Access to technology to support telehealth in areas without specialty care for liver disease.

BACKGROUND AND AIMS: Telehealth may be a successful strategy to increase access to specialty care for liver disease, but whether the areas with low access to care and a high burden of liver-related mortality have the necessary technology access to support a video-based telehealth strategy to expand access to care is unknown. APPROACH AND RESULTS: Access to liver disease specialty care was defined at the county level as <160.9 km (100 miles) from a liver transplant (LT) center or presence of local gastroenterology (GI). Liver-related mortality rates were compared by access to care, and access to technology was compared by degree of access to care and burden of liver-related mortality. Counties with low access to liver disease specialty care had higher rates of mortality from liver disease, and this was highest in areas both >160.9 km from an LT center and without local GI. These counties were more rural, had higher poverty, and had decreased access to devices and internet at broadband speeds. Technology access was lowest in areas with low access to care and the highest burden of liver-related mortality. CONCLUSIONS: Areas with poor access to liver disease specialty care have a greater burden of liver-related mortality, and many of their residents lack access to technology. Therefore, a telehealth strategy based solely on patient device ownership and internet access will exclude a large proportion of individuals in the areas of highest need. Further work should be done at the local and state levels to design optimal strategies to reach their populations of need.

Challenging diagnosis: unveiling extensive multisystemic sarcoidosis with musculoskeletal involvement through a clinically ambiguous soft tissue mass in the palm.

We report about a 33-year-old man who was referred for assessment of a progressively enlarging mass of the palmar hand muscles, serving as the initial indication of extensive multisystemic sarcoidosis with musculoskeletal involvement. The case underscores the diagnostic challenges associated with the indolent course of sarcoidosis, highlighting the need for recognizing seemingly benign symptoms for early detection. Musculoskeletal imaging findings presented in the case stress the importance of considering sarcoidosis in the differential diagnosis of orthopedic cases. This report emphasizes the importance of understanding possible musculoskeletal imaging findings in sarcoidosis, thereby enabling radiologists to effectively guide patient management.

A critical moment in machine learning in medicine: on reproducible and interpretable learning.

Over the past two decades, advances in computational power and data availability combined with increased accessibility to pre-trained models have led to an exponential rise in machine learning (ML) publications. While ML may have the potential to transform healthcare, this sharp increase in ML research output without focus on methodological rigor and standard reporting guidelines has fueled a reproducibility crisis. In addition, the rapidly growing complexity of these models compromises their interpretability, which currently impedes their successful and widespread clinical adoption. In medicine, where failure of such models may have severe implications for patients' health, the high requirements for accuracy, robustness, and interpretability confront ML researchers with a unique set of challenges. In this review, we discuss the semantics of reproducibility and interpretability, as well as related issues and challenges, and outline possible solutions to counteracting the "black box". To foster reproducibility, standard reporting guidelines need to be further developed and data or code sharing encouraged. Editors and reviewers may equally play a critical role by establishing high methodological standards and thus preventing the dissemination of low-quality ML publications. To foster interpretable learning, the use of simpler models more suitable for medical data can inform the clinician how results are generated based on input data. Model-agnostic explanation tools, sensitivity analysis, and hidden layer representations constitute further promising approaches to increase interpretability. Balancing model performance and interpretability are important to ensure clinical applicability. We have now reached a critical moment for ML in medicine, where addressing these issues and implementing appropriate solutions will be vital for the future evolution of the field.

Increase in acute mastoiditis at the end of the COVID-19 pandemic.

PURPOSE: Common respiratory infections were significantly reduced during the COVID-19 pandemic due to general protective and hygiene measures. The gradual withdrawal of these non-pharmaceutical interventions (NPI) was associated with a notable increase in these infections, particularly in pediatric and adult otorhinolaryngology. The aim of this retrospective monocentric study was to evaluate the impact of NPI during the COVID-19 pandemic on the incidence and severity of acute mastoiditis (AM). METHODS: Pre-pandemic clinical data of AM cases from 2011 to 2019 were compared with infection counts from January 2020 to June 2023 for seasonal periodicity, age-specific differences, pathogens, and complication rates in a German third-level hospital. RESULTS: Out of 196 patients with AM 133 were children, the majority between 1 and 5 years of age. Complications of AM, such as meningitis, brain abscess, and sinus vein thrombosis, were more common in adults (87%) than in children (17%). Morbidity and mortality rates were similar before, during and after the pandemic. Pneumococci were the most common pathogen in both age groups, with a post-pandemic cumulation of Streptococcus pyogenes infections in children. While pre-pandemic cases clustered in spring, seasonality was absent in all age groups during the main phase of the pandemic. The cessation of NPI caused a steep rise in AM cases in both age groups starting from December 2022. CONCLUSION: NPI during the COVID-19 pandemic reduced the incidence of AM. Their reversal led to a substantial increase in the incidence of AM during the post-pandemic period, which may be due to a general increase in viral respiratory infections and an insufficiently trained immune system.

Camel milk products beyond yoghurt and fresh milk: challenges, processing and applications.

Camel (Camelus dromedarius and (Camelus bactrianus) are commonly domesticated in the arid and semi-arid regions because they are well adapted to live in harsh climatic conditions. Camel milk is widely consumed in these regions due to its high nutritional value and medicinal properties. It is rich in protein, minerals and vitamins. Moreover, it possesses therapeutic properties such as anti-microbial, anti-oxidants, anti-viral and anti-cancer. Camel milk can be processed into value added products with the aim of extending shelf life and diversifying its usage. However, there are various challenges experienced in processing of camel milk products. This study aims at reviewing published literature on camel milk products processing, processing challenges, the available solutions and applications. To achieve these aims, literature search was carried out using narrative methodology. Literature review provided information concerning processing of camel milk products, the challenges, how to overcome these processing challenges and applications. From this review of literature on camel milk products it can be concluded that it's possible to process these products with some challenges but scientific and technological solutions are available that are improving over time.

Characterization of social determinants of health of a liver transplant referral population.

Disparities exist in referral and access to the liver transplant (LT) waitlist, and social determinants of health (SDOH) are increasingly recognized as important factors driving health inequities, including in LT. The SDOH of potential transplant candidates is therefore important to characterize when designing targeted interventions to promote equity in access to LT. Yet, it is uncertain how a transplant center should approach this issue, characterize SDOH, identify disparities, and use these data to inform interventions. We performed a retrospective study of referrals for first-time, single-organ LT to our center from 2016 to 2020. Addresses were geoprocessed and mapped to the corresponding county, census tract, and census block group to assess their geospatial distribution, identify potential disparities in referrals, and characterize their communities across multiple domains of SDOH to identify potential barriers to evaluation and selection. We identified variability in referral patterns and areas with disproportionately low referrals, including counties in the highest quartile of liver disease mortality (9%) and neighborhoods in the highest quintile of socioeconomic deprivation (17%) and quartile of poverty (21%). Black individuals were also under-represented compared with expected state demographics (12% vs. 18%). Among the referral population, several potential barriers to evaluation and selection for LT were identified, including poverty, educational attainment, access to healthy food, and access to technology. This approach to the characterization of a transplant center's referral population by geographic location and associated SDOH demonstrates a model for identifying disparities in a referral population and potential barriers to evaluation that can be used to inform targeted interventions for disparities in LT access.

A tutorial on Bayesian single-test reliability analysis with JASP.

The current practice of reliability analysis is both uniform and troublesome: most reports consider only Cronbach's α, and almost all reports focus exclusively on a point estimate, disregarding the impact of sampling error. In an attempt to improve the status quo we have implemented Bayesian estimation routines for five popular single-test reliability coefficients in the open-source statistical software program JASP. Using JASP, researchers can easily obtain Bayesian credible intervals to indicate a range of plausible values and thereby quantify the precision of the point estimate. In addition, researchers may use the posterior distribution of the reliability coefficients to address practically relevant questions such as "What is the probability that the reliability of my test is larger than a threshold value of .80?". In this tutorial article, we outline how to conduct a Bayesian reliability analysis in JASP and correctly interpret the results. By making available a computationally complex procedure in an easy-to-use software package, we hope to motivate researchers to include uncertainty estimates whenever reporting the results of a single-test reliability analysis.

A scoping review of inequities in access to organ transplant in the United States.

BACKGROUND: Organ transplant is the preferred treatment for end-stage organ disease, yet the majority of patients with end-stage organ disease are never placed on the transplant waiting list. Limited access to the transplant waiting list combined with the scarcity of the organ pool result in over 100,000 deaths annually in the United States. Patients face unique barriers to referral and acceptance for organ transplant based on social determinants of health, and patients from disenfranchised groups suffer from disproportionately lower rates of transplantation. Our objective was to review the literature describing disparities in access to organ transplantation based on social determinants of health to integrate the existing knowledge and guide future research. METHODS: We conducted a scoping review of the literature reporting disparities in access to heart, lung, liver, pancreas and kidney transplantation based on social determinants of health (race, income, education, geography, insurance status, health literacy and engagement). Included studies were categorized based on steps along the transplant care continuum: referral for transplant, transplant evaluation and selection, living donor identification/evaluation, and waitlist outcomes. RESULTS: Our search generated 16,643 studies, of which 227 were included in our final review. Of these, 34 focused on disparities in referral for transplantation among patients with chronic organ disease, 82 on transplant selection processes, 50 on living donors, and 61 on waitlist management. In total, 15 studies involved the thoracic organs (heart, lung), 209 involved the abdominal organs (kidney, liver, pancreas), and three involved multiple organs. Racial and ethnic minorities, women, and patients in lower socioeconomic status groups were less likely to be referred, evaluated, and added to the waiting list for organ transplant. The quality of the data describing these disparities across the transplant literature was variable and overwhelmingly focused on kidney transplant. CONCLUSIONS: This review contextualizes the quality of the data, identifies seminal work by organ, and reports gaps in the literature where future research on disparities in organ transplantation should focus. Future work should investigate the association of social determinants of health with access to the organ transplant waiting list, with a focus on prospective analyses that assess interventions to improve health equity.

Racial and Socioeconomic Disparities in Utilization of Telehealth in Patients with Liver Disease During COVID-19.

BACKGROUND AND AIMS: The coronavirus disease 2019 (COVID-19) pandemic resulted in a rapid expansion of telehealth services in hepatology. However, known racial and socioeconomic disparities in internet access potentially translate into barriers for the use of telehealth, particularly video technology. The specific aim of this study was to determine if disparities in race or socioeconomic status exist among patients utilizing telehealth visits during COVID-19. METHODS: We performed a retrospective cohort study of all adult patients evaluated in hepatology clinics at Duke University Health System. Visit attempts from a pre-COVID baseline period (January 1, 2020 through February 29, 2020; n = 3328) were compared to COVID period (April 1, 2020 through May 30, 2020; n = 3771). RESULTS: On multinomial regression modeling, increasing age was associated with higher odds of a phone or incomplete visit (canceled, no-show, or rescheduled after May 30,2020), and non-Hispanic Black race was associated with nearly twice the odds of completing a phone visit instead of video visit, compared to non-Hispanic White patients. Compared to private insurance, Medicaid and Medicare were associated with increased odds of completing a telephone visit, and Medicaid was associated with increased odds of incomplete visits. Being single or previously married (separated, divorced, widowed) was associated with increased odds of completing a phone compared to video visit compared to being married. CONCLUSIONS: Though liver telehealth has expanded during the COVID-19 pandemic, disparities in overall use and suboptimal use (phone versus video) remain for vulnerable populations including those that are older, non-Hispanic Black, or have Medicare/Medicaid health insurance.

Tricuspid valve prolapse as an early predictor for severe phenotype in children with Marfan syndrome.

AIM: In Marfan syndrome, various cardiovascular pathologies, such as aortic dilatation and mitral valve pathologies, already occur in childhood and determine course of the disease. This study aimed to establish additional cardiovascular risk markers for severe Marfan phenotypes. We investigated tricuspid valve prolapse (TVP) and its predictive value for outcome of paediatric Marfan disease. METHODS: In this retrospective, observational cohort study, we identified 130 paediatric Marfan patients (10.7 ± 4.8 years) with FBN1 variants. We divided patients into two groups based on TVP presence and performed a cross-sectional analysis to investigate the association of TVP with other cardiovascular, ocular and systemic pathologies, at first and last visit. A longitudinal analysis was performed with follow-up data. RESULTS: At baseline, patients with TVP had higher incidence of aortic root dilatation (p = 0.013), mitral valve prolapse (p = 0.0001) and systemic manifestations (p = 0.025) than patients without TVP. At follow-up, previous presence of TVP predicted higher probability of aortic root dilatation (p = 0.002), mitral valve prolapse (p = 0.0001) and systemic manifestations (p = 0.002). CONCLUSION: This shows that TVP is linked to both cardiac and extracardiac Marfan manifestations and TVP is an important marker for a disease severity in these children. Therefore, TVP should be assessed routinely using echocardiography in paediatric Marfan patients.

Foundations of Machine Learning-Based Clinical Prediction Modeling: Part I-Introduction and General Principles.

We provide explanations on the general principles of machine learning, as well as analytical steps required for successful machine learning-based predictive modeling, which is the focus of this series. In particular, we define the terms machine learning, artificial intelligence, as well as supervised and unsupervised learning, continuing by introducing optimization, thus, the minimization of an objective error function as the central dogma of machine learning. In addition, we discuss why it is important to separate predictive and explanatory modeling, and most importantly state that a prediction model should not be used to make inferences. Lastly, we broadly describe a classical workflow for training a machine learning model, starting with data pre-processing and feature engineering and selection, continuing on with a training structure consisting of a resampling method, hyperparameter tuning, and model selection, and ending with evaluation of model discrimination and calibration as well as robust internal or external validation of the fully developed model. Methodological rigor and clarity as well as understanding of the underlying reasoning of the internal workings of a machine learning approach are required, otherwise predictive applications despite being strong analytical tools are not well accepted into the clinical routine.

Foundations of Machine Learning-Based Clinical Prediction Modeling: Part II-Generalization and Overfitting.

We review the concept of overfitting, which is a well-known concern within the machine learning community, but less established in the clinical community. Overfitted models may lead to inadequate conclusions that may wrongly or even harmfully shape clinical decision-making. Overfitting can be defined as the difference among discriminatory training and testing performance, while it is normal that out-of-sample performance is equal to or ever so slightly worse than training performance for any adequately fitted model, a massively worse out-of-sample performance suggests relevant overfitting. We delve into resampling methods, specifically recommending k-fold cross-validation and bootstrapping to arrive at realistic estimates of out-of-sample error during training. Also, we encourage the use of regularization techniques such as L1 or L2 regularization, and to choose an appropriate level of algorithm complexity for the type of dataset used. Data leakage is addressed, and the importance of external validation to assess true out-of-sample performance and to-upon successful external validation-release the model into clinical practice is discussed. Finally, for highly dimensional datasets, the concepts of feature reduction using principal component analysis (PCA) as well as feature elimination using recursive feature elimination (RFE) are elucidated.

Foundations of Machine Learning-Based Clinical Prediction Modeling: Part III-Model Evaluation and Other Points of Significance.

Various available metrics to describe model performance in terms of discrimination (area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 Score) and calibration (slope, intercept, Brier score, expected/observed ratio, Estimated Calibration Index, Hosmer-Lemeshow goodness-of-fit) are presented. Recalibration is introduced, with Platt scaling and Isotonic regression as proposed methods. We also discuss considerations regarding the sample size required for optimal training of clinical prediction models-explaining why low sample sizes lead to unstable models, and offering the common rule of thumb of at least ten patients per class per input feature, as well as some more nuanced approaches. Missing data treatment and model-based imputation instead of mean, mode, or median imputation is also discussed. We explain how data standardization is important in pre-processing, and how it can be achieved using, e.g. centering and scaling. One-hot encoding is discussed-categorical features with more than two levels must be encoded as multiple features to avoid wrong assumptions. Regarding binary classification models, we discuss how to select a sensible predicted probability cutoff for binary classification using the closest-to-(0,1)-criterion based on AUC or based on the clinical question (rule-in or rule-out). Extrapolation is also discussed.

Foundations of Machine Learning-Based Clinical Prediction Modeling: Part IV-A Practical Approach to Binary Classification Problems.

We illustrate the steps required to train and validate a simple, machine learning-based clinical prediction model for any binary outcome, such as, for example, the occurrence of a complication, in the statistical programming language R. To illustrate the methods applied, we supply a simulated database of 10,000 glioblastoma patients who underwent microsurgery, and predict the occurrence of 12-month survival. We walk the reader through each step, including import, checking, and splitting of datasets. In terms of pre-processing, we focus on how to practically implement imputation using a k-nearest neighbor algorithm, and how to perform feature selection using recursive feature elimination. When it comes to training models, we apply the theory discussed in Parts I-III. We show how to implement bootstrapping and to evaluate and select models based on out-of-sample error. Specifically for classification, we discuss how to counteract class imbalance by using upsampling techniques. We discuss how the reporting of a minimum of accuracy, area under the curve (AUC), sensitivity, and specificity for discrimination, as well as slope and intercept for calibration-if possible alongside a calibration plot-is paramount. Finally, we explain how to arrive at a measure of variable importance using a universal, AUC-based method. We provide the full, structured code, as well as the complete glioblastoma survival database for the readers to download and execute in parallel to this section.

Foundations of Machine Learning-Based Clinical Prediction Modeling: Part V-A Practical Approach to Regression Problems.

This chapter goes through the steps required to train and validate a simple, machine learning-based clinical prediction model for any continuous outcome. We supply fully structured code for the readers to download and execute in parallel to this section, as well as a simulated database of 10,000 glioblastoma patients who underwent microsurgery, and predict survival from diagnosis in months. We walk the reader through each step, including import, checking, splitting of data. In terms of pre-processing, we focus on how to practically implement imputation using a k-nearest neighbor algorithm. We also illustrate how to select features based on recursive feature elimination and how to use k-fold cross validation. We demonstrate a generalized linear model, a generalized additive model, a random forest, a ridge regressor, and a Least Absolute Shrinkage and Selection Operator (LASSO) regressor. Specifically for regression, we discuss how to evaluate root mean square error (RMSE), mean average error (MAE), and the R2 statistic, as well as how a quantile-quantile plot can be used to assess the performance of the regressor along the spectrum of the outcome variable, similarly to calibration when dealing with binary outcomes. Finally, we explain how to arrive at a measure of variable importance using a universal, nonparametric method.

Dimensionality Reduction: Foundations and Applications in Clinical Neuroscience.

Advancements in population neuroscience are spurred by the availability of large scale, open datasets, such as the Human Connectome Project or recently introduced UK Biobank. With the increasing data availability, analyses of brain imaging data employ more and more sophisticated machine learning algorithms. However, all machine learning algorithms must balance generalization and complexity. As the detail of neuroimaging data leads to high-dimensional data spaces, model complexity and hence the chance of overfitting increases. Different methodological approaches can be applied to alleviate the problems that arise in high-dimensional settings by reducing the original information into meaningful and concise features. One popular approach is dimensionality reduction, which allows to summarize high-dimensional data into low-dimensional representations while retaining relevant trends and patterns. In this paper, principal component analysis (PCA) is discussed as widely used dimensionality reduction method based on current examples of population-based neuroimaging analyses.

Introduction to Machine Learning in Neuroimaging.

Advancements in neuroimaging and the availability of large-scale datasets enable the use of more sophisticated machine learning algorithms. In this chapter, we non-exhaustively discuss relevant analytical steps for the analysis of neuroimaging data using machine learning (ML), while the field of radiomics will be addressed separately (c.f., Chap. 18 -Radiomics). Broadly classified into supervised and unsupervised approaches, we discuss the encoding/decoding framework, which is often applied in cognitive neuroscience, and the use of ML for the analysis of unlabeled data using clustering.

Machine Learning-Based Radiomics in Neuro-Oncology.

In the last decades, modern medicine has evolved into a data-centered discipline, generating massive amounts of granular high-dimensional data exceeding human comprehension. With improved computational methods, machine learning and artificial intelligence (AI) as tools for data processing and analysis are becoming more and more important. At the forefront of neuro-oncology and AI-research, the field of radiomics has emerged. Non-invasive assessments of quantitative radiological biomarkers mined from complex imaging characteristics across various applications are used to predict survival, discriminate between primary and secondary tumors, as well as between progression and pseudo-progression. In particular, the application of molecular phenotyping, envisioned in the field of radiogenomics, has gained popularity for both primary and secondary brain tumors. Although promising results have been obtained thus far, the lack of workflow standardization and availability of multicenter data remains challenging. The objective of this review is to provide an overview of novel applications of machine learning- and deep learning-based radiomics in primary and secondary brain tumors and their implications for future research in the field.

Foundations of Time Series Analysis.

For almost a century, classical statistical methods including exponential smoothing and autoregression integrated moving averages (ARIMA) have been predominant in the analysis of time series (TS) and in the pursuit of forecasting future events from historical data. TS are chronological sequences of observations, and TS data are therefore prevalent in many aspects of clinical medicine and academic neuroscience. With the rise of highly complex and nonlinear datasets, machine learning (ML) methods have become increasingly popular for prediction or pattern detection and within neurosciences, including neurosurgery. ML methods regularly outperform classical methods and have been successfully applied to, inter alia, predict physiological responses in intracranial pressure monitoring or to identify seizures in EEGs. Implementing nonparametric methods for TS analysis in clinical practice can benefit clinical decision making and sharpen our diagnostic armory.

The Artificial Intelligence Doctor: Considerations for the Clinical Implementation of Ethical AI.

The applications of artificial intelligence (AI) and machine learning (ML) in modern medicine are growing exponentially, and new developments are fast-paced. However, the lack of trust and appropriate legislation hinder its clinical implementation. Recently, there is a clear increase of directives and considerations on Ethical AI. However, most literature broadly deals with ethical tensions on a meta-level without offering hands-on advice in practice. In this article, we non-exhaustively cover basic practical guidelines regarding AI-specific ethical aspects, including transparency and explicability, equity and mitigation of biases, and lastly, liability.