Machine learning based outcome prediction of microsurgically treated unruptured intracranial aneurysms.

Machine learning (ML) has revolutionized data processing in recent years. This study presents the results of the first prediction models based on a long-term monocentric data registry of patients with microsurgically treated unruptured intracranial aneurysms (UIAs) using a temporal train-test split. Temporal train-test splits allow to simulate prospective validation, and therefore provide more accurate estimations of a model's predictive quality when applied to future patients. ML models for the prediction of the Glasgow outcome scale, modified Rankin Scale (mRS), and new transient or permanent neurological deficits (output variables) were created from all UIA patients that underwent microsurgery at the Kepler University Hospital Linz (Austria) between 2002 and 2020 (n = 466), based on 18 patient- and 10 aneurysm-specific preoperative parameters (input variables). Train-test splitting was performed with a temporal split for outcome prediction in microsurgical therapy of UIA. Moreover, an external validation was conducted on an independent external data set (n = 256) of the Department of Neurosurgery, University Medical Centre Hamburg-Eppendorf. In total, 722 aneurysms were included in this study. A postoperative mRS > 2 was best predicted by a quadratic discriminant analysis (QDA) estimator in the internal test set, with an area under the receiver operating characteristic curve (ROC-AUC) of 0.87 ± 0.03 and a sensitivity and specificity of 0.83 ± 0.08 and 0.71 ± 0.07, respectively. A Multilayer Perceptron predicted the post- to preoperative mRS difference > 1 with a ROC-AUC of 0.70 ± 0.02 and a sensitivity and specificity of 0.74 ± 0.07 and 0.50 ± 0.04, respectively. The QDA was the best model for predicting a permanent new neurological deficit with a ROC-AUC of 0.71 ± 0.04 and a sensitivity and specificity of 0.65 ± 0.24 and 0.60 ± 0.12, respectively. Furthermore, these models performed significantly better than the classic logistic regression models (p < 0.0001). The present results showed good performance in predicting functional and clinical outcomes after microsurgical therapy of UIAs in the internal data set, especially for the main outcome parameters, mRS and permanent neurological deficit. The external validation showed poor discrimination with ROC-AUC values of 0.61, 0.53 and 0.58 respectively for predicting a postoperative mRS > 2, a pre- and postoperative difference in mRS > 1 point and a GOS < 5. Therefore, generalizability of the models could not be demonstrated in the external validation. A SHapley Additive exPlanations (SHAP) analysis revealed that this is due to the most important features being distributed quite differently in the internal and external data sets. The implementation of newly available data and the merging of larger databases to form more broad-based predictive models is imperative in the future.

Using emergency department triage for machine learning-based admission and mortality prediction.

AIMS: Patient admission is a decision relying on sparsely available data. This study aims to provide prediction models for discharge versus admission for ward observation or intensive care, and 30 day-mortality for patients triaged with the Manchester Triage System. METHODS: This is a single-centre, observational, retrospective cohort study from data within ten minutes of patient presentation at the interdisciplinary emergency department of the Kepler University Hospital, Linz, Austria. We trained machine learning models including Random Forests and Neural Networks individually to predict discharge versus ward observation or intensive care admission, and 30 day-mortality. For analysis of the features' relevance, we used permutation feature importance. RESULTS: A total of 58323 adult patients between 1 December 2015 and 31 August 2020 were included. Neural Networks and Random Forests predicted admission to ward observation with an AUC-ROC of 0.842 ±â€…0.00 with the most important features being age and chief complaint. For admission to intensive care, the models had an AUC-ROC of 0.819 ±â€…0.002 with the most important features being the Manchester Triage category and heart rate, and for the outcome 30 day-mortality an AUC-ROC of 0.925 ±â€…0.001. The most important features for the prediction of 30 day-mortality were age and general ward admission. CONCLUSION: Machine learning can provide prediction on discharge versus admission to general wards and intensive care and inform about risk on 30 day-mortality for patients in the emergency department.

Workflow assessment of an augmented reality application for planning of perforator flaps in plastic reconstructive surgery: Game or game changer?

Objective: In contrast to the rising amount of financial investments for research and development in medical technology worldwide is the lack of usability and clinical readiness of the produced systems. We evaluated an augmented reality (AR) setup under development for preoperative perforator vessel mapping for elective autologous breast reconstruction. Methods: In this grant-supported research pilot, we used magnetic resonance angiography data (MR-A) of the trunk to superimpose the scans on the corresponding patients with hands-free AR goggles to identify regions-of-interest for surgical planning. Perforator location was assessed using MR-A imaging (MR-A projection) and Doppler ultrasound data (3D distance) and confirmed intraoperatively in all cases. We evaluated usability (System Usability Scale, SUS), data transfer load and documented personnel hours for software development, correlation of image data, as well as processing duration to clinical readiness (time from MR-A to AR projections per scan). Results: All perforator locations were confirmed intraoperatively, and we found a strong correlation between MR-A projection and 3D distance measurements (Spearman r = 0.894). The overall usability (SUS) was 67 ± 10 (=moderate to good). The presented setup for AR projections took 173 min to clinical readiness (=availability on AR device per patient). Conclusion: In this pilot, we calculated development investments based on project-approved grant-funded personnel hours with a moderate to good usability outcome resulting from some limitations: assessment was based on one-time testing with no previous training, a time lag of AR visualizations on the body and difficulties in spatial AR orientation. The use of AR systems can provide new opportunities for future surgical planning, but has more potential for educational (e.g., patient information) or training purposes of medical under- and postgraduates (spatial recognition of imaging data associated with anatomical structures and operative planning). We expect future usability improvements with refined user interfaces, faster AR hardware and artificial intelligence-enhanced visualization techniques.

Epidemiology of burn injury and the ideal dressing in global burn care - Regional differences explored.

PURPOSE: Burn injuries are to this day a major cause of morbidity and mortality, especially within low- and middle-income countries. Understanding the etiology of burn injury and epidemiologic- and hospital-specific factors associated with burns is vital for allotting resources for prevention and treatment. Therefore, the purpose of this study was to develop a profile of epidemiological differences in burn care and the ideal burn dressing among the different continents based on a global online survey. OBJECTIVES: This analysis evaluated trends in demographics, epidemiology of burn care, burn incidence, infection, related mortality and burn treatment (e.g., dressing changes and materials). The objective of this study was to investigate and compare the epidemiological profile of burn injury/care amongst the continents and a global control group to determine their utility for guiding evidence-based burn care and identify differences and/or similarities in their clinical practice. METHODS: A retrospective analysis of data was performed that was acquired during a previous study investigating the ideal burn dressing on a global perspective. The data was analyzed depending on the continent, on which the respondent indicated their hospital to be (Africa, Australia & New Zealand, Asia, Europe, Middle and South America, North America). Statistical analysis was performed to evaluate patient and hospital demographics and variables associated with burn injuries and their treatment. Outcomes of interest also included infections, mortality, length of stay on the ICU and important burn dressing characteristics. RESULTS: Healthcare providers in different areas of the world share similar views and needs regarding burn care management and on what constitutes an ideal burn dressing. We found significant differences in the various continents regarding hospitalization and length of stay on the ICU, with Australia taking the lead. Africa, with a high proportion of low-income-countries, reported the highest rate of burn infections, mortality, and a disproportionally high number of burn incidences amongst children. In general, men were mostly obtaining burn injuries amongst all continents. We found no significant differences regarding the most important characteristics of an ideal burn dressing. CONCLUSION: Our results suggest significant epidemiological differences regarding burn injuries and care amongst the continents, possibly resulting from the different infrastructure and/or circumstances on the various continents. Future scientific studies need to focus on adequate pain management and designing longer lasting materials that contain the "ideal" properties, by also taking individual regional needs/desires and the patient's perspective and economic boundaries into account. This analysis has delivered valuable insights into the epidemiological differences and/or similarities amongst the various continents.

Lifting Hospital Electronic Health Record Data Treasures: Challenges and Opportunities.

Electronic health records (EHRs) have been successfully used in data science and machine learning projects. However, most of these data are collected for clinical use rather than for retrospective analysis. This means that researchers typically face many different issues when attempting to access and prepare the data for secondary use. We aimed to investigate how raw EHRs can be accessed and prepared in retrospective data science projects in a disciplined, effective, and efficient way. We report our experience and findings from a large-scale data science project analyzing routinely acquired retrospective data from the Kepler University Hospital in Linz, Austria. The project involved data collection from more than 150,000 patients over a period of 10 years. It included diverse data modalities, such as static demographic data, irregularly acquired laboratory test results, regularly sampled vital signs, and high-frequency physiological waveform signals. Raw medical data can be corrupted in many unexpected ways that demand thorough manual inspection and highly individualized data cleaning solutions. We present a general data preparation workflow, which was shaped in the course of our project and consists of the following 7 steps: obtain a rough overview of the available EHR data, define clinically meaningful labels for supervised learning, extract relevant data from the hospital's data warehouses, match data extracted from different sources, deidentify them, detect errors and inconsistencies therein through a careful exploratory analysis, and implement a suitable data processing pipeline in actual code. Only few of the data preparation issues encountered in our project were addressed by generic medical data preprocessing tools that have been proposed recently. Instead, highly individualized solutions for the specific data used in one's own research seem inevitable. We believe that the proposed workflow can serve as a guidance for practitioners, helping them to identify and address potential problems early and avoid some common pitfalls.

Technical and Medical Aspects of Burn Size Assessment and Documentation.

In burn medicine, the percentage of the burned body surface area (TBSA-B) to the total body surface area (TBSA) is a crucial parameter to ensure adequate treatment and therapy. Inaccurate estimations of the burn extent can lead to wrong medical decisions resulting in considerable consequences for patients. These include, for instance, over-resuscitation, complications due to fluid aggregation from burn edema, or non-optimal distribution of patients. Due to the frequent inaccurate TBSA-B estimation in practice, objective methods allowing for precise assessments are required. Over time, various methods have been established whose development has been influenced by contemporary technical standards. This article provides an overview of the history of burn size estimation and describes existing methods with a critical view of their benefits and limitations. Traditional methods that are still of great practical relevance were developed from the middle of the 20th century. These include the "Lund Browder Chart", the "Rule of Nines", and the "Rule of Palms". These methods have in common that they assume specific values for different body parts' surface as a proportion of the TBSA. Due to the missing consideration of differences regarding sex, age, weight, height, and body shape, these methods have practical limitations. Due to intensive medical research, it has been possible to develop three-dimensional computer-based systems that consider patients' body characteristics and allow a very realistic burn size assessment. To ensure high-quality burn treatment, comprehensive documentation of the treatment process, and wound healing is essential. Although traditional paper-based documentation is still used in practice, it no longer meets modern requirements. Instead, adequate documentation is ensured by electronic documentation systems. An illustrative software already being used worldwide is "BurnCase 3D". It allows for an accurate burn size assessment and a complete medical documentation.

Global burn care and the ideal burn dressing reloaded - A survey of global experts.

PURPOSE: Burn care is a highly relevant medical specialty in every part of the world. Different infrastructure, healthcare systems and access to medical supplies lead to different needs, treatment strategies and outcomes. A fundamental tool in a burn care provider's armamentarium is the use of different dressings. Several studies have investigated the question of the ideal burn dressing, but none could achieve a proper global perspective. With advanced dressings being on the rise, we conducted this study to get a global understanding of the actual use and idea of the ideal burn dressing. OBJECTIVE: The objective of this study was to investigate the understanding of an 'ideal burn dressing' on a global scale. MATERIALS AND METHODS: A questionnaire about burn care and the ideal burn dressing has been created and translated to five of the most spoken languages world-wide (English, Spanish, French, Chinese, Indonesian). It has been uploaded to an online survey platform and sent out to burn experts worldwide. The voluntary participation was possible for a period of four weeks. RESULTS: In total, 196 respondents from 49 countries participated in the study, yielding a response rate of 24.5%. The most important burn dressing characteristics in a cumulative ranking were (1) lack of adhesion (80.54%), (2) pain-free dressing change (79.87%), (3) requirement of fewer dressing changes, while in a linear ranking they were (1) anti-infective (35.14% 1st), pain-reduction (24.14% 2nd), and high absorbency (23.49% 3rd). Silver-based dressings are the most used dressings for superficial (45.21%) and deep (52.78%). 94.81% believe that the choice of burn dressing affects the outcome. CONCLUSION: This investigation has delivered valuable insights into the global perspective of the ideal burn dressing. Yet, the question of the ideal burn dressing is still inconclusive. Wound dressing research is of fundamental interest for patients, healthcare providers and healthcare systems.

BurnCase 3D software validation study: Burn size measurement accuracy and inter-rater reliability.

OBJECTIVE: The aim of this study was to compare the accuracy of burn size estimation using the computer-assisted software BurnCase 3D (RISC Software GmbH, Hagenberg, Austria) with that using a 2D scan, considered to be the actual burn size. METHODS: Thirty artificial burn areas were pre planned and prepared on three mannequins (one child, one female, and one male). Five trained physicians (raters) were asked to assess the size of all wound areas using BurnCase 3D software. The results were then compared with the real wound areas, as determined by 2D planimetry imaging. To examine inter-rater reliability, we performed an intraclass correlation analysis with a 95% confidence interval. RESULTS: The mean wound area estimations of the five raters using BurnCase 3D were in total 20.7±0.9% for the child, 27.2±1.5% for the female and 16.5±0.1% for the male mannequin. Our analysis showed relative overestimations of 0.4%, 2.8% and 1.5% for the child, female and male mannequins respectively, compared to the 2D scan. The intraclass correlation between the single raters for mean percentage of the artificial burn areas was 98.6%. There was also a high intraclass correlation between the single raters and the 2D Scan visible. CONCLUSION: BurnCase 3D is a valid and reliable tool for the determination of total body surface area burned in standard models. Further clinical studies including different pediatric and overweight adult mannequins are warranted.

Smartphone applications in burns.

OBJECTIVE: Since the introduction of applications (apps) for smartphones, the popularity of medical apps has been rising. The aim of this review was to demonstrate the current availability of apps related to burns on Google's Android and Apple's iOS store as well as to include a review of their developers, features, and costs. METHODS: A systematic online review of Google Play Store and Apple's App Store was performed by using the following search terms: "burn," "burns," "thermal," and the German word "Verbrennung." All apps that were programmed for use as medical apps for burns were included. The review was performed from 25 February until 1 March 2014. A closer look at the free and paid calculation apps including a standardized patient was performed. RESULTS: Four types of apps were identified: calculators, information apps, book/journal apps, and games. In Google Play Store, 31 apps were related to burns, of which 20 were calculation apps (eight for estimating the total body surface area (TBSA) and nine for total fluid requirement (TFR)). In Apple's App Store, under the category of medicine, 39 apps were related to burns, of which 21 were calculation apps (19 for estimating the TBSA and 17 for calculating the TFR). In 19 out of 32 available calculation apps, our study showed a correlation of the calculated TFR compared to our standardized patient. CONCLUSION: The review demonstrated that many apps for medical burns are available in both common app stores. Even free available calculation apps may provide a more objective and reproducible procedure compared to manual/subjective estimations, although there is still a lack of data security especially in personal data entered in calculation apps. Further clinical studies including smartphone apps for burns should be performed.

Intuitive presentation of clinical forensic data using anonymous and person-specific 3D reference manikins.

The increasing use of CT/MR devices in forensic analysis motivates the need to present forensic findings from different sources in an intuitive reference visualization, with the aim of combining 3D volumetric images along with digital photographs of external findings into a 3D computer graphics model. This model allows a comprehensive presentation of forensic findings in court and enables comparative evaluation studies correlating data sources. The goal of this work was to investigate different methods to generate anonymous and patient-specific 3D models which may be used as reference visualizations. The issue of registering 3D volumetric as well as 2D photographic data to such 3D models is addressed to provide an intuitive context for injury documentation from arbitrary modalities. We present an image processing and visualization work-flow, discuss the major parts of this work-flow, compare the different investigated reference models, and show a number of cases studies that underline the suitability of the proposed work-flow for presenting forensically relevant information in 3D visualizations.

The potential impact of wrong TBSA estimations on fluid resuscitation in patients suffering from burns: things to keep in mind.

INTRODUCTION: Accurate estimation of burn size is of critical importance, as it is incorporated in every resuscitation formula. The aim of this study was to investigate total burn surface area (TBSA) accuracy among burn specialists, evaluate the potential impact of incorrect evaluation on variations of resultant fluid resuscitation volumes and to discuss future possibilities to estimate or measure TBSA more precisely. METHODS: In a poll during two international burn meetings in 2010 and 2011 demonstrating three pictures of patients with different burn wound patterns and sizes we asked participants to estimate the total surface area burned in percentages. We then calculated resultant fluid volume differences based on established resuscitation formulas. RESULTS: In the polled 80 participants, the estimations for three patients demonstrated the following differences (DIF=MAX-MIN): for patient 1, 2 and 3 they were 22.5 (25-2.5), 16.5 (20-3.5) and 31.5 (40-8.5) %TBSA, respectively. Based on these differences we calculated the volume differences for patients 1,2 and 3, which were 1080ml (Cincinnati Formula), 5280ml (Parkland Formula) and 2016ml (Cincinnati Formula), respectively. CONCLUSIONS: The analysis showed high deviations of total body surface area among participants, also resulting in large variations of initial fluid resuscitation volumes. One option to address estimation variances is to perform more accurate assessments; also incorporating new technologies aiding to improve the quality of body surface estimations and related decisions.

The pain and stress of wound treatment in patients with burns: an international burn specialist perspective.

UNLABELLED: This study aimed to explore the views of burn specialists on the importance of reducing stress and pain during wound treatment. METHODS: Burns specialists were invited to complete an online survey, consisting of 10 questions about pain and stress in their patients. RESULTS: There were 141 respondents from 39 countries. Most were European (54.9%), and the majority were surgeons (71.8%). Pain-free and stress-free dressing changes were viewed as important overall ('very important:' 47.5% and 40.8%, respectively), although, in both cases, 11.3% did not view either to be important. Respondents identified 7 benefits of simple, pain-free dressing removal, although the focus was on clinical advantages rather than being patient-centered. Although most acknowledged that pain is linked with stress, disagreement levels ranged from 21.9% to 25.3%. Additionally, only 22.5% agreed that stress is related to wound healing. CONCLUSION: In general, burn specialists recognized that pain can lead to stress and that it is important to reduce stress and pain at dressing changes. Most also acknowledged that stress can affect wound healing. However, these results suggest a need for research to further explore perceptions about pain and stress, and how these perceptions can impact wound management regimes.

The properties of an "ideal" burn wound dressing--what do we need in daily clinical practice? Results of a worldwide online survey among burn care specialists.

OBJECTIVE: Using Internet polling to classify characteristics of a burn wound dressing considered as "ideal" by burn care specialists for small sized burns (<20% TBSA). METHODS: Open, voluntary Internet-based cross-sectional survey with twenty non-compulsory questions and collection of information related to profession, staff grade, work location. RESULTS: In total one-hundred and twenty-one participants from 39 countries were included (response rate: 121/1000=12.1%) within the one month survey period (1-31st December 2011). The majority of respondents were surgeons (72.1%; 88/121), and most participants were from Europe 59.4% (72/121). According to the survey the following are the properties of an "ideal" burn wound dressing: non-adhesion ("essential": 55/120, 45.8%; "desirable": 50/120, 41.7%), absorbency ("essential": 41/120, 34.2%; "desirable": 64/120, 53.3%) and antimicrobial activity ("essential": 52/121, 43.0%; "desirable": 49/121, 40.5%). In addition, ease of removal, which would produce more pain-free dressing changes, was also considered to be an asset - ideally requiring dressing changes twice per week with a range of different dressing sizes available. As polled directly, most of the respondents thought that such a dressing was currently not available. CONCLUSION: This Internet-based survey provides a first insight into a 'wish list' of properties for burn wound dressings required by specialists in burn care from around the world. As with any kind of idealism, to date, no such burn wound dressing seems to be available in clinical practice according to the poll. Future scientific efforts need to focus on designing materials, which feature at least some of the properties revealed by this analysis.