A machine learning predictive model for recurrence of resected distal cholangiocarcinoma: Development and validation of predictive model using artificial intelligence.

INTRODUCTION: Distal Cholangiocarcinoma (dCCA) represents a challenge in hepatobiliary oncology, that requires nuanced post-resection prognostic modeling. Conventional staging criteria may oversimplify dCCA complexities, prompting the exploration of novel prognostic factors and methodologies, including machine learning algorithms. This study aims to develop a machine learning predictive model for recurrence after resected dCCA. MATERIAL AND METHODS: This retrospective multicentric observational study included patients with dCCA from 13 international centers who underwent curative pancreaticoduodenectomy (PD). A LASSO-regularized Cox regression model was used to feature selection, examine the path of the coefficient and create a model to predict recurrence. Internal and external validation and model performance were assessed using the C-index score. Additionally, a web application was developed to enhance the clinical use of the algorithm. RESULTS: Among 654 patients, LNR (Lymph Node Ratio) 15, neural invasion, N stage, surgical radicality, and differentiation grade emerged as significant predictors of disease-free survival (DFS). The model showed the best discrimination capacity with a C-index value of 0.8 (CI 95 %, 0.77%-0.86 %) and highlighted LNR15 as the most influential factor. Internal and external validations showed the model's robustness and discriminative ability with an Area Under the Curve of 92.4 % (95 % CI, 88.2%-94.4 %) and 91.5 % (95 % CI, 88.4%-93.5 %), respectively. The predictive model is available at https://imim.shinyapps.io/LassoCholangioca/. CONCLUSIONS: This study pioneers the integration of machine learning into prognostic modeling for dCCA, yielding a robust predictive model for DFS following PD. The tool can provide information to both patients and healthcare providers, enhancing tailored treatments and follow-up.

The influence of socioeconomic inequity and guidelines compliance on clinical outcomes of patients with acute biliary pancreatitis. An international multicentric cohort study.

BACKGROUND: There is lack of data on the association between socioeconomic factors, guidelines compliance and clinical outcomes among patients with acute biliary pancreatitis (ABP). METHODS: Post-hoc analysis of the international MANCTRA-1 registry evaluating the impact of regional disparities as indicated by the Human Development Index (HDI), and guideline compliance on ABP clinical outcomes. Multivariable logistic regression models were employed to identify prognostic factors associated with mortality and readmission. RESULTS: Among 5313 individuals from 151 centres across 42 countries marked disparities in comorbid conditions, ABP severity, and medical procedure usage were observed. Patients from lower HDI countries had higher guideline non-compliance (p < 0.001) and mortality (5.0% vs. 3.2%, p = 0.019) in comparison with very high HDI countries. On adjusted analysis, ASA score (OR 1.810, p = 0.037), severe ABP (OR 2.735, p < 0.001), infected necrosis (OR 2.225, p = 0.006), organ failure (OR 4.511, p = 0.001) and guideline non-compliance (OR 2.554, p = 0.002 and OR 2.178, p = 0.015) were associated with increased mortality. HDI was a critical socio-economic factor affecting both mortality (OR 2.452, p = 0.007) and readmission (OR 1.542, p = 0.046). CONCLUSION: These data highlight the importance of collaborative research to characterise challenges and disparities in global ABP management. Less developed regions with lower HDI scores showed lower adherence to clinical guidelines and higher rates of mortality and recurrence.

Towards a tailored approach for patients with acute diverticulitis and abscess formation. The DivAbsc2023 multicentre case-control study.

BACKGROUND: This multicentre case-control study aimed to identify risk factors associated with non-operative treatment failure for patients with CT scan Hinchey Ib-IIb and WSES Ib-IIa diverticular abscesses. METHODS: This study included a cohort of adult patients experiencing their first episode of CT-diagnosed diverticular abscess, all of whom underwent initial non-operative treatment comprising either antibiotics alone or in combination with percutaneous drainage. The cohort was stratified based on the outcome of non-operative treatment, specifically identifying those who required emergency surgical intervention as cases of treatment failure. Multivariable logistic regression analysis to identify independent risk factors associated with the failure of non-operative treatment was employed. RESULTS: Failure of conservative treatment occurred for 116 patients (27.04%). CT scan Hinchey classification IIb (aOR 2.54, 95%CI 1.61;4.01, P < 0.01), tobacco smoking (aOR 2.01, 95%CI 1.24;3.25, P < 0.01), and presence of air bubbles inside the abscess (aOR 1.59, 95%CI 1.00;2.52, P = 0.04) were independent predictors of failure. In the subgroup of patients with abscesses > 5 cm, percutaneous drainage was not associated with the risk of failure or success of the non-operative treatment (aOR 2.78, 95%CI - 0.66;3.70, P = 0.23). CONCLUSIONS: Non-operative treatment is generally effective for diverticular abscesses. Tobacco smoking's role as an independent risk factor for treatment failure underscores the need for targeted behavioural interventions in diverticular disease management. IIb Hinchey diverticulitis patients, particularly young smokers, require vigilant monitoring due to increased risks of treatment failure and septic progression. Further research into the efficacy of image-guided percutaneous drainage should involve randomized, multicentre studies focussing on homogeneous patient groups.

Global disparities in surgeons' workloads, academic engagement and rest periods: the on-calL shIft fOr geNEral SurgeonS (LIONESS) study.

The workload of general surgeons is multifaceted, encompassing not only surgical procedures but also a myriad of other responsibilities. From April to May 2023, we conducted a CHERRIES-compliant internet-based survey analyzing clinical practice, academic engagement, and post-on-call rest. The questionnaire featured six sections with 35 questions. Statistical analysis used Chi-square tests, ANOVA, and logistic regression (SPSS® v. 28). The survey received a total of 1.046 responses (65.4%). Over 78.0% of responders came from Europe, 65.1% came from a general surgery unit; 92.8% of European and 87.5% of North American respondents were involved in research, compared to 71.7% in Africa. Europe led in publishing research studies (6.6 ± 8.6 yearly). Teaching involvement was high in North America (100%) and Africa (91.7%). Surgeons reported an average of 6.7 ± 4.9 on-call shifts per month, with European and North American surgeons experiencing 6.5 ± 4.9 and 7.8 ± 4.1 on-calls monthly, respectively. African surgeons had the highest on-call frequency (8.7 ± 6.1). Post-on-call, only 35.1% of respondents received a day off. Europeans were most likely (40%) to have a day off, while African surgeons were least likely (6.7%). On the adjusted multivariable analysis HDI (Human Development Index) (aOR 1.993) hospital capacity > 400 beds (aOR 2.423), working in a specialty surgery unit (aOR 2.087), and making the on-call in-house (aOR 5.446), significantly predicted the likelihood of having a day off after an on-call shift. Our study revealed critical insights into the disparities in workload, access to research, and professional opportunities for surgeons across different continents, underscored by the HDI.