Amel Ouyahia

OBJECTIVE: This study aimed to assess 30-day morbidity and mortality rates following cholecystectomy for benign gallbladder disease and identify the factors associated with complications. SUMMARY BACKGROUND DATA: Although cholecystectomy is common for benign gallbladder disease, there is a gap in the knowledge of the current practice and variations on a global level. METHODS: A prospective, international, observational collaborative cohort study of consecutive patients undergoing cholecystectomy for benign gallbladder disease from participating hospitals in 57 countries between January 1 and June 30, 2022, was performed. Univariate and multivariate logistic regression models were used to identify preoperative and operative variables associated with 30-day postoperative outcomes. RESULTS: Data of 21,706 surgical patients from 57 countries were included in the analysis. A total of 10,821 (49.9%), 4,263 (19.7%), and 6,622 (30.5%) cholecystectomies were performed in the elective, emergency, and delayed settings, respectively. Thirty-day postoperative complications were observed in 1,738 patients (8.0%), including mortality in 83 patients (0.4%). Bile leaks (Strasberg grade A) were reported in 278 (1.3%) patients and severe bile duct injuries (Strasberg grades B-E) were reported in 48 (0.2%) patients. Patient age, ASA physical status class, surgical setting, operative approach and Nassar operative difficulty grade were identified as the five predictors demonstrating the highest relative importance in predicting postoperative complications. CONCLUSION: This multinational observational collaborative cohort study presents a comprehensive report of the current practices and outcomes of cholecystectomy for benign gallbladder disease. Ongoing global collaborative evaluations and initiatives are needed to promote quality assurance and improvement in cholecystectomy.

PURPOSE: Brucellosis is a major ubiquitous zoonosis transmitted from livestock to humans. It is a public health problem in developing countries. Between 2003 and 2005, the incidence of brucellosis in Algeria showed a 181% increase from 8.79 to 24.71. Between 2005 and 2007, the incidence remained almost stable. The estimated mean incidence of neurobrucellosis is 4% with clinical manifestations that are variable and often multi-focal in the same patient. The purpose of this retrospective study is to describe 5 cases of neurobrucellosis managed in our department between 2001 and 2007. MATERIALS AND METHODS: It was a retrospective study 5 patients. There were 2 women and 3 men with a mean age of 20 years. RESULTS: Neurological involvement occurred immediately in all patients. Clinical manifestations were variable with meningoencephalitis in 2, meningoencephalitis associated with a polyperipheral neuropathy in 1, meningomyeloradiculitis in 1, and acute diffuse encephalitis in 1. Definitive diagnosis was based on isolation of bacteria from a blood specimen in 1 case and detection of antibodies in blood and cerebrospinal fluid in 4. All patients were treated using a combination of 3 of the following 4 drugs: doxycycline, rifampicine, cotrimoxazole and aminoside. Treatment was associated with corticosteroid therapy in 3 cases. DISCUSSION: Neurobrucellosis can affect any part of the nervous system and can mimic any neurological disease. Early detection and treatment is the only predictor of favorable outcome of neurobrucellosis, but there is no standardized treatment protocol. Neurobrucellosis should be included in differential diagnosis for any patient presenting central or peripheral neurological manifestations especially in endemic zones.

Meningococcal meningitis, a severe bacterial infection, demands precise diagnosis and immediate intervention. This paper explores the potential of Artificial Intelligence (AI) in improving diagnostic accuracy and clinical decision-making for this condition. We assess interpretability and reliability by analyzing the decision-making process of Machine Learning (ML) models tailored to identify Meningococcal meningitis among different etiologies of meningitis. Initially, we train and test various ML models, including logistic regression, K-nearest neighbors, support vector machine, decision tree, gradient boosting, AdaBoost, random forest, and LightGBM classifier, on a dataset comprising 460 cases of Meningococcal meningitis and 474 cases of other types of meningitis. Among these models, the gradient-boosting model exhibits superior performance metrics, including accuracy (0.88), precision (0.92), recall (0.83), AUROC (0.93), and f1-score (0.87). Subsequently, we employ Explainable AI (XAI) tools (ELI5 and LIME) to elucidate the importance of features in the ML models. Our results highlight key factors contributing to model success, such as Neisseria meningitidis identified through cerebrospinal fluid (CSF) culture and latex agglutination, gram-negative diplococci in CSF smear examination, white cell counts in CSF, and patient age. Local explanations reveal the presence of neutrophils in CSF as a characteristic feature of Meningococcal meningitis. LIME analysis indicates the significance of low lymphocyte percentages and elevated white blood cell counts in predicting this condition. These findings underscore the effectiveness of integrating global and local interpretability techniques, aligning with expert knowledge, and emphasizing the importance of transparent AI models in clinical decision-making processes.

Abstract Meningitis, characterized by meninges and cerebrospinal fluid inflammation, poses diagnostic challenges due to diverse clinical manifestations. This work introduces an explainable AI automatic medical decision methodology that determines critical features and their relevant values for the differential diagnosis of various meningitis cases. We proceed with knowledge acquisition to define the rules for this research. Currently, we have established the etiological diagnosis of Meningococcaemia, Meningococcal Meningitis, Tuberculous Meningitis, Aseptic Meningitis, Haemophilus influenzae Meningitis, and Pneumococcal Meningitis. The data preprocessing was conducted after collecting data from samples with meningitis diseases at Setif Hospital in Algeria. Tree-based ensemble methods were then applied to assess the model’s performance. Finally, we implement an XAI agnostic explainability approach based on the SHapley Additive exPlanations technique to attribute each feature’s contribution to the model’s output. Experiments were conducted on the collected dataset and the SINAN database, obtained from the Brazilian Government’s Health Information System on Notifiable Diseases, which comprises 6729 patients aged over 18 years. The Extreme Gradient Boosting model was chosen for its superior performance metrics (Accuracy: 0.90, AUROC: 0.94, and F1-score: 0.98). Setif’s hospital data revealed notable performance metrics (Accuracy: 0.7143, F1-Score: 0.7857). This study’s findings showcase each feature’s contribution to the model’s predictions and diagnosis. It also reveals critical biomarker ranges associated with distinct types of Meningitis. Significant diagnostic effect was found for Meningococcal Meningitis with elevated neutrophil levels ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:mo>&gt;</mml:mo> </mml:mrow> </mml:math> 40%) and balanced lymphocyte levels (40%–60%). Tuberculous Meningitis demonstrated low neutrophil levels ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:mo>&lt;</mml:mo> </mml:mrow> </mml:math> 60%) and elevated lymphocyte levels ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:mo>&gt;</mml:mo> </mml:mrow> </mml:math> 60%). H. influenzae meningitis exhibited a predominance of neutrophils ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:mo>&gt;</mml:mo> </mml:mrow> </mml:math> 80%), while Aseptic meningitis showed lower neutrophil levels ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:mo>&lt;</mml:mo> </mml:mrow> </mml:math> 40%) and lymphocyte levels within the range of 50%–60%. The majority of the AI automatic medical decision results are twinned with validation by our team of infectious disease experts, confirming the alignment of algorithmic diagnoses with clinical practices.