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.

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.

A therapeutic strategy to improve wound healing has become an increasingly important medical task due to the rising incidence of adiposity and type II diabetes as well as the proceeding population aging. In order to cope with the resulting burdens, new strategies to achieve rapid and complete wound healing must now be developed. Accordingly, the development of a bioactive wound dressing in the form of a messengerRNA (mRNA)-bearing poly(lactide-co-glycolide acid) (PLGA) coating on surgical suture is being pushed further with this study. Furthermore, the evaluation of the polymer-based transfection reagent Viromer RED has shown that it can be used for the transfection of eukaryotic cells: The mRNA gets properly complexed and translated into a functional protein. In addition, the mRNA-PLGA coating triggered the expression of the keratinocyte growth factor (KGF) in HaCat cells although KGF is not expressed under physiological conditions. Moreover, transfection via surgical sutures coated with mRNA does not affect the cell viability and a proinflammatory reaction in the transfected cells is not induced. These properties make the mRNA-PLGA coating very attractive for the in vivo application. For the future, this could mean that through the use of mRNA-coated sutures in surgical wound closure, cells in the wound area can be transfected directly, thus accelerating and improving wound healing.