Clinical Study on the Evaluation of the Efficacy of Cervical Cancer

NCT ID: NCT06254729

Last Updated: 2024-02-12

Basic Information

• Recruitment Status: NOT_YET_RECRUITING
• Total Enrollment: 4000 participants
• Study Classification: OBSERVATIONAL
• Study Start Date: 2024-02-16
• Study Completion Date: 2030-02-16

Brief Summary

The main objectives of this study are to construct a multi-omics-based prognostic and side-effect prediction model for cervical cancer based on pre-treatment imaging, digital pathology, genomics, proteomics, molecular biology, metabolomics, and intestinal flora characteristics data of cervical cancer patients, combined with patients' clinical information, to guide the precise treatment of cervical cancer patients; and to deeply excavate the characteristics related to recurrent cervical cancer based on time-series multi-omics data. Construct an artificial intelligence auxiliary model for dynamic monitoring of cervical cancer recurrence based on longitudinal multi-omics. To provide a real-time and timely tool for clinical early prediction, early identification, early diagnosis and early intervention of cervical cancer, to prolong the survival time and improve the quality of patients' survival.

1. To realize multi-omics feature extraction of cervical cancer patients before treatment, and build a prognosis and side-effect prediction model of cervical cancer to guide accurate treatment;

2. To make iterative, comprehensive, real-time assessment of the risk of recurrence of cervical cancer based on time-series multi-omics data, and to build an early warning model for early identification and early diagnosis of recurrent cervical cancer;

3. To establish a prognostic and side-effect prediction and risk dynamic assessment model for cervical cancer, to build an intelligent decision support system, to implement the application of prognostic and side-effect prediction and dynamic monitoring model, to further assist in the precise diagnosis and treatment of cervical cancer, and to provide an accurate prognostic tool for identifying, diagnosing, and intervening in cervical cancer during the follow-up process.

Detailed Description

1. Construct a prognosis and side effect prediction model based on pre-treatment multi-omics features of cervical cancer patients.

1. Case selection: According to the overall experimental design, 2800 patients in the training group were used as the training data set, and 1200 patients in the validation group were used as the validation data collection.

2. Model training and tuning: a. Extract the multi-omics features of the training group, carry out self-learning of the features, and form a preliminary cervical cancer prognosis and side-effect prediction model; b. Input the multi-omics data of the validation group into the model, and carry out the structure of the model and the training parameters, and seek for the optimal model structure and training parameters; c. Determine the optimal cervical cancer prognosis prediction and side-effect model.

2.Mining recurrent tumor characteristics based on multi-omics data and constructing a comprehensive assessment model for recurrence risk .

1. Case selection: In accordance with the overall experimental design, 2800 patients in the training group were used as the training dataset, and 1200 patients in the validation group were collected as the validation data.

2. Model training and tuning: a. The multi-omics data features of the training group before the diagnosis of recurrence in previous follow-up visits are used to carry out self-learning of the features, assess the risk of tumor recurrence based on multi-omics features in the course of previous follow-up visits, form a dynamic, real-time recurrence risk assessment model, and derive a comprehensive risk value for the decision-making of recurrence intervention; b. Multi-omics features related to the previous follow-up visits of the validation group before the diagnosis of recurrence are inputted into the model, and the iterative time-series recurrence risk assessment is carried out on the patients. time-series recurrence risk iterative assessment of patients to assess the diagnostic performance of the model; c. Adjust the structure and training parameters of the model according to the segmentation accuracy of the validation group to seek the optimal model structure and training parameters; d. Use technical means such as data augmentation and other technical means to think of enlarging the sample size to improve the segmentation accuracy; e. Determine the optimal risk assessment model.

3. Establish the prognosis and side-effect prediction and dynamic monitoring system of cervical cancer.

a. Docking the above constructed model with the outpatient system to construct a prognosis and side reaction prediction and dynamic monitoring system in the process of cervical cancer diagnosis and treatment; b. Constructing an intelligent decision support system through the prognosis and side reaction prediction and risk dynamic assessment model, implementing the application of recurrence prediction and dynamic monitoring system, and assisting the clinicians to make decisions on intervention measures.

Conditions

Uterine Cervical Neoplasms

Study Design

• Observational Model Type: COHORT
• Study Time Perspective: PROSPECTIVE

Study Groups

training group

The training group is used to train the model.

Observational study

Intervention Type: OTHER

Our study does not have any exposure factors.

validation group

The validation group is used to evaluate model performance.

Observational study

Intervention Type: OTHER

Our study does not have any exposure factors.

Interventions

Observational study

Our study does not have any exposure factors.

Intervention Type: OTHER

Eligibility Criteria

Inclusion Criteria

• Pathology: patients with pathologically confirmed cervical cancer
• Location: primary tumor of the cervix

Exclusion Criteria

• Patients with no prior radiation therapy
• Patients without treatment
• Patients without regular follow-up

• Minimum Eligible Age: 18 Years
• Eligible Sex: FEMALE
• Accepts Healthy Volunteers: Yes

Sponsors

Gansu Maternal and Child Health Hospital

UNKNOWN

Sponsor Role: collaborator

Hanzhong Central Hospital

OTHER

Sponsor Role: collaborator

First Affiliated Hospital Xi'an Jiaotong University

OTHER

Sponsor Role: lead

Responsible Party

Responsibility Role: SPONSOR

Principal Investigators

Jinlu Ma

Role: STUDY_CHAIR

First Affiliated Hospital of Xian Jiaotong University

Central Contacts

Jinlu Ma, Doctor

Role: CONTACT

majinlu@xjtufh.edu.cn

18992842959

Mengjiao Cai, Doctor

Role: CONTACT

664642357@qq.com

15339267236

Other Identifiers

YXJLRH2022039

Identifier Type: -

Identifier Source: org_study_id