfunction or other life-threatening systemic diseases;
• Died during hospitalization;
• Had an expected lifespan of less than six months or was unable to complete the study follow-up for other reasons.

Критерии приведены из реестра в оригинале (на английском). Окончательную оценку соответствия проводит исследовательский центр.

Здоровые добровольцы: Да

Дизайн исследования

Модель наблюдения

Когортное

Центры проведения

Китай · 1 центр

• The Second Affiliated Hospital of Nanchang University — Nanchang

Публикации

• Du S, Wu Y, Tao J, Shu L, Yan T, Xiao B, Lv S, Ye M, Gong Y, Zhu X, Hu P, Wu M. Development and Validation of Machine Learning Models for Outcome Prediction in Patients with Poor-Grade Aneurysmal Subarachnoid Hemorrhage Following Endovascular Treatment. Ther Clin Risk Manag. 2025 Mar 7;21:293-307. doi: 10.2147/TCRM.S504745. eCollection 2025. PMID 40071129
• Hu P, Wu Y, Yan T, Shu L, Liu F, Xiao B, Ye M, Wu M, Lv S, Zhu X. Deep learning-based quantification of total bleeding volume and its association with complications, disability, and death in patients with aneurysmal subarachnoid hemorrhage. J Neurosurg. 2024 Mar 29;141(2):343-354. doi: 10.3171/2024.1.JNS232280. Print 2024 Aug 1. PMID 38552240
• Hu P, Yan T, Xiao B, Shu H, Sheng Y, Wu Y, Shu L, Lv S, Ye M, Gong Y, Wu M, Zhu X. Deep learning-assisted detection and segmentation of intracranial hemorrhage in noncontrast computed tomography scans of acute stroke patients: a systematic review and meta-analysis. Int J Surg. 2024 Jun 1;110(6):3839-3847. doi: 10.1097/JS9.0000000000001266. PMID 38489547
• Hu P, Zhou H, Yan T, Miu H, Xiao F, Zhu X, Shu L, Yang S, Jin R, Dou W, Ren B, Zhu L, Liu W, Zhang Y, Zeng K, Ye M, Lv S, Wu M, Deng G, Hu R, Zhan R, Chen Q, Zhang D, Zhu X. Deep learning-assisted identification and quantification of aneurysmal subarachnoid hemorrhage in non-contrast CT scans: Development and external validation of Hybrid 2D/3D UNet. Neuroimage. 2023 Oct 1;279:120321. doi: 10.1016 PMID 37574119

Идентификаторы

NCT: NCT07570680 · IIT-O-2025-054

Первоисточники (государственные реестры)

• ClinicalTrials.gov (NIH, США)

Открыть это исследование на ClinicalTrials.gov ↗