A Clinical Evaluation of AI Solutions Developed in the CHAIMELEON Project for Cancer: Prostate, Lung, Breast, Colon and Rectum

An in Silico External Clinical Validation of AI Solutions for Cancer Management in the CHAIMELEON Project. Applied to 4 Target Types of Cancer (Lung, Breast, Prostate and Colorectal), Collected Through the Routine Delivery of Health Care With no Enrolment Conditinos (Real World Data).

The goal of this observational study is to see how useful an experimental viewer and AI solutions are for clinicians in their daily work. The investigators want to find out if the AI helps clinicians interpret medical images for different types of cancer.

The AI solutions aim to:

• Classify whether prostate cancer is low or high risk
• Classify the histological subtype in breast cancer
• Estimate the life expectancy of patients with lung cancer
• Determine the size of colon cancer, lymph node involvement and the possibility of metastasis..
• Assess the invasion of sorrounding tissues in the case of rectum cancer. The study will involve clinicians from various centres who will review a set of cases not previously analysed by the AI. Clinicians will do this in two phases: first using only their own expertise and then with the help of the AI solutions.

The technical team want to see if the AI solutions assist clinicians and could become useful in the everyday clinical practice. Clinicians will complete a survey to share their feedback on the usability of the platform and how helpful the AI solutions are.

Study Overview

• Status: Completed
• Conditions: Breast Cancer; Prostate Cancer; Colon Cancer; Lung Cancer, Non-Small Cell; Rectum Cancer
• Intervention / Treatment: Other: Risk in prostate cancer; Other: Life expectancy in lung cancer; Other: Histological subtype; Other: Staging of colon cancer; Other: invasion in rectum cancer

Detailed Description

In order to conduct a robust clinical validation, the investigators have designed a study on the required sample size. The study is design to evaluate the role of an AI-assisted tool as a support for improving the daily clinical work. The investigators used an online website (https://statulator.com/SampleSize/ss2PP.html) for the calculation and use the "paired binary proportions" option. Using the case of prostate cancer, the investigators want to compare the probability of correct risk classification in prostate cancer by clinicians alone and/or guided by AI. The study will have a significance (α) = 0.05; power (β) = 80%; the analysis will be "two sided" and with equal group sizes.

An 10% improvement in cancer risk classification was observed when clinicians had access to an AI tool solution (Yilmaz et al.,). In addition, the authors reported that expert readers had an accuracy rate of 81% compared to 69% for novice readers when determining the Gleason score of lesions (a medical term used in pathology to classify the aggressiveness of cells in a tumour). The authors also assumed an 80% correlation between paired observations.

As a result, at least 60 new cases would be needed to evaluate the performance of the AI tool.

• Study Type: Observational
• Enrollment (Actual): 300

Contacts and Locations

Study Locations

• Spain
  • Valencia, Spain, 46026
    • Hospital Universitario y Politécnico La Fe

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients with a cancer diagnosis of prostate, breast, lung and colorectal from the University and politechnic Hospital la Fe, Valencia.

Description

Inclusion Criteria:

• patients with an histological confirmation of cancer diagnosis (prostate, lung, breast, colon or rectum)
• availability of radiological images (MR for prostate and rectum, CT for lung and colon or mammographys for breast).
• enough follow up (12 months for prostate, breast and rectum), 18 months for lung, and 24 months for colon.

Exclusion Criteria:

• patients with incomplete or low quality data (radiological, pathological or uncomplete clinical data necessary for the ground truth)

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Group 1: Evaluation with Medical expertise only; Evaluation of different medical images of people with 5 types of cancer using their own expertise.	Other: Risk in prostate cancer; the prediction involves the classification of the prostate cancer according to the level of prostatic antigen (PSA), the biopsy classification of the aggressiveness of the tumour, and also the localisation of the tumour; Other: Life expectancy in lung cancer; Clinicians will evaluate life expectancy in lung cancer using CTs, together with some clinical information.; Other: Histological subtype; An assessment by pathology of the subtype of breast tumour; Other: Staging of colon cancer; classify size, lymph node involvement and possibility of metastasis in medical images (computerized tomosynthesis) of thorax and pelvis region; Other: invasion in rectum cancer; assess whether vascular extramural o mesorectal fascia has been invaded in the tumour using magnetic resonance medical images taken at diagnosis in the pelvic region
Group 2: Evaluation with the support of AI solutions; Evaluation of different medical images of people with 5 types of cancer guided by the AI solutions developed.	Other: Risk in prostate cancer; the prediction involves the classification of the prostate cancer according to the level of prostatic antigen (PSA), the biopsy classification of the aggressiveness of the tumour, and also the localisation of the tumour; Other: Life expectancy in lung cancer; Clinicians will evaluate life expectancy in lung cancer using CTs, together with some clinical information.; Other: Histological subtype; An assessment by pathology of the subtype of breast tumour; Other: Staging of colon cancer; classify size, lymph node involvement and possibility of metastasis in medical images (computerized tomosynthesis) of thorax and pelvis region; Other: invasion in rectum cancer; assess whether vascular extramural o mesorectal fascia has been invaded in the tumour using magnetic resonance medical images taken at diagnosis in the pelvic region

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Usability of experimental viewer with AI tools	Usability of the platform was assessed at the end of each of the two study phases: a standard clinical phase (without artificial intelligence assistance) and a second phase assisted by AI models. Participants evaluated their experience using a 5-point Likert scale, where 1 indicated "strongly disagree" and 5 indicated "strongly agree," in response to statements regarding ease of use, interface clarity, system efficiency, overall satisfaction, and other aspects related to user interaction with the platform. This assessment enabled a comparison of user perceptions of the viewer's usability under both conventional clinical conditions and AI-assisted conditions. Higher scores reflect a better user experience.	5 months
Utility of experimental medical images viewer	The utility of the experimental viewer was assessed by comparing clinicians' diagnostic accuracy and time spent when using the system alone versus with AI assistance. Higher accuracy and reduced interpretation time were considered indicators of greater utility. The goal was to determine whether the viewer enhances clinical decision-making, streamlines workflows, and supports better patient care. Additional data such as clinician gender, specialty, and experience were collected to enable subgroup analyses. Statistical evaluations included confusion matrices to assess diagnostic performance, and Sankey flow diagrams to visualize changes in decision-making between unaided and AI-assisted phases. These tools provided a comprehensive understanding of the viewer's practical benefit in real clinical scenarios.	5 months

Collaborators and Investigators

• Sponsor: Instituto de Investigacion Sanitaria La Fe
• Collaborators: University of Pisa; Charite University, Berlin, Germany; IRCCS Policlinico S. Donato; University Hospital Rijeka; University of Messina; Istanbul Medipol University Hospital; Osakidetza; Hospitales Universitarios Virgen del Rocío; Centro Hospitalar do Porto; National Cancer Center Affiliate of Vilnius University Hospital Santaros Klinikos; Le Collège des Enseignants de Radiologie de France

Publications and helpful links

General Publications

• Yilmaz EC, Turkbey B. The added value of a deep learning-based computer-aided detection system on prostate cancer detection among readers with varying level of multiparametric MRI expertise. Chin Clin Oncol. 2022 Dec;11(6):42. doi: 10.21037/cco-22-104. Epub 2022 Nov 15. No abstract available.

Helpful Links

• Accelerating the lab to market transition of AI tools for cancer management is an European project that contemplates the evaluation of the in silico clinical validation

Study record dates

Study Major Dates

• Study Start (Actual): September 1, 2024
• Primary Completion (Actual): October 30, 2024
• Study Completion (Actual): November 1, 2024

Study Registration Dates

• First Submitted: April 11, 2025
• First Submitted That Met QC Criteria: April 22, 2025
• First Posted (Actual): April 30, 2025

Study Record Updates

• Last Update Posted (Actual): April 30, 2025
• Last Update Submitted That Met QC Criteria: April 22, 2025
• Last Verified: September 1, 2024

More Information

Terms related to this study

• Keywords: Clinical validation; AI model solutions; experimental dedicated-platform
• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Intestinal Diseases; Respiratory Tract Diseases; Gastrointestinal Neoplasms; Digestive System Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Colorectal Neoplasms; Intestinal Neoplasms; Rectal Diseases; Lung Diseases; Respiratory Tract Neoplasms; Thoracic Neoplasms; Lung Neoplasms; Carcinoma, Bronchogenic; Bronchial Neoplasms; Rectal Neoplasms; Carcinoma, Non-Small-Cell Lung
• Other Study ID Numbers: CHAIMELEON insilico validation; 952172 (Other Grant/Funding Number: European Union's Horizon 2020)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No