Research and Development of an Artificial Intelligence Technology System for Digital Pathological Diagnosis and Therapeutic Effect Prediction Based on Multimodal Data Fusion of Common Tumors and Major Infectious Diseases in the Respiratory System Using Deep Learning Technology.
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- Artificial Intelligence
- Sponsor
- Wuhan Union Hospital, China
- Enrollment
- 1000
- Locations
- 1
- Primary Endpoint
- The outcome of clinical diagnosis of suspected patients with COVID-19 (Positive/Negative).
- Status
- Recruiting
- Last Updated
- 4 years ago
Overview
Brief Summary
To improve accurate diagnosis and treatment of common malignant tumors and major infectious diseases in the respiratory system, we aim to establish a large medical database that includes standardized and structured clinical diagnosis and treatment information such as electronic medical records, image features, pathological features, and multi-omics information, and to develop a multi-modal data fusion-based technology system for individualized intelligent pathological diagnosis and therapeutic effect prediction using artificial intelligence technology.
Detailed Description
The main aims are as follows: 1. To establish a medical big data platform for multi-modal information fusion of common tumors and major infectious diseases (lung cancer/pulmonary nodules, tuberculosis, and COVID-19) based on the existing pathological image features and clinical multi-omics information database: The medical big data platform supports the acquisition of the patient's clinical electronic medical records (including routine clinical detection), full view digital section of pathological image data, medical imaging (CT, MRI, ultrasound, nuclear medicine, etc.), multiple omics data (genome, transcriptome, and metabolome, proteomics) omics data, etiology, pathology, and associated graphic data reports and multimodal medical treatment data. We aim to realize the storage, sharing, fusion computing, privacy protection, and security supervision of multi-modal and cross-scale biomedical big data. Our work will open up key business processes and links across regions, across hospitals, between different terminals, between hospitals and doctors, and between departments, so as to promote continuous data accumulation and knowledge precipitation in hospitals and promote medical collaboration. 2. To create a multimodal information fusion database with pathologic features, imaging features, multi-omics (pathologic, genomic, transcriptome, metabolome, proteomics, etc.), and clinical information of patients at different stages of lung cancer/pulmonary nodules, tuberculosis, and COVID-19. The database scale includes multimodal data of at least 600 lung cancer/pulmonary nodules, 200 tuberculosis, and 200 COVID-19 patients. Moreover, there will be more than 10 biomarkers significantly related to the diagnosis and treatment of patients with lung cancer/pulmonary nodules, tuberculosis and COVID-19 were excavated through association analysis, providing parameters for artificial intelligence model construction. 3. We will make use of artificial intelligence technology to create the multi-modal medical big data cross-analysis technology and the above disease individualized accurate diagnosis and curative effect prediction models. In order to solve the three key problems of multi-modal data fusion mining, such as unbalanced, small sample size, and poor interpretability, we will establish an ARTIFICIAL intelligence recognition algorithm for image images and pathological images, and use image processing and deep learning technologies to mine multi-level depth visual features of image data and pathological data. In addition, we will use bioinformatics analysis algorithms to conduct molecular network mining and functional analysis of molecular markers at the level of multiple omics technologies (pathologic, genomic, transcriptome, metabolome, proteome, etc.).
Investigators
Yang Jin
Department of Respiratory and Critical Care Medicine
Wuhan Union Hospital, China
Eligibility Criteria
Inclusion Criteria
- •Participants with the clinical diagnosis of lung cancer, pulmonary tuberculosis, and COVID-
- •Participants that have signed informed consent.
- •Participants \>= 18 years old and \< 90 years old.
- •Participants with detailed electronic medical records, image records, pathological records, multi-omics information, and other important clinical diagnostic information.
- •Healthy participants with no clinical diagnosis of lung cancer, pulmonary tuberculosis, and COVID-19.
Exclusion Criteria
- •Participants \< 18 years old.
- •Participants with primary clinical and pathological data missing.
- •Participants lost to follow-up.
- •Participants with too poor medical image quality to perform segment and mark ROI accurately.
Outcomes
Primary Outcomes
The outcome of clinical diagnosis of suspected patients with COVID-19 (Positive/Negative).
Time Frame: 2021-2024
The outcome of clinical diagnosis of patients with COVID-19 (Positive/Negative).
Whole genome sequencing of blood samples
Time Frame: 2021-2024
Whole-genome sequencing of blood samples before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. Whole-genome sequencing is mainly used to find single nucleotide polymorphisms (SNPs), copy number variations, and insertions/deletions.
The outcome of clinical diagnosis of suspected patients with pulmonary tuberculosis (Positive/Negative).
Time Frame: 2021-2024
The outcome of clinical diagnosis of patients with pulmonary tuberculosis (Positive/Negative).
Treatment response of anti-cancer therapy at first evaluation in patients with lung cancer/pulmonary nodules (CR, PR, PD, SD).
Time Frame: 2021-2024
The treatment response of anti-cancer therapy at first evaluation in patients with lung cancer/pulmonary nodules follows The Response Evaluation Criteria In Solid Tumors (RECIST version 1.1) from the World Health Organization (WHO). The evaluation index is as follows. CR (complete response): Disappearance of all target lesions and reduction in the short axis measurement of all pathologic lymph nodes to ≤10 mm. PR (partial response): 30% decrease in the sum of the longest diameter of the target lesions compared with baseline. PD (progressive disease):≥20% increase of at least 5 mm in the sum of the longest diameter of the target lesions compared with the smallest sum of the longest diameter recorded OR The appearance of new lesions, including those detected by FDG-PET (fludeoxyglucose positron emission tomography). SD (stable disease): Neither PR nor PD.
Progression free survival
Time Frame: 2021-2024
The time interval between the date of treatment initiation and disease progression (Months) of patients with lung cancer/pulmonary nodules.
Whole-genome sequencing of tissue samples
Time Frame: 2021-2024
Whole-genome sequencing of tissue samples after surgery in patients with lung cancer/pulmonary nodular and tuberculosis. Whole-genome sequencing is mainly used to find single nucleotide polymorphisms (SNPs), copy number variations, and insertions/deletions.
Transcriptome sequencing of blood samples
Time Frame: 2021-2024
Transcriptome sequencing of blood samples before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. The collection of all transcripts, including messenger RNA, ribosomal RNA, transport RNA, and non-coding RNA.
Proteomics of blood samples
Time Frame: 2021-2024
Proteomics of blood specimens before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. Unlabeled proteomics technology based on the timsTOF Pro ion mobility platform for differential quantitative proteomics analysis using data-dependent acquisition - Synchronous cumulative continuous fragmentation (ddaPASEF) scan mode.
The outcome of clinical diagnosis of suspected patients with lung cancer/pulmonary nodular (Benign/Malignant nodule).
Time Frame: 2021-2024
The outcome of clinical diagnosis of patients with lung cancer/pulmonary nodular (Benign/Malignant nodule). ① Benign nodule ② Malignant neoplasm/nodule: squamous cell carcinoma, adenocarcinoma, small cell carcinoma, and large cell carcinoma.
Treatment response of anti-inflammation and antiviral therapy at first evaluation in patients with COVID-19 (effective/ineffective treatment).
Time Frame: 2021-2024
Treatment response of anti-inflammation and antiviral therapy at first evaluation in patients with COVID-19 (effective/ineffective treatment). effective treatment： Improved total time to recovery, resolution of fever, cough remission, and pneumonia severity. ineffective treatment： The above conditions have not improved or patients go die.
Transcriptome sequencing of tissue samples
Time Frame: 2021-2024
Transcriptome sequencing of tissue samples after surgery in patients with lung cancer/pulmonary nodular and tuberculosis. The collection of all transcripts, including messenger RNA, ribosomal RNA, transport RNA, and non-coding RNA.
Transcriptome sequencing of urine samples
Time Frame: 2021-2024
Transcriptome sequencing of urine specimens before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. The collection of all transcripts, including messenger RNA, ribosomal RNA, transport RNA, and non-coding RNA.
Proteomics of tissue samples
Time Frame: 2021-2024
Proteomicstissue samples after surgery in patients with lung cancer/pulmonary nodular and tuberculosis. Unlabeled proteomics technology based on the timsTOF Pro ion mobility platform for differential quantitative proteomics analysis using data-dependent acquisition - Synchronous cumulative continuous fragmentation (ddaPASEF) scan mode.
Proteomics of exhaled air condensate samples
Time Frame: 2021-2024
Proteomics of exhaled air condensate specimens before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. Unlabeled proteomics technology based on the timsTOF Pro ion mobility platform for differential quantitative proteomics analysis using data-dependent acquisition - Synchronous cumulative continuous fragmentation (ddaPASEF) scan mode.
Overall survival
Time Frame: 2021-2024
The time interval between the date of diagnosis and death (Months) of patients with lung cancer/pulmonary nodules.
Whole genome sequencing of exhaled air condensate samples
Time Frame: 2021-2024
Whole-genome sequencing of exhaled air condensate samples before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. Whole-genome sequencing is mainly used to find single nucleotide polymorphisms (SNPs), copy number variations, and insertions/deletions.
Metabolomics of tissue samples
Time Frame: 2021-2024
Metabolomics of tissue samples after surgery in patients with lung cancer/pulmonary nodular and tuberculosis. Non-target metabolites are generally analyzed qualitatively and quantitatively based on LC-MS technology for metabolites in samples, and identified by matching primary and secondary information with local self-built databases and commercial standard databases.
Treatment response of antituberculous bacilli and anti-inflammation therapy at first evaluation in patients with pulmonary tuberculosis.
Time Frame: 2021-2024
Treatment cure： patients with bacteriologically confirmed TB at the beginning of treatment who were smear- or culture-negative in the last month of treatment and on at least one previous occasion. Treatment completer: patients who completed treatment without evidence of failure but with no record to show that sputum smear or culture results in the last month of treatment and on at least one previous occasion were negative. Treatment success: The sum of cured and treatment completed. Treatment failure: patients whose sputum smear or culture is positive at month 5 or later during treatment. Treatment relapse: Patients who were declared cured or treatment completed at the end of their most recent course of TB treatment, and are now diagnosed with a recurrent episode of TB. This can be either a true relapse or a new episode of TB caused by reinfection. Patient died.
Metabolomics of blood samples
Time Frame: 2021-2024
Metabolomics of blood specimens before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. Non-target metabolites are generally analyzed qualitatively and quantitatively based on LC-MS technology for metabolites in samples, and identified by matching primary and secondary information with local self-built databases and commercial standard databases.
Metabolomics of exhaled air condensate samples
Time Frame: 2021-2024
Metabolomics of exhaled air condensate specimens before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. Non-target metabolites are generally analyzed qualitatively and quantitatively based on LC-MS technology for metabolites in samples, and identified by matching primary and secondary information with local self-built databases and commercial standard databases.
Whole genome sequencing of urine samples
Time Frame: 2021-2024
Whole-genome sequencing of urine specimens before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. Whole-genome sequencing is mainly used to find single nucleotide polymorphisms (SNPs), copy number variations, and insertions/deletions.
Transcriptome sequencing of exhaled air condensate samples
Time Frame: 2021-2024
Transcriptome sequencing of exhaled air condensate specimens before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. The collection of all transcripts, including messenger RNA, ribosomal RNA, transport RNA, and non-coding RNA.
Metabolomics of urine samples
Time Frame: 2021-2024
Metabolomics of urine specimens before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. Non-target metabolites are generally analyzed qualitatively and quantitatively based on LC-MS technology for metabolites in samples, and identified by matching primary and secondary information with local self-built databases and commercial standard databases.
Proteomics of urine samples
Time Frame: 2021-2024
Proteomics of urine specimens before and after treatment in patients with lung cancer/pulmonary nodular, tuberculosis, and COVID-19. Unlabeled proteomics technology based on the timsTOF Pro ion mobility platform for differential quantitative proteomics analysis using data-dependent acquisition - Synchronous cumulative continuous fragmentation (ddaPASEF) scan mode.
Secondary Outcomes
- weight (kilograms)(2021-2024)
- height (meters)(2021-2024)
- blood pressure (mmHg)(2021-2024)
- sex (male/female)(2021-2024)
- C-reactive protein in blood(mg/L)(2021-2024)
- total protein in blood(umol/L)(2021-2024)
- glutamic-pyruvic transaminase in blood(U/L)(2021-2024)
- prothrombin time in blood(PT)(2021-2024)
- thrombin time in blood (TT)(2021-2024)
- leucocytes in blood(×109/L)(2021-2024)
- heart rate in each minute(2021-2024)
- age (years)(2021-2024)
- Forced vital capacity (FVC)(2021-2024)
- peak expiratory flow (PEF)(2021-2024)
- St. George's Respiratory Questionnaire(SGRQ)(2021-2024)
- fibrinogen in blood(g/L)(2021-2024)
- neutrophils in blood(×109/L)(2021-2024)
- monocytes in blood(×109/L)(2021-2024)
- Nervous specific enolase (U/mL)(2021-2024)
- forced expiratory volume in one second (FEV1)(2021-2024)
- carbon monoxide diffusion capacity (DLCO)(2021-2024)
- Active part thrombin time in blood(APTT)(2021-2024)
- lymphocytes in blood(×109/L)(2021-2024)
- Squamous Cell Carcinoma Antigen(ug/L)(2021-2024)
- Cancer antigen 125 (U/mL)(2021-2024)
- eosinophils in the blood(×109/L)(2021-2024)
- Tissue Polypeptide Specific Antigen(ug/L)(2021-2024)
- Bombesin (U/mL)(2021-2024)
- β2-microglobulin (U/mL)(2021-2024)
- aspartate aminotransferase in blood(U/L)(2021-2024)
- D-dimer in blood(ug/L)(2021-2024)
- platelets in the blood(×109/L)(2021-2024)
- Carcinoembryonic Antigen (ug/L)(2021-2024)
- Cancer antigen 15-3 (U/mL)(2021-2024)
- Cytokeratin 19 fragment (ug/L)(2021-2024)
- the outcome of Etiological detection(2021-2024)