Unveiling new patterns: A surgical deep learning model for intestinal obstruction management.

BACKGROUND: Swift and accurate decision-making is pivotal in managing intestinal obstructions. This study aims to integrate deep learning and surgical expertise to enhance decision-making in intestinal obstruction cases. METHODS: We developed a deep learning model based on the YOLOv8 framework, trained on a dataset of 700 images categorised into operated and non-operated groups, with surgical outcomes as ground truth. The model's performance was evaluated through standard metrics. RESULTS: At a confidence threshold of 0.5, the model demonstrated sensitivity of 83.33%, specificity of 78.26%, precision of 81.7%, recall of 75.1%, and mAP@0.5 of 0.831. CONCLUSIONS: The model exhibited promising outcomes in distinguishing operative and nonoperative management cases. The fusion of deep learning with surgical expertise enriches decision-making in intestinal obstruction management. The proposed model can assist surgeons in intricate scenarios such as intestinal obstruction management and promotes the synergy between technology and clinical acumen for advancing patient care.

DraiNet: AI-driven decision support in pneumothorax and pleural effusion management.

OBJECTIVE: This study presents DraiNet, a deep learning model developed to detect pneumothorax and pleural effusion in pediatric patients and aid in assessing the necessity for tube thoracostomy. The primary goal is to utilize DraiNet as a decision support tool to enhance clinical decision-making in the management of these conditions. METHODS: DraiNet was trained on a diverse dataset of pediatric CT scans, carefully annotated by experienced surgeons. The model incorporated advanced object detection techniques and underwent evaluation using standard metrics, such as mean Average Precision (mAP), to assess its performance. RESULTS: DraiNet achieved an impressive mAP score of 0.964, demonstrating high accuracy in detecting and precisely localizing abnormalities associated with pneumothorax and pleural effusion. The model's precision and recall further confirmed its ability to effectively predict positive cases. CONCLUSION: The integration of DraiNet as an AI-driven decision support system marks a significant advancement in pediatric healthcare. By combining deep learning algorithms with clinical expertise, DraiNet provides a valuable tool for non-surgical teams and emergency room doctors, aiding them in making informed decisions about surgical interventions. With its remarkable mAP score of 0.964, DraiNet has the potential to enhance patient outcomes and optimize the management of critical conditions, including pneumothorax and pleural effusion.

Watchful Waiting After Radiological Guided Drainage of Intra-abdominal Abscess in Patients With Crohn's Disease Might Be Associated With Increased Rates of Stoma Construction.

Background: Management of spontaneous intra-abdominal abscess (IAA) in patients with Crohn's disease (CD) with radiologically guided percutaneous drainage (PD) was debated. Methods: This is a secondary analysis from a multicenter, retrospective cohort study of all the patients with CD who underwent PD followed by surgery at 19 international tertiary centers. Results: Seventeen patients (4.8%) who did not undergo surgery after PD were compared to those who had PD followed by surgical intervention 335/352 (95.2%). Patients who had PD without surgery were those with longer disease duration, more frequently had previous surgery for CD (laparotomies/laparoscopies), enteric fistula, on steroid treatment before and continue to have it after PD. Patients who had PD without subsequent surgical resection had a higher risk of stoma construction at later stages 8/17 (47.1%) versus 90/326 (27.6%) (P < .01). Patients with PD with no subsequent surgery had numerically higher rates of abscess recurrence 5/17 (29.4%) compared to those who had PD followed by surgery 45/335 (13.4%) the difference was not statistically significant (P = .07). Conclusions: Even with the low number of patients enrolled in this study who had PD of IAA without subsequent surgery, the findings indicate a markedly worse prognosis in terms of recurrence, length of stay, readmission, and stoma construction. Watchful waiting after PD to treat patients with spontaneous IAA might be indicated in selected patients with poor health status or poor prognostic factors.

An Atypical Presentation of Hydatid Disease, Accompanied by a Pancreatic Pseudocyst: A Case Report.

Hydatid disease (HD) is a zoonotic disease, which typically affects the liver and the lungs. Primary retroperitoneal localization of the disease is infrequent. The most common symptom is abdominal pain; however, the clinical features of HD may be generally dependent on the location of the cyst. A 53-year-old female patient presented to Kocaeli University General Surgery Clinic, Turkey in September 2019 with complaints of flank pain, constipation and vomiting. The MRI revealed cystic lesions in the pancreas and psoas muscle. Both cysts were excised totally during laparotomy. Histopathology reports showed that the lesion in psoas muscle was hydatid cyst whereas the lesion in pancreas was pancreatic pseudocyst. Postoperative period was uneventful and the patient was discharged with albendazole treatment. No recurrence occurred during follow-up period. Atypical localization for hydatid disease is a diagnostic dilemma for surgeons, especially in endemic countries. Hydatid disease should always be considered in the differential diagnosis of retroperitoneal lesions, inadequate management can lead to complications and fatalities. Surgery combined with antiparasitic therapy, may be an option in the presence of obstruction of gastrointestinal and/or urinary tract.

Effects of Asenapine and Paliperidone on Depression, Anxiety and Analgesy in Mice: Alterations in Brain Neurotrophic Factors, Neurogenesis, and Blood Enzyme Levels.

Schizophrenia, an important brain neurodevelopmental disorder, is observed in 1% of the global population. New-generation antipsychotics have been developed as alternatives to typical antipsychotics for more effective and safe therapy. Chronic administration of asenapine and paliperidone compared to haloperidol on depression, anxiety and analgesy in the forced swimming test (FST), elevated plus maze (EPM) and hot plate tests were examined in mice. Moreover effects of drugs, on expression levels of brain neurotrophic factors [brain-derived neurotrophic factor (BDNF), cAMP response element binding protein (CREB),nerve growth factor (NGF), synapsin and fibroblast growth factor 2 (FGF2)] in the hippocampus of mice, neurogenesis and neurodegeneration, and blood enzyme levels were also investigated. In FST, haloperidol (0.25 mg/kg) significantly increased immobility time while both asenapine (0.075 mg/kg) and paliperidone (0.25 and 0.50 mg/kg) significantly diminished this parameter. In EPM test, haloperidol significantly increased both % time spent in open arms and % open arm entries. Asenapine (0.075 mg/kg) and paliperidone (0.50 mg/kg) significantly increased % time spent in the open arms. They also increased % open arm entries, but this parameter failed to reach a statistically significant value. In hot plate test, haloperidol (0.125 and 0.25 mg/kg) and paliperidone (0.25 and 0.50 mg/kg) significantly increased the latency to lick the hind paws but asenapine had no effect. Asenapine and paliperidone upregulated more neurotrophic factors in the brain and caused less neurodegeneration compared to haloperidol. Investigated drugs had no effect on liver enzymes and plasma glucose levels. Asenapine and paliperidone may be preferred over classical antipsychotics since they have antidepressant-like effect, upregulate more neurotrophic factors and cause less neurodegeneration in naive mice without having diabetogenic and liver damaging effects. Paliperidone seems to possess superior effects compared to asenapine since it also exerts analgesic-like effect.