Pancreatic Cancer, Pancreatic Cystic Lesions
Conditions
Brief summary
This international, multicenter retrospective study aims to develop a deep learning (DL)-based predictive model to identify malignant transformation in pancreatic cystic lesions, improving upon current clinical guidelines. The model will integrate clinical, biochemical, and multimodal imaging data. Several 3D convolutional neural networks will be trained using advanced preprocessing, data augmentation, and hybrid fusion techniques. Model performance will be compared to that of existing international guidelines. The study involves no additional procedures for patients and adheres to strict data anonymization and privacy regulations.
Interventions
PROCEDUREPancreatic surgery
Pancreatic resective surgery performed for pancreatic cystic lesions with high risk of malignant degeneration based on clinical, biochemical, and/or radiological features following current guidelines on pancreatic cystic lesions management.
Sponsors
Centre Hospitalier Universitaire de Nice
Study design
Observational model
COHORT
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Patients diagnosed with PCL(s ) who underwent pancreatic surgery in one of the participant centers. Surgical indication must adhere to at least one of current guidelines on PCLs management (6), based on clinical, biochemical, and radiological (MR and/or EUS) features. * Pancreatic surgery B83performed for supposed increased risk of cyst(s) malignant degeneration following current guidelines on PCLs management (6). * Absence of clinical, biochemical, radiological, and anatomopathological evidence of pancreatic cancer at pancreatic surgery. * Non-opposition to the anonymous data processing by the included patients.
Exclusion criteria
* Patients presenting with evidence of pancreatic cancer at surgery. * PCL(s) diagnosis and treatment performed without one between EUS and pancreatic MR. surgery performed in the absence of the criteria proposed by current guidelines. * Unavailability of both preoperative EUS and pancreatic MR data. * Unavailability of postoperative PCL(s) anatomopathological analysis results. * SBO diagnosis performed without CT-scan.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Prediction of malignant degeneration of pancreatic cystics lesions | 90 days from patients hospital discharge. | Predict the presence of malignant degeneration (defined as: high grade dysplasia, in situ PADC, or T1 PADC) in pancreatic cystic lesion(s) using artificial intelligence model based on clinical, biochemical, and radiological features. This will be measured through Area Under the Receiver Operator Characteristic curve (AUROC) assesment. AUROC varies between 0.5 and 1, corresponding to no class separation capacity and full class separation capacity, respectively. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Precision of performance evaluation | 90 days from patients hospital discharge. | The number of true positives divided by all the positive predictions (true positives and false positives). It varies between 0 (no correct prediction) to 1 (full correct predictions). |
| Recall of performance evaluation | 90 days from patients hospital discharge. | The number of true positives divided by the actual positive instances in the dataset (true positives and false negatives). It varies between 0 (no correct prediction) to 1 (full correct predictions). |
| Balanced accuracy | 90 days from patients hospital discharge. | the aritmethic mean of sensitivity and specificity. It varies between 0 (no correct prediction) to 1 (full correct predictions). |
| Accuracy of performance evaluation | 90 days from patients hospital discharge. | the number of true positives and true negatives among all predictions. It varies between 0 (no correct prediction) to 1 (full correct predictions). |
| Confusion matrix | 90 days from patients hospital discharge. | A visual representation of true positives, false positives, true negatives, and false negatives. It is depicted through a table. |
| Log-loss | 90 days from patients hospital discharge. | It indicates how close the prediction probability is to the corresponding actual/true value (0 or 1 in case of binary classification). The more the predicted probability diverges from the actual value, the higher is the log-loss value. |
| Cohen's Kappa | 90 days from patients hospital discharge. | A metric used to measure the level of agreement between two raters which can be a useful tool to gauge the performance of a classification model. It accounts for the fact that the raters may happen to agree on some items purely by chance. It varies between 0 (no correct prediction) to 1 (full correct predictions). |
| F1-score | 90 days from patients hospital discharge. | It combines precision and recall. It ranges from 0-100%, and a higher F1 score denotes a better quality classifier. |
Contacts
Primary ContactAndrea CHIERICI
Outcome results
None listed