Introduction

Early diagnosis of pancreatic cancer remains difficult due to the lack of overt findings on imaging. Our prior analysis revealed that indirect signs such as pancreatic atrophy and ductal stenosis or dilation often precede tumor visibility. In collaboration with Fujifilm Corporation, we developed an AI-based system capable of detecting pancreatic masses, atrophy, and ductal abnormalities on contrast-enhanced CT(CE-CT) and non-contrast CT(NC-CT). This study evaluated its diagnostic performance.

Aims & Methods

The AI algorithm extracts the pancreatic parenchyma, ducts, and tumor regions from CT images and classifies the presence of four imaging findings (pancreatic mass, atrophy, ductal dilation, and ductal stenosis). The model was trained and validated using approximately 2,000 images. For testing, we used an external dataset comprising 90 pancreatic cancer cases (Tis/T1: T2: T3–T4 = 1:1:1) and 100 controls collected from affiliated institutions. Reference standard for each imaging findings was established by two expert radiologists. Diagnosis of pancreas cancer was also performed using the logistic regression model with the results of each imaging finding. Diagnostic performances were performed on CE-CT and NC-CT, and AI diagnostic accuracy and reading time were compared with those of four radiologists and two gastroenterologists.

Results

For the diagnosis of pancreas cancer, the AI showed a sensitivity of 98.9% and specificity of 93.0% on CE-CT, and sensitivity of 83.9% and specificity of 92.0% on NC-CT. The system successfully detected early-stage cancers, including Tis and T1, by identifying indirect imaging findings. Detection metrics for CE-CT vs. NC-CT were as follows: mass (sensitivity 97.2% vs. 87.5%; specificity 74.6% vs. 71.4%), atrophy (74.0% vs. 59.6%; 90.7% vs. 92.9%), ductal dilation (78.8% vs. 90.5%; 96.4% vs. 88.3%), and ductal stenosis (87.7% vs. 93.9%; 90.4% vs. 85.1%).
Physicians showed mean sensitivities/specificities of 88.9%/99.3% on CE-CT and 53.4%/99.5% on NC-CT. Mean reading time per case was 22 seconds (AI) vs. 63 seconds (physicians) for CE-CT and 20 seconds (AI) vs. 78 seconds (physicians) for NC-CT.

Conclusion

The AI system demonstrated diagnostic performance comparable to that of experienced radiologists and significantly reduced reading time. While its specificity was somewhat lower than that of physicians, the system effectively identified early-stage pancreatic cancers using secondary findings. At present, it may be best applied as a second-reader support tool in radiological interpretation. Further refinement may expand its role in early detection and possibly future screening.

Disclosure

N.H., A.O., and M.T. are employees of Fujifilm Corporation.
A.M., K.S., T.M., and Y.K. declare financial conflicts of interest with Fujifilm Corporation.

Introduction

Intraductal papillary mucinous neoplasms (IPMNs) of the pancreas are the most frequently identified precursor lesions of pancreatic cancer (PDAC). Only a minority progress towards malignancy, making their identification a critical point in cancer prevention. The available guidelines are imprecise, commonly resulting in over treatment of indolent lesions.

Aims & Methods

The aim of this study (EMI-IPMN, NCT06706700) is to discover novel biological and radiological biomarkers that can distinguish malignant from benign IPMNs. We focused on Endocrine, Metabolic and Inflammatory (EMI) factors, some pathways that are characterized in PDAC but poorly investigated in IPMN progression.
Patients with a presumed diagnosis of IPMN with indication for surgical resection who underwent high-quality magnetic resonance imaging (MRI) and/or computed tomography (CT), were prospectively enrolled. Peripheral blood (PB) and cyst fluid (CF) samples were collected during surgery, and lesions were histologically classified as IPMN with low-grade dysplasia (LGD), high-grade dysplasia (HGD), or invasive cancer (IC). Malignant IPMNs were defined as those with HGD and IC. Cytokine and hormone levels were measured in both fluids using multiplex assays and compared across the diagnostic groups. Continuous variables were converted into categorical variables based on optimal cut-off values, and both univariate and multivariate logistic regression analyses were conducted.

Results

Among the 205 patients enrolled, 133 (58 females, 75 males, median age 69.2) had a histological diagnosis of IPMN: 49 (36.8%) had LGD, 44 (33.1%) HGD and 40 (30.1%) had IC. Analysis of the EMI profile revealed higher concentrations of several markers (IL-8, VEGF, GLP-1, glucagon, and C-peptide) in CF compared to PB. Specific cytokines such as MCP-1 IP-10, TNFα, and IL-8 were significantly elevated in the CF of HGD/IC cases compared to LGD (p=0.05, 0.041, 0.001 and 0.025 respectively). Similarly, IP-10, IL-8, and MDC levels in PB were higher in HGD/IC patients (p=0.006, 0.008 and 0.004 respectively).
Pancreatic fat content, assessed with mDixon Quant Fat Fraction MRI sequences, was notably higher in HGD/IC patients (13.89%) compared to LGD patients (8.38%, p<0.05), and positively correlated with MCP-1 levels in CF.
Among these biological and radiological markers TNFα in the CF demonstrated a substantial diagnostic accuracy for identifying malignant IPMN, with an area under the ROC curve (AUC) of 0.72. In the final multivariable analysis we demonstrate that high TNFα levels in CF and HbA1c were the two independent risk factors for the identification of malignant IPMN (OR 10.8 and 1.11 respectively).

Conclusion

The progression of IPMN to PDAC is associated with a proinflammatory shift in the tumor microenvironment, reflected by local (CF) and systemic (PB) elevations in key cytokines (TNFα, MCP-1, and IL-8) whose involvement in PDAC progression is well established. Elevated hormone levels in CF, along with the strong association between malignant IPMN and HbA1c, underscore the critical role of endocrine alterations in the early stages of pancreatic tumorigenesis. These findings may be harnessed to enable earlier detection of malignant transformation in IPMN. Moreover, the correlation between imaging markers and biological profiles suggests that MRI could serve as non-invasive proxies for underlying pathological changes. Together, these results offer new insights into the pathophysiology of IPMN progression and may imporve diagnostic strategies

Introduction

The integration of artificial intelligence (AI) into nursing practice offers a significant opportunity to enhance patient care and support clinical decision-making. This study examines the deployment of a customized generative language model (GPT) as a clinical assistant in outpatient digestive care. The tool aims to streamline access to evidence-based information and promote structured patient follow-up. While its implementation holds considerable potential for improving efficiency and fostering clinical learning, it also presents challenges related to validation, user adoption, and building trust among nursing professionals.

Results & Findings

A digital tool named Digestive Nursing Follow-Up was developed and piloted in the Gastroenterology Departments of two university hospitals in Spain during Q1 2025. The tool was integrated into four clinical domains: inflammatory bowel disease, gastroesophageal reflux disease, irritable bowel syndrome, and advanced endoscopy. The AI assistant was designed to: Collect and organize structured clinical data; Provide evidence-based clinical suggestions aligned with institutional protocols; Facilitate learning and care continuity. Prior to implementation, participating nurses underwent a one-hour training session. The tool was then incorporated into routine consultations, and nurses were surveyed pre- and post-intervention using a 5-point Likert Scale. Open-ended feedback was also collected.

Summary & Discussion

80% of nurses rated the tool as easy to use following training, and 75% reported high satisfaction, citing improved time management and a reduction in repetitive tasks. Positive perceptions centered on enhanced consultation efficiency and clinical safety. However, concerns were expressed regarding the balance between technology and patient-centered care, as well as the need for ongoing training and more personalized outputs.

Conclusion

Among the strengths identified were improved time management, support for clinical decision-making, and enhancement of standardized nursing practice. The main weaknesses were resistance to change and the initial learning curve, which required additional support. Opportunities include the potential of AI to strengthen professional training, enhance professional autonomy, and contribute to the standardization of clinical procedures. The tool reinforces clinical safety by being based on established protocols, and its use can accelerate their implementation and promote continuous learning, helping to consolidate a more efficient care model. The observed technological dependence was more associated with increased consultation efficiency, highlighting the importance of progressive and balanced integration with clinical practice.

References

1. Exploring the deep learning of artificial intelligence in nursing: a concept analysis with Walker and Avant’s approach. BMC Nurs. 2024;23:170. doi:10.1186/s12912-024-02170-x.
2. Examining the Role of AI in Changing the Role of Nurses in Patient Care: Systematic Review. JMIR Nurs. 2025;1:e63335. doi:10.2196/63335.
3. Artificial intelligence in healthcare: a scoping review of perceived threats to patient rights and safety. Arch Public Health. 2024;82:1414. doi:10.1186/s13690-024-01414-1.
4. Revolutionizing healthcare: the role of artificial intelligence in clinical practice. BMC Med Educ. 2023;23:4698. doi:10.1186/s12909-023-04698-z.
5. Utilization of Generative Artificial Intelligence in Nursing Education: A Topic Modeling Analysis. Educ Sci. 2023;14:1234. doi:10.3390/educsci14111234.
6. Human-centered design and evaluation of AI-empowered clinical decision support systems: a systematic review. Front Comput Sci. 2023;5:1187299. doi:10.3389/fcomp.2023.1187299.
7. Generative AI in healthcare: an implementation science informed translational path on application, integration and governance. Implement Sci. 2024;13:357. doi:10.1186/s13012-024-01357-9.
8. Telehealth and Remote Patient Monitoring Innovations in Nursing Practice: State of the Science. OJIN: The Online Journal of Issues in Nursing. 2022;27(2):1-15.
9. Artificial Intelligence and Digital Innovations in Nursing Care. Nurs Rep. 2023;13(1):45-60.

Introduction

Radiation proctopathy (RP) is a common late complication of pelvic radiotherapy, affecting up to 20% of patients treated for pelvic malignancies. It manifests as rectal bleeding, anaemia, urgency, and diarrhoea, significantly reducing quality of life. Argon Plasma Coagulation (APC) remains the standard endoscopic therapy but has notable limitations, including high recurrence rates, the need for multiple sessions, and risks such as ulceration and perforation.
PuraStat, a synthetic self-assembling peptide hydrogel, offers an innovative alternative by creating a transparent matrix that promotes haemostasis and mucosal healing without thermal injury. While small series have shown benefit, robust real-world evidence is lacking.

Aims & Methods

We assessed real-world outcomes of PuraStat in RP at a UK tertiary centre (2023–2024). Consecutive patients with chronic radiation-induced rectal bleeding were included and treated by a single endoscopist. Patients were stratified into two cohorts:
1. De novo PuraStat – no prior APC (n=50)
2. APC→PuraStat – persistent or recurrent symptoms despite APC (n=50)
PuraStat was applied during flexible sigmoidoscopy, either as monotherapy or following APC. The primary outcome was resolution or improvement of rectal bleeding. Secondary outcomes included the number of repeat endoscopic interventions within 6 months and treatment-related adverse events.

Results

A total of 100 patients were included (median age: 74 years, range 64–85; 52% male). Most had prostate or gynaecological cancer treated with pelvic radiotherapy.
- De novo PuraStat (n=50): All achieved symptomatic relief, with marked bleeding reduction and endoscopic improvement. Follow-up sigmoidoscopy showed mucosal healing or mild residual proctitis in 92%. Mean repeat sessions: 1.3 (range 0–3) over 6 months.
- APC→PuraStat (n=50): These patients had undergone a median of 3 APC sessions with limited success. PuraStat led to complete symptom control in all cases, reducing the need for frequent interventions (mean: 1.5 sessions over 6 months).
No adverse events (e.g., perforation, infection, severe pain) were reported in either group. Patients with severe radiation-associated vascular ectasia (RAVE) and refractory bleeding demonstrated excellent response to PuraStat.

Conclusion

This large real-world series demonstrates that PuraStat is a safe, effective, and well-tolerated therapy for radiation proctopathy, whether used as first-line treatment or following APC failure. It provided rapid and sustained bleeding control, significantly reduced the need for repeat endoscopic interventions, and promoted mucosal healing without the risks associated with thermal therapies. Importantly, PuraStat showed consistent efficacy even in patients with severe radiation-associated vascular ectasia (RAVE) and those refractory to conventional modalities, highlighting its role as both a frontline and salvage option. These findings position PuraStat as a valuable addition to the therapeutic armamentarium for radiation-induced rectal bleeding. Larger prospective, multicentre studies and cost-effectiveness analyses are warranted to validate these results and define its optimal place in treatment algorithms.

Table 1: Treatment Outcomes by Group

References

1- White K, Henson CC. Endoscopically delivered PuraStat for the treatment of severe haemorrhagic radiation proctopathy: Service evaluation of a new endoscopic treatment for a challenging condition. Frontline Gastroenterol. 2021;12(1):37–42. doi:10.1136/flgastro-2020-101735
2-Van de Wetering FT, Verleye L, Andreyev HJN, Maher J, Vlayen J, Pieters BR, et al. Non-surgical interventions for late rectal problems (proctopathy) of radiotherapy in people who have received radiotherapy to the pelvis. Cochrane Database Syst Rev. 2016;(4):CD003455. doi:10.1002/14651858.CD003455.pub2
3-Andreyev HJN, Davidson SE, Gillespie C, Allum WH, Swarbrick E. Practice guidance on the management of acute and chronic gastrointestinal problems arising as result of treatment for cancer. Gut. 2012;61:179–192. doi:10.1136/gutjnl-2011-300563
4-Dahiya DS, Kichloo A, Tuma F, Albosta M, Wani F. Radiation proctitis and management strategies. Clin Endosc. 2022;55(1):22–32. doi:10.5946/ce.2020.288
5-Rustagi T, Mashimo H. Endoscopic management of chronic radiation proctopathy. World J Gastroenterol. 2011;17(41):4554–4562. doi:10.3748/wjg.v17.i41.4554
6-Lenz L, Rohr R, Nakao F, Libera E, Ferrari A. Chronic radiation proctopathy: A practical review of endoscopic treatment. World J Gastrointest Surg. 2016;8(2):151–158. doi:10.4240/wjgs.v8.i2.151

Introduction

Colorectal anastomotic dehiscence (CAD) is one of the most severe postoperative complications in colorectal surgery, significantly impacting patient morbidity and mortality. Current risk assessment methods rely on clinical and intraoperative factors, but no real-time predictive tool exists. This study aimed to develop an artificial intelligence model based on intraoperative recording of the anastomosis for CAD prediction.

Aims & Methods

A convolutional neural network (CNN) was trained using a dataset of annotated frames from colorectal surgery videos across three international high-volume centers: IPO Lisboa, Hospital das Clínicas de Ribeirão Preto, São Paulo, Brazil and Royal Liverpool University Hospital. The dataset included a total of 5,356 annotated frames from 25 patients, 2,007 frames classified as CAD-positive and 3,349 as CAD-negative. Four CNN architectures (EfficientNetB0, EfficientNetB7, ResNet50, and MobileNetV2) were tested. Performance was evaluated using sensitivity, specificity, accuracy, and area under the receiver operating characteristic (AUROC) curve. Heatmaps were generated to identify key regions influencing predictions.

Results

The best-performing model achieved an accuracy of 99.55%, AUROC of 99.60%, sensitivity of 99.21%, specificity of 100%, PPV of 100%, and NPV of 98.94%. The model reliably identified CAD-positive frames and provided visual explanations through heatmaps.

Conclusion

To our knowledge, this is the first AI model developed to predict CAD using intraoperative video analysis. Its accuracy suggests the potential to redefine surgical decision-making by providing real-time risk assessment. Further refinement with a larger dataset and diverse surgical techniques could enable intraoperative interventions to prevent CAD before it occurs, marking a paradigm shift in colorectal surgery.