Machine learning and artificial intelligence in the multi-omics approach to gut microbiota

The gut microbiome is involved in human health and disease, and its comprehensive understanding is necessary to exploit it as a diagnostic or therapeutic tool. Multi-omics approaches, including metagenomics, metatranscriptomics, metabolomics, and metaproteomics, enable depicting the complexity of the gut microbial ecosystem. However, these tools generate a large data stream, which integration is needed to produce clinically useful readouts but, in turn, might be difficult to carry out with conventional statistical methods.

Leggi
Marzo 2025

Association of occupational physical activity and sedentary behaviour with the risk of hepatocellular carcinoma: a case-control study based on the Inpatient Clinico-Occupational Database of Rosai Hospital Group

Objectives
While there is growing evidence that physical activity reduces the risk of hepatocellular carcinoma (HCC), the impact of occupational physical activity and sedentary behaviour remains unclear. This study aimed to investigate the associations between occupational physical activity and sedentary behaviour and HCC risk.

Design
Matched case-control study.

Setting
Nationwide multicentre, hospital-inpatient data set in Japan, from 2005 to 2021.

Participants
The study included 5625 inpatients diagnosed with HCC and 27 792 matched controls without liver disease or neoplasms. Participants were matched based on sex, age, admission date, and hospital.

Primary measures
The association between levels of occupational physical activity (low, medium, high) and sedentary time (short, medium, long) with the risk of HCC.

Secondary measures
Stratification of HCC risk by viral infection status (hepatitis B/C virus), alcohol consumption levels and the presence of metabolic diseases (hypertension, diabetes, dyslipidaemia, obesity).

Results
High occupational physical activity was not associated with HCC caused by hepatitis B/C virus infection in men. In women, high occupational physical activity was associated with a reduced risk of non-viral HCC, with ORs (95% CIs) of 0.65 (0.45–0.93). Among patients with non-viral HCC, medium occupational physical activity combined with medium alcohol intake further decreased the HCC risk in men with an OR of 0.70 (0.50–0.97), while high occupational physical activity combined with lowest alcohol intake decreased the HCC risk in women with an OR of 0.69 (0.48–0.99). Men and women with medium sedentary time had a lower HCC risk compared with those with long sedentary time, with ORs of 0.88 (0.79–0.98) in men and 0.77 (0.62–0.97) in women, respectively. In patients without viral infection or alcohol use, medium sedentary time reduced the HCC risk associated with fatty liver disease without comorbid metabolic diseases in women.

Conclusions
High levels of occupational physical activity and/or medium periods of sedentary time are associated with a reduced risk of HCC, particularly non-alcoholic steatohepatitis.

Leggi
Marzo 2025

Multicentre, multi-arm, double-blind randomised placebo-controlled dose-finding trial investigating the safety and Efficacy of MirococePt (APT070) In Reducing delayed graft function In the Kidney ALlograft (EMPIRIKAL-2): study protocol for a randomised controlled trial

Background
Up to 50% of kidney transplant patients are diagnosed with delayed graft function (DGF) following transplantation—the majority being linked to ischaemia reperfusion injury (IRI). DGF is traditionally defined as the requirement for dialysis during the first week after transplantation and is associated with inferior graft and patient outcomes. Local synthesis of complement components, largely by the renal tubule, plays a critical role in IRI. We have developed Mirococept, a membrane-targeted complement inhibitor, that can be administered to the donor kidney ex vivo prior to transplantation. After administration, Mirococept is retained in the donor organ, thereby minimising the risk of systemic side effects. We previously launched the EMPIRIKAL study aiming to evaluate the efficacy of Mirococept in reducing DGF in deceased-donor kidney transplantation (KT). The funding body recommended termination of the study to allow a dose-saturating study before the next stage of clinical evaluation. This was carried out in a porcine kidney model and led to a revised dosing regimen for EMPIRIKAL-2 (60–180 mg compared with 5–25 mg in the initial trial). The EMPIRIKAL-2 trial (REC 24/NE/0071) aims to identify the most safe and efficacious dose of Mirococept to reduce DGF rate in deceased-donor KT.

Methods and analysis
EMPIRIKAL-2 is a Phase IIa multicentre double-blind randomised controlled trial (RCT) with an initial safety run. Participants will be recruited from renal departments at National Health Service tertiary hospital sites in the UK. The purpose of the safety run is to assess the tolerance of each of the three proposed Mirococept doses (60, 120 or 180 mg), before the RCT begins. Three patients will be assigned to each treatment dose, starting from the lower dose. The safety run will be considered successful if at least one dose can be taken forward to the RCT for comparison to placebo.
If safety is met, 144 participants (36 per arm excluding drop-outs) will be randomised to all doses meeting the safety criteria or placebo on a 1:1:1:1 basis. The primary endpoint is DGF, defined as the requirement for dialysis during the first week after transplantation. Safety evaluation will include the monitoring of laboratory data and the recording of all adverse events. Immunosuppression therapy, antibiotic and antiviral prophylaxis will be administered as per local centre protocols. Enrolment in the RCT is anticipated to take approximately 12 months, and patients will be followed-up for 12 months.

Ethics and dissemination
The study has been approved by the Northeast – Newcastle and North Tyneside 2 Research Ethics Service Committee, REC reference 24/NE/0071. The results of the study will be reported and disseminated at international conferences and in peer-reviewed scientific journals. Once published, a lay summary of the results will be made available to participants who request this information.

Trial registration number
ISRCTN14279222. Registered on 4 July 2024.

Protocol version
2.0 dated 9 May 2024.

Leggi
Marzo 2025

Surveillance in inflammatory bowel disease: white light endoscopy with segmental re-inspection versus dye-based chromoendoscopy – a multi-arm randomised controlled trial (HELIOS)

Background
It remains unclear if the increased colorectal neoplasia detection rate in inflammatory bowel disease (IBD) by high-definition (HD) dye-based chromoendoscopy compared with HD white-light endoscopy is due to enhanced contrast or increased inspection times. Longer withdrawal times may yield similar neoplasia detection rates as found by HD chromoendoscopy.

Objective
To compare colorectal neoplasia detection rates for HD white-light endoscopy with segmental re-inspection and HD chromoendoscopy, using single-pass HD white-light endoscopy as an additional control group.

Design
In a multicentre, randomised controlled trial, IBD patients aged ≥18 years without active disease and scheduled for endoscopic surveillance were included. Patients were 2:2:1 randomised to HD white-light endoscopy with segmental re-inspection of each colonic segment (double pass), HD chromoendoscopy or single-pass HD white-light endoscopy. The primary outcome was colorectal neoplasia detection rate. Assuming equal colorectal neoplasia rates (non-inferiority margin of 10%) between segmental re-inspection and chromoendoscopy and superiority of segmental re-inspection vs single-pass HD white-light endoscopy, a sample size of 566 patients was required.

Results
In total, 563 patients were analysed per-protocol. Colorectal neoplasia detection rates were 10.3% (n=24/234) for HD white-light endoscopy with segmental re-inspection and 13.1% (n=28/214) for HD chromoendoscopy. This confirmed non-inferiority to HD chromoendoscopy (–2.8%, lower limit 95% CI –7.8, p

Leggi
Marzo 2025

Optimizing Bowel Preparation Quality for Colonoscopy: Consensus Recommendations by the US Multi-Society Task Force on Colorectal Cancer

This document is an update to the 2014 recommendations for optimizing the adequacy of bowel cleansing for colonoscopy from the US Multi-Society Task Force on Colorectal Cancer, which represents the American College of Gastroenterology and the American Society for Gastrointestinal Endoscopy. The US Multi-Society Task Force developed consensus statements and key clinical concepts addressing important aspects of bowel preparation for colonoscopy. The majority of consensus statements focus on individuals at average risk for inadequate bowel preparation.

Leggi
Marzo 2025

Patients and doctors preferences in early-stage triple-negative breast cancer treatment in Asia-Pacific: a multi-territory discrete choice experiment using a cross-sectional survey

Objectives
This study aimed to assess preferences of patients and doctors regarding treatment attributes for early-stage triple-negative breast cancer (eTNBC) in the Asia–Pacific region.

Design
A discrete choice experiment (DCE) by cross-sectional survey was conducted with patients and doctors. Key attributes relevant to eTNBC treatment decision-making were verified through a consultative process with clinical experts. The levels and description of seven attributes were refined through cognitive interviews. A D-efficient fractional-factorial design was employed to create 15 choice sets with seven key attributes.

Setting
An online web-based DCE with the 15 choice sets was developed and made available to participants in Australia, Japan, Korea, the Philippines and Taiwan.

Participants
The final dataset comprised 115 patients who self-reported a diagnosis of eTNBC and 86 medical oncologists, breast and general surgeons with at least five years of experience managing eTNBC patients.

Primary outcomes
Patients’ and doctors’ preferences on seven attributes: pathological complete response (pCR), disease-free/event-free survival (DFS/EFS), chance of undergoing breast-conserving surgery after receiving anticancer treatment, febrile neutropenia, peripheral sensory neuropathy (PSN), diarrhoea and irreversible endocrine-related side effects requiring lifelong medication. Data were analysed using a mixed logit model to determine preference weights for attribute levels, which were then used to compute the relative importance score (RIS) for each attribute.

Results
The median age of patients was 44.0 (IQR 38.0–56.5) years. Most patients (68%) were married, and 77% had children. Additionally, 40% were employed full-time, and 70% held a college degree. Nearly half (46%) were diagnosed before the age of 40. Among the doctors, 58% were medical oncologists and the remaining breast or general surgeons. pCR, DFS/EFS and PSN were the three most important attributes in both doctor and patient groups. pCR had the highest weighted preference among patients and doctors (RIS, 28.5 and 32.9, respectively). In general, patients assigned more weight to safety attributes compared with doctors, while doctors assigned more weight to efficacy attributes than patients did. Surgeons assigned more weight to irreversible endocrine-related side effects than medical oncologists (RIS, 14.4 vs 5.4). Differences in preferences within the regions were noted.

Conclusions
While our study revealed a concordance between patients’ and doctors’ ranking of the seven assessed treatment attributes, patients generally assigned greater emphasis on safety-related attributes in comparison to doctors.

Leggi
Marzo 2025

Predicting the risk of acute kidney injury in patients with acute pancreatitis complicated by sepsis using a stacked ensemble machine learning model: a retrospective study based on the MIMIC database

Objective
This study developed and validated a stacked ensemble machine learning model to predict the risk of acute kidney injury in patients with acute pancreatitis complicated by sepsis.

Design
A retrospective study based on patient data from public databases.

Participants
This study analysed 1295 patients with acute pancreatitis complicated by septicaemia from the US Intensive Care Database.

Methods
From the MIMIC database, data of patients with acute pancreatitis and sepsis were obtained to construct machine learning models, which were internally and externally validated. The Boruta algorithm was used to select variables. Then, eight machine learning algorithms were used to construct prediction models for acute kidney injury (AKI) occurrence in intensive care unit (ICU) patients. A new stacked ensemble model was developed using the Stacking ensemble method. Model evaluation was performed using area under the receiver operating characteristic curve (AUC), precision-recall (PR) curve, accuracy, recall and F1 score. The Shapley additive explanation (SHAP) method was used to explain the models.

Main outcome measures
AKI in patients with acute pancreatitis complicated by sepsis.

Results
The final study included 1295 patients with acute pancreatitis complicated by sepsis, among whom 893 cases (68.9%) developed acute kidney injury. We established eight base models, including Logit, SVM, CatBoost, RF, XGBoost, LightGBM, AdaBoost and MLP, as well as a stacked ensemble model called Multimodel. Among all models, Multimodel had an AUC value of 0.853 (95% CI: 0.792 to 0.896) in the internal validation dataset and 0.802 (95% CI: 0.732 to 0.861) in the external validation dataset. This model demonstrated the best predictive performance in terms of discrimination and clinical application.

Conclusion
The stack ensemble model developed by us achieved AUC values of 0.853 and 0.802 in internal and external validation cohorts respectively and also demonstrated excellent performance in other metrics. It serves as a reliable tool for predicting AKI in patients with acute pancreatitis complicated by sepsis.

Leggi
Febbraio 2025