Background:Given the absence of consolidated and standardized international guidelines for managing pediatric appendicitis and the few strictly data-driven studies in this specific, we investigated the use of machine learning (ML) classifiers for predicting the diagnosis, management and severity of appendicitis in children.Materials and Methods:Predictive models were developed and validated on a dataset acquired from 430 children and adolescents aged 0-18 years, based on a range of information encompassing history, clinical examination, laboratory parameters, and abdominal ultrasonography. Logistic regression, random forests, and gradient boosting machines were used for predicting the three target variables.Results:A random forest classifier achieved areas under the precision-recall curve of 0.94, 0.92, and 0.70, respectively, for the diagnosis, management, and severity of appendicitis. We identified smaller subsets of 6, 17, and 18 predictors for each of targets that sufficed to achieve the same performance as the model based on the full set of 38 variables. We used these findings to develop the user-friendly online Appendicitis Prediction Tool for children with suspected appendicitis.Discussion:This pilot study considered the most extensive set of predictor and target variables to date and is the first to simultaneously predict all three targets in children: diagnosis, management, and severity. Moreover, this study presents the first ML model for appendicitis that was deployed as an open access easy-to-use online tool.Conclusion:ML algorithms help to overcome the diagnostic and management challenges posed by appendicitis in children and pave the way toward a more personalized approach to medical decision-making. Further validation studies are needed to develop a finished clinical decision support system.

Appendicitis is among the most frequent reasons for pediatric abdominal surgeries. Previous decision support systems for appendicitis have focused on clinical, laboratory, scoring, and computed tomography data and have ignored abdominal ultrasound, despite its noninvasive nature and widespread availability. In this work, we present interpretable machine learning models for predicting the diagnosis, management and severity of suspected appendicitis using ultrasound images. Our approach utilizes concept bottleneck models (CBM) that facilitate interpretation and interaction with high-level concepts understandable to clinicians. Furthermore, we extend CBMs to prediction problems with multiple views and incomplete concept sets. Our models were trained on a dataset comprising 579 pediatric patients with 1709 ultrasound images accompanied by clinical and laboratory data. Results show that our proposed method enables clinicians to utilize a human-understandable and intervenable predictive model without compromising performance or requiring time-consuming image annotation when deployed. For predicting the diagnosis, the extended multiview CBM attained an AUROC of 0.80 and an AUPR of 0.92, performing comparably to similar black-box neural networks trained and tested on the same dataset.

Introduction: Since early 2020 the COVID-19 pandemic and statutory preventive reorganization of treatment capacities with cancellation of elective surgery as well as curfew regulations led to vastly decreased utilization of primary health care.Materials and Methods: To assess whether there are negative effects on pediatric acute care in Bavaria during the spring 2020 lockdown a state-wide retrospective multi-center study was performed to analyze the rate of perforated appendicitis during lockdown. Children who have been operated on during the corresponding period in 2018/19 served as control group.Results: Overall, 514 patients (292 boys, 222 girls) were included (2020: 176 patients; 2019: 181 patients; 2018: 157 patients). Median age was 11.2 years. Four hundred thirty-nine patients (85.4%) underwent laparoscopic surgery, 69 (13.4%) open surgery and 1.2% underwent conversion from laparoscopic to open surgery. In 2020 a perforation rate of 27.8% (49/176 patients) was found, in 2018–2019 perforation rate was 20.7% (70/338 patients, p = 0.0359, Cochran-Mantel-Haenszel-Test). Subgroup analysis showed that in younger patients (≤ 11.2 years), in 2020 perforation rate was significantly higher with 37.6% (32/85 patients), while 22.2% (39/176) in 2018/2019 (p = 0.014, Fisher's exact test).In boys perforation rate was significantly higher in 2020 with 35.0% (35/100 patients) compared to 21.4% in 2018–2019 (p = 0.0165, Fisher's exact test).Conclusion: During the period of curfew regulations in Bavaria the rate of perforated appendicitis in childhood increased significantly, especially in younger children and boys. Potentially this has to be attributed to delayed presentation to pediatric surgery care. Because of potential long-term sequelae of perforated appendicitis these adverse effects during curfew have to be taken into account for future political decision making to ensure reasonable patient care and avoid collateral damage in near-future or on-going pandemic situations.

The moisture content of the human skin, but also the loss of water through the skin, the transepidermal water loss (TEWL), plays a significant role in the skin’s health. Various medical indications require the use of a wound dressing. However, how the skin environment changes under a wound dressing has not yet been sufficiently investigated. Skin moisture and TEWL values were measured in 20 healthy volunteers before and after the application of a total of 23 different wound dressings distributed over the back. Significant changes in the parameters from day 1 to day 2 were tested. Wound dressings change the underlying skin environment. Occlusive dressings significantly increase skin hydration and TEWL. The findings could contribute to quantitative analysis and monitoring of topical-wound therapy in the future.

Appendicitis is a common childhood disease, the management of which still lacks consolidated international criteria. In clinical practice, heuristic scoring systems are often used to assess the urgency of patients with suspected appendicitis. Previous work on machine learning for appendicitis has focused on conventional classification models, such as logistic regression and tree-based ensembles. In this study, we investigate the use of risk supersparse linear integer models (risk SLIM) for learning data-driven risk scores to predict the diagnosis, management, and complications in pediatric patients with suspected appendicitis on a dataset consisting of 430 children from a tertiary care hospital. We demonstrate the efficacy of our approach and compare the performance of learnt risk scores to previous analyses with random forests. Risk SLIM is able to detect medically meaningful features and outperforms the traditional appendicitis scores, while at the same time is better suited for the clinical setting than tree-based ensembles.

(1) Background: Isolated posterior cruciate ligament (PCL) tears represent a severe type of injury. In hospitals, PCL reconstruction (PCL-R) is less frequently performed than other types of knee surgery. It is unclear whether there is consensus among surgeons on how to perform rehabilitation after PCL-R or if there are different, more individual approaches in daily routines. (2) Methods: Rehabilitation protocols and their main criteria (the progression of weight bearing and range of motion, the use of knee braces, rehabilitation training, and sports-specific training) were retrospectively analyzed after PCL-R. (3) Results: Only 33 of 120 (27.5%) analyzed institutes use rehabilitation protocols after PCL-R. The applied protocols showed vast differences between the individual rehabilitation criteria, especially with regard to the progression of weight bearing and the range of motion. The only standardized recommendations were the obligatory use of knee braces and the general restriction of weight bearing and range of motion immediately post-surgery. Therefore, because of the lack of a consensus about a standardized rehabilitation protocol after PCL-R, no recommendation can be made on one particular protocol. (4) Conclusion: There is no acknowledged standardized rehabilitation protocol after PCL-R. In clinical practice, recommendations are influenced by, i.a., surgeons’ opinions and experience. The lack of scientific evidence on a particular standardized rehabilitation protocol after PCL-R suggests that rehabilitation protocols need to be tailored to the individual patient.