XRAInet: AI-based decision support for pneumothorax and pleural effusion management.

PURPOSE: This study aimed to develop and assess the performance of an artificial intelligence (AI)-driven decision support system, XRAInet, in accurately identifying pediatric patients with pleural effusion or pneumothorax and determining whether tube thoracostomy intervention is warranted. METHODS: In this diagnostic accuracy study, we retrospectively analyzed a data set containing 510 X-ray images from 170 pediatric patients admitted between 2005 and 2022. Patients were categorized into two groups: Tube (requiring tube thoracostomy) and Conservative (managed conservatively). XRAInet, a deep learning-based algorithm, was trained using this data set. We evaluated its performance using various metrics, including mean Average Precision (mAP), recall, precision, and F1 score. RESULTS: XRAInet, achieved a mAP score of 0.918. This result underscores its ability to accurately identify and localize regions necessitating tube thoracostomy for pediatric patients with pneumothorax and pleural effusion. In an independent testing data set, the model exhibited a sensitivity of 64.00% and specificity of 96.15%. CONCLUSION: In conclusion, XRAInet presents a promising solution for improving the detection and decision-making process for cases of pneumothorax and pleural effusion in pediatric patients using X-ray images. These findings contribute to the expanding field of AI-driven medical imaging, with potential applications for enhancing patient outcomes. Future research endeavors should explore hybrid models, enhance interpretability, address data quality issues, and align with regulatory requirements to ensure the safe and effective deployment of XRAInet in healthcare settings.

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.

Impact of gestational and parental factors and maternal intake of progesterone on the development of hypospadias: A retrospective case-control study.

OBJECTIVE: Impact of environmental, maternal, paternal, and fetal factors on the development of hypospadias have been questioned in association with disrupted hormonal balance. We aimed to examine the association between maternal progesterone use and the associated risk factors and hypospadias. MATERIALS AND METHODS: There were 429 male children as the cases with hypospadias (n = 280, Group 1) and the controls without hypospadias (n = 149, Group 2). Those working in agriculture and industry, cleaners, and hairdressers were determined as risky occupational groups concerning the exposure of estrogenic endocrine disrupters. The association of progestin usage and the other risk factors with hypospadias were the study outcomes. RESULTS: The median gestational age was significantly lower in Group 2 (p = 0.019). Prematurity was more common in Group 1 (p = 0.043). Although the median birth weight in Group 1 was significantly lower (p < 0.001), there was no significant difference between the ratios of low birth weight babies in the groups. The risky occupations were more frequently detected in Group 2 (p = 0.001). The rate and duration of progestin usage in Group 1 were significantly higher than that in Group 2 (p < 0.001). CONCLUSION: Low birth weight and the use and duration of progestins during pregnancy were significantly associated with increased hypospadias risk.

Ultrasound-guided dorsal penile nerve block vs neurostimulator-guided pudendal nerve block in children undergoing hypospadias surgery: A prospective, randomized, double-blinded trial.

BACKGROUND AND AIMS: Hypospadias is a common congenital malformation in pediatric patients. Surgical repair of this malformation is a painful procedure and has long-term effects. Pudendal and penile nerve blocks are commonly preferred techniques for maintaining postoperative analgesia. However, the conventional landmark-based penile block technique involves numerous potential complications and provides a shorter analgesic period compared to the pudendal block. A promising ultrasound-guided dorsal penile nerve block was recently described. We aimed to compare the analgesic effectiveness of ultrasound-guided penile nerve block with that of neurostimulator-guided pudendal nerve block. METHOD: Thirty-three patients aged 1-7 years were included in this prospective, double-blinded, randomized controlled trial. Patients were divided into two groups and received either ultrasound-guided dorsal penile nerve block or neurostimulator-guided pudendal nerve block. All blocks were performed by the same two anesthesiologists, and the same surgeons performed the surgical procedures. The Face, Legs, Activity, Cry, and Consolability (FLACC) scale was used for postoperative pain management. The primary outcome of the study was time to first analgesic requirement. Secondary outcomes were FLACC scores at different time points, and types and cumulative doses of analgesic drugs. RESULTS: Dorsal penile nerve block provided longer analgesia than pudendal nerve block (32.29 ± 5.47 hours and 21.13 ± 3.53 hours, respectively; differences in mean: 11.16, 95% CI: 7.873-14.465) (P < .001). FLACC scores at the time of first analgesic requirement were significantly lower in dorsal penile nerve block group than pudendal nerve block group (median [IQR]: 2 [2-2.5] and 3 [3-5], respectively; differences in median: -1, 95% CI: -1.851 to -0.149) (P < .001). CONCLUSION: Ultrasound-guided dorsal penile nerve block provided a longer analgesic period and reduced opioid consumption compared to neurostimulator-guided pudendal nerve block.

Evaluation of the efficacy of Hypericum perforatum (St. John's wort) oil in the prevention of stricture due to esophageal corrosive burns.

BACKGROUND/PURPOSE: The inflammatory response that follows the caustic burns results in fibrosis on the esophageal wall leading to esophageal stricture, dysphagia, and malnutrition. The controversy over the use of corticosteroids warrants alternative therapeutic interventions. We investigated the effect of extracts from St. John's wort (SJW) with known wound-healing activity on stricture formation in rat esophageal injury models. METHODS: Five experimental groups were involved: sham group with no injury, control group with injury without treatment, and three different treatment groups (methylprednisolone, SJW extract, and combination of the two). Histopathological examination of esophageal damage and collagen accumulation, stenosis index, and tissue hydroxyproline levels were used to assess stricture and the effect of treatments. RESULTS: There was a significant weight loss in all groups except for those without injury and those treated with SJW extract, the latter gained weight albeit not significant. Stenosis index was increased in all groups compared to sham but not significantly in those treated with SJW extract. Histopathological and biochemical analyses produced mixed results. CONCLUSIONS: Some of the experimental indicators such as weight gain and stenosis index suggested the treatment of esophageal injury models using extracts of St. John's wort effective while other histopathological indicators show no significant benefit.

Erector Spinae Plane Block vs Quadratus Lumborum Block for pediatric lower abdominal surgery: A double blinded, prospective, and randomized trial.

STUDY OBJECTIVE: To evaluate and compare the analgesic effect of ultrasound-guided erector spinae plane (ESP) block with ultrasound-guided Quadratus Lumborum Block in pediatric lower abdominal surgeries. DESIGN: Randomized, prospective, double-blinded trial. SETTING: Operating room and surgical ward. PATIENTS: Sixty patients, aged 1 to 7 years with ASA scores of I-II scheduled for elective lower abdominal surgery were included in the study. INTERVENTIONS: Patients were randomized into two groups as ESPB group and QLB group. Ultrasound guided ESP block at L1 vertebral level was performed preoperatively using 0.5 ml/kg 0.25% bupivacaine (max 20 ml) to the patients in ESPB group. And ultrasound guided QLB block with transmuscular approach was performed preoperatively using 0.5 ml/kg 0.25% bupivacaine (max 20 ml) to the patients in QLB group. MEASUREMENTS: Face, Legs, Activity, Cry and Consolability (FLACC) scores for pain were recorded at 0, 1, 3 and 6 h postoperatively. Analgesic requirements and time to first analgesic requirement were also recorded. MAIN RESULTS: Fifty-seven patients were included in the final analyses. No significant difference was determined between the groups' FLACC scores at 0, 1, 3 or 6 h postoperatively (p > 0.05). No significant difference was also determined in times to first analgesia between the groups (p > 0.05). CONCLUSIONS: This study shows that the ESPB provides similar postoperative analgesia to the QLB in pediatric patients undergoing lower abdominal surgery. Clinicians could decide according to their clinical experiences. CLINICAL TRIALS: https://clinicaltrials.gov/ct2/show/NCT03463382.