IBS-K
Irritable bowel syndrome and colorectal cancer risk: a predictive algorithm.
A prospective observational study dedicated to the early identification of patients with irritable bowel syndrome at risk of colorectal cancer, using clinical data, questionnaires and predictive algorithms to support personalised diagnostic pathways.
The project
IBS-K is a multi-year research project, conducted from 2023 to 2025, promoted by Nefrocenter Research and the Santa Rita Clinic of Atripalda (Avellino). The study was conceived to explore the relationship between irritable bowel syndrome and colorectal cancer risk, a condition in which early diagnosis may be hindered by non-specific symptoms and the absence of well-established biomarkers.
The project involves a multi-year, real-world observational study lasting 36 months, based on the preliminary administration, in the pre-screening phase, of Rome IV questionnaires to a representative cohort of subjects from both inpatient wards and outpatient clinics Subjects identified as at risk will undergo further second- and third-level investigations to validate the initial clinical suspicion.
Results
The main objective of IBS-K is to standardise a structured and personalised diagnostic pathway, aimed at a more precise definition of the clinical picture for the staging of irritable bowel syndrome, identifying early on any symptomatic or asymptomatic forms associated with colorectal cancer.
The project intends to develop an early-diagnosis model based on the integration of clinical data, questionnaires and instrumental investigations, supported by a scalable information system driven by machine-learning algorithms.
The aim is to provide the clinician with a tool useful for the personalisation of diagnostic-therapeutic pathways, reducing delays in the identification and treatment of neoplastic forms.
The main expected result is the description and development of a predictive algorithm capable of identifying those subjects with irritable bowel syndrome most exposed to the risk of neoplastic progression and related complications.
The algorithm will be oriented towards predicting comorbidity and mortality in at-risk subjects, helping to modify and improve current diagnostic-therapeutic pathways. The integration of clinical data, questionnaires, diagnostic investigations and machine-learning systems may support a strongly preventive, timely and personalised medicine, with potential benefits in the early diagnosis of colorectal cancer.
