View clinical trials related to Predictive Cancer Model.
Filter by:The goal of this prospective observational cohort study is to validate a previously developed pancreatic cancer risk prediction algorith (the PRISM model) using electronic health records from the general population. The main questions it aims to answer are: - Will a pancreatic cancer risk model, developed on routine EHR data, reliably and accurately predict pancreatic cancer in real-time? - What is the average time from model deployment and risk prediction, to the date of pancreatic cancer development and what is the stage of pancreatic cancer at diagnosis? The risk model will be deployed on data from individuals eligible for the study. Each individual will be assigned a risk score and tracked over time to assess the model's discriminatory performance and calibration.
It is known that the development of colorectal adenoma is dependent on the appearance of somatic mutations in protooncogenes and tumor suppressor genes. Based on our previous mutation analyses of 120 patients with high-risk adenoma removed by enbloc resection with subsequent colonoscopy after 1 year, there is a correlation between mutation in exon 7 of the TP53 gene and risk of early metachronous lesions development. The results also indicate that mutation phenotype (mutation profile and burden) of all lesions detected on index colonoscopy can determine risk of metachronous lesions. As not all synchronous lesions were analyzed and the surveillance colonoscopy interval was less than 3 years, this assumption could not be confirmed. In this study it is planned to perform mutation analysis of all synchronous lesions in 200 patients and correlate the data with appearance of metachronous lesions after 1, 3 and 5 years. Moreover, the mutation profile of all metachronous lesions developed during the 5 years of surveillance will be determinated and compared with mutation profile of index lesions from the same localization to verify their common biological origin. This all could help personalize the surveillance program in terms of reduction of the burden on the patient and endoscopic workplaces and risk of developing colorectal cancer in a particular patient.
The goal of this clinical trial is to assess the (cost-)effectiveness of a personalised risk assessment tool (PERSARC) to increase patients' knowledge about risks and benefits of treatment options and to reduce decisional conflict in comparison with usual care in high-grade extremity Soft-Tissue Sarcoma-patients. High-grade (2-3) extremity Soft-Tissue Sarcoma patients (>= 18 years) will either receive standard care (control group) or care with the use of PERSARC; i.e. PERSARC will be used in multidisciplinary tumour boards to guide treatment advice and in consultation in which the oncological/orthopaedic surgeon informs the patient about his/her diagnoses and discusses the benefits and harms of all relevant treatment options (intervention group)
This study will assess the ability of the Known Medicine platform to predict the efficacy of certain cancer drug treatments and to validate that tumor organoid drug sensitivity is representative of patient treatment outcomes.
It is a prospective, observational cohort study of patients with dense breast tissue. The study was based on the radiomics and other clinicopathological information of patients to establish the diagnostic system for breast disease by using artificial intelligence.
Platinum-sensitive is an important basis for the treatment of recurrent epithelial ovarian cancer (EOC) without effective methods to predict.We aimed to develop and validate the EOC deep learning system to predict the platinum-sensitive of EOC patients through analysis of enhanced magnetic resonance imaging (MRI) images before initial treatment.Ninety-three EOC patients received platinum-based chemotherapy (>= 4 cycles) and debulking surgery from Sun Yat-sen Memorial Hospitalin China from January 2011 to January 2020 were enrolled. This deep-learning EOC signature achieved a high predictive power for platinum-sensitive, and the signature based on MRI whole volume is better than that on primary tumor area only.
The purpose of this study was to investigate whether the combined radiomic model based on radiomic features extracted from focus and perifocal area (5mm) can effectively improve prediction performance of distinguishing precancerous lesions from early-stage lung adenocarcinoma, which could assist clinical decision making for surgery indication. Besides, response and long term clinical benefit of immunotherapy of advanced NSCLC lung cancer patients could also be predicted by this strategy.
This is a cross-sectional study aimed at identifying factors which best predicts patients at high risk of colorectal cancer or colorectal adenomas and to develop a risk prediction model.
This study aims to investigate the feasibility and efficiency of CT radiomic analysis which serves as a high through-put analytical strategy applied to image big-data resource in evaluating and predicting the response of immunotherapeutics. A multi-center retrospective diagnostic test has been designed for this aim to compare the predictive performance of clinical model, qualitative model incorporating semantic CT features and image-based quantitative radiomic model. The reference standard of therapeutic effect is determined by the latest evaluation result utilizing iRECIST within 365 days after recruited. This study intends to enroll 400 participates who had been diagnosed with advanced somatic solid tumor confirmed by histo- or cyto-pathological examination and were planning to receive immunotherapy.
In the previous study, the investigator established a predictive model for non-sentinel lymph node involvement in early breast cancer (cT1-2cN0, 1-2 SLNs involvement). To validation the clinical value of the model, the investigator design a prospectively research using the model guiding for further axillary lymph node dissection in SLN-positve early breast cancer.