Differentiating necrotizing soft tissue infections from cellulitis by soft tissue infectious fluid analysis: a pilot study

Machine Learning Approach to Classify Vibrio vulnificus Necrotizing Fasciitis, Non-Vibrio Necrotizing Fasciitis and Cellulitis

Background

Recent advancements in artificial intelligence have led to increased adoption of machine learning in disease identification, particularly for challenging diagnoses like necrotizing fasciitis and Vibrio vulnificus infections. This shift is driven by the technology's efficiency, objectivity, and accuracy, offering potential solutions to longstanding diagnostic hurdles in clinical practice.

Methods

This investigation incorporated 180 inpatients suffering from soft tissue infections. The participants were categorized into groups: cellulitis, non-Vibrio necrotizing fasciitis (NF), or V. Vulnificus NF. To predict the three relevant outcomes, we employed Light Gradient Boosting Machine (LightGBM) and 5-fold cross-validation methodologies for the development of a multi-class categorization model. Moreover, we applied the SHapley Additive exPlanations (SHAP) methodology to decipher the model's predictions.

Results

The multi-classification model possesses substantial predictive capacity, with a weighted-average AUC of 0.86, sensitivity of 87.2%, specificity of 74.5%, NPV of 81.6%, and PPV of 85.4%. The model's calibration was assessed using the Brier score, yielding a weighted mean of 0.084. This low value demonstrates a strong correlation between predicted probabilities and actual outcomes, indicating high predictive accuracy and reliability in the model's forecasts.

Conclusions

We effectively developed a multiclassification model aimed at forecasting the occurrence of cellulitis, non-Vibrio NF, or V. Vulnificus NF in patients suffering from soft tissue infection, and we further described the model's predictions using the SHAP algorithm.

Comparison of GAP, R-GAP, and new trauma score (NTS) systems in predicting mortality of traffic accidents that injure hospitals at Mashhad University of medical sciences

Background

There are several trauma scoring systems with varying levels of accuracy and reliability that have been developed to predict and classify mortality in trauma patients in the hospital admission. Considering the importance of the country's emergency organization and the World Health Organization in the category of traffic accidents, we used this information in the study. The objective of this study is to evaluate and compare the predictive power of three scoring systems (R-GAP, GAP, and NTS) on traffic accident injuries.

Methods

In an analytical cross-sectional study, all the data related to the mission of traffic accidents at the pre-hospital emergency management of Mashhad University of Medical Sciences in 2022 were extracted from the automation system, and the outcome of the patients in the hospital was recorded from the integrated hospital system. Then, GAP, R-GAP, and New Trauma Scores (NTS) were calculated, and their results were compared using ROC curve and logistic regression.

Results

In this study, 47,971 injuries from traffic accidents were evaluated. Their average age was 30.16 ± 10.93 years. R-GAP showed negligible difference than GAP and NTS scores (the area under the curve equals 0.904, 0.935, and 0.884, respectively), and the average scores of R-GAP, GAP, and NTS are equal to 22.45/45 ± 1/9, 22.25 ± 1.5, and 22.49 ± 1.3, respectively. Injury severity based on R-GAP, GAP, and NTS scores was mild in most patients. The effect of these models on the patient outcome based on OR values, R-GAP, GAP, and NTS models showed high values. All analysis was performed in SPSS 26.

Conclusion

According to the study results, it seems that R-GAP, GAP, and NTS, have the highest power to predict death in traffic accident injuries. It is recommended to include these points in the electronic file of the pre-hospital emergency for the injured. Also, the severity and outcome of the patient can be predicted by these scores, which play an important role in the triage of the injured and determining the appropriate treatment center.

Synthesis, DFT, and in silico biological evaluation of chalcone bearing pyrazoline ring against Helicobacter pylori receptors

Peptic ulcer disease (PUD), often caused by Helicobacter pylori infection, is a prevalent gastrointestinal condition characterized by the erosion of the gastric or duodenal mucosal lining. H. pylori adheres to gastric epithelial cells, secreting toxins and disrupting the stomach's defenses. H. pylori relies on various receptors to establish infection, making these molecules attractive therapeutic targets. This study aimed to develop novel anti-ulcer compounds by combining benzothiazole, pyrazoline, and chalcone pharmacophores. A series of chalcone derivatives 4a-c were synthesized via Claisen-Schmidt condensation and characterized using spectroscopic techniques such as FT-IR, NMR and elemental analysis. The DFT calculations, using B3LYP method with 6-311G basis set, revealed the p-tolyl derivative 4b exhibited the highest thermal stability while the p-bromophenyl derivative 4c showed the lowest stability but highest chemical reactivity. The HOMO-LUMO energy gaps as well as the dipole moments decreased in the order: 4b > 4a > 4c, reflecting a similar reactivity trend. Molecular docking showed ligands 4a-c bound effectively to the H. pylori urease enzyme, with docking scores from -5.3862 to -5.7367 kcal/mol with superior affinity over lansoprazole. Key interactions involved hydrogen bonds and hydrophobic pi-hydrogen bonds with distances ranging 3.46-4.34 Å with active site residues ASN666, SER714 and ASN810. The combined anti-inflammatory, antimicrobial, and H. pylori anti-adhesion properties make these novel chalcones promising PUD therapeutic candidates.

Knowledge and acceptance of artificial intelligence and its applications among the physicians working in military medical centers affiliated with Aja University: A cross-sectional study

BACKGROUND

The use of artificial intelligence (AI) in medical sciences promises many benefits. Applying the benefits of this science in developing countries is still in the development stage. This important point depends considerably on the knowledge and acceptance levels of physicians.

MATERIALS AND METHODS

This study was a cross-sectional descriptive-analytical study that was conducted on 169 medical doctors using a purposive sampling method. To collect data, questionnaires were used to obtain demographic characteristics, a questionnaire to investigate the knowledge of AI and its applications, and an acceptability questionnaire to investigate AI. For data analysis, SPSS (Statistical Package for the Social Sciences) version 22 and appropriate descriptive and inferential statistical tests were used, and a significance level of < 0.05 was considered.

RESULTS

Most of the participants (102) were male (60.4%), married (144) (85.20%), had specialized doctorate education (97) (57.4%), and had average work experience of 10.78 ± 6.67 years. The mean and standard deviation of knowledge about AI were 9.54 ± 3.04, and acceptability was 81.64 ± 13.83. Multiple linear regressions showed that work history (P = 0.017) and history of participation in AI training courses (P = 0.007) are effective in knowledge and acceptability of AI.

CONCLUSION

The knowledge and acceptability of the use of AI among the studied physicians were at an average level. However, due to the importance of using AI in medical sciences and the inevitable use of this technology in the near future, especially in medical sciences in crisis, war, and military conditions, it is necessary for the policymakers of the health system to improve the knowledge and methods of working with this technology in the medical staff in addition to providing the infrastructure.

Identifying necrotizing soft tissue infection using infectious fluid analysis and clinical parameters based on machine learning algorithms

Background

Determining the presence of necrotizing soft tissue infection (NSTI) poses a significant hurdle. As of late, there has been a notable increase in the application of artificial intelligence (AI) machine learning techniques in identifying diseases, a shift that can be attributed to their exceptional efficiency, unbiased nature, and high precision.

Methods

Information was gathered from a cohort of 13 patients suffering from NSTI, alongside 12 patients with cellulitis. The construction of NSTI diagnostic machine learning models utilized four different algorithms, specifically random forest, k-nearest neighbors (KNN), support vector machine (SVM), and logistic regression. These models were constructed based on 28 distinctive attributes identified through statistical examination. Following this, the diagnostic efficiency of each algorithms was evaluated. A novel random forest model, streamlined for clinical use, was later developed by focusing on 6 attributes that had the most pronounced influence on the accuracy of our initial random forest model.

Results

The following data was noted regarding the sensitivity and specificity of the four NSTI diagnostic models:logistic regression displayed 78.2 % and 83.7 %, KNN presented 79.1 % and 87.1 %, SVM showed 83.5 % and 86.3 %, and random forest exhibited 89.6 % and 92.9 %, respectively. In comparison, lactate levels in fluid demonstrated 100 % sensitivity and 76.9 % specificity at an optimal cut-off point of 69.6 mg/dL. Among all four machine learning models, random forest outperformed the others and also showed better results than fluid lactate. A newly constructed random forest model, created using 6 of the 13 identified features, displayed promising results in diagnosing NSTI, having a sensitivity and specificity of 90.2 % and 92.2 %, respectively.

Conclusions

Developing a diagnostic model for NSTI employing the random forest algorithm has resulted in a diagnostic technique that is more efficient, cost-effective, and expedient. This approach could provide healthcare practitioners with the tools to identify and manage NSTI with greater efficacy.

Enhanced perioperative care in emergency general surgery: the WSES position paper

Enhanced perioperative care protocols become the standard of care in elective surgery with a significant improvement in patients' outcome. The key element of the enhanced perioperative care protocol is the multimodal and interdisciplinary approach targeted to the patient, focused on a holistic approach to reduce surgical stress and improve perioperative recovery. Enhanced perioperative care in emergency general surgery is still a debated topic with little evidence available. The present position paper illustrates the existing evidence about perioperative care in emergency surgery patients with a focus on each perioperative intervention in the preoperative, intraoperative and postoperative phase. For each item was proposed and approved a statement by the WSES collaborative group.

Necrotising soft-tissue infections

The incidence of necrotising soft-tissue infections has increased during recent decades such that most physicians might see at least one case of these potentially life-threatening infections in their career. Despite advances in care, necrotising soft-tissue infections are still associated with high morbidity and mortality, underlining a need for continued education of the medical community. In particular, failure to suspect necrotising soft-tissue infections, fuelled by poor awareness of the disease, promotes delays to first surgical debridement, amplifying disease severity and adverse outcomes. This Review will focus on practical approaches to management of necrotising soft-tissue infections including prompt recognition, initiation of specific management, exploratory surgery, and aftercare. Increased alertness and awareness for these infections should improve time to diagnosis and early referral to specialised centres, with improvement in the prognosis of necrotising soft-tissue infections.

In-hospital mortality associated with necrotizing soft tissue infection due to Vibrio vulnificus: a matched-pair cohort study

Background

It remains unclear whether Vibrio vulnificus necrotizing soft tissue infection (NSTI) is associated with higher mortality compared with non-Vibrio NSTI. This study’s objective was to compare outcomes including in-hospital mortality and prognosis between patients with V. vulnificus NSTI and those with non-Vibrio NSTI.

Method

A retrospective 1:2 matched-pair cohort study of hospitalized patients with NSTI diagnosed by surgical finding was conducted in two tertiary hospitals in southern Taiwan between January 2015 and January 2020. In-hospital outcomes (mortality, length of stay) were compared between patients with and without V. vulnificus infection. We performed multiple imputation using chained equations followed by multivariable regression analyses fitted with generalized estimating equations to account for clustering within matched pairs. All-cause in-hospital mortality and length of stay during hospitalization were compared for NSTI patients with and without V. vulnificus.

Result

A total of 135 patients were included, 45 in V. vulnificus NSTI group and 90 in non-Vibrio group. The V. vulnificus NSTI patients had higher mortality and longer hospital stays. Multivariable logistic regression analysis revealed that V. vulnificus NSTI was significantly associated with higher in-hospital mortality compared with non-Vibrio NSTI (adjusted odds ratio = 1.52; 95% confidence interval 1.36–1.70; p < 0.01).

Conclusion

Vibrio vulnificus NSTI was associated with higher in-hospital mortality and longer hospital stay which may increase health care costs, suggesting that preventing V. vulnificus infection is essential.