Kidney abnormality segmentation has important potential to enhance the clinical workflow, especially in settings requiring quantitative assessments. Kidney volume could serve as an important biomarker for renal diseases, with changes in volume correlating directly with kidney function. Currently, clinical practice often relies on subjective visual assessment for evaluating kidney size and abnormalities, including tumors and cysts, which are typically staged based on diameter, volume, and anatomical location. To support a more objective and reproducible approach, this research aims to develop a robust, thoroughly validated kidney abnormality segmentation algorithm, made publicly available for clinical and research use. We employ publicly available training datasets and leverage the state-of-the-art medical image segmentation framework nnU-Net. Validation is conducted using both proprietary and public test datasets, with segmentation performance quantified by Dice coefficient and the 95th percentile Hausdorff distance. Furthermore, we analyze robustness across subgroups based on patient sex, age, CT contrast phases, and tumor histologic subtypes. Our findings demonstrate that our segmentation algorithm, trained exclusively on publicly available data, generalizes effectively to external test sets and outperforms existing state-of-the-art models across all tested datasets. Subgroup analyses reveal consistent high performance, indicating strong robustness and reliability. The developed algorithm and associated code are publicly accessible at https://github.com/DIAGNijmegen/oncology-kidney-abnormality-segmentation.
Randomized controlled trials (RCTs) are the standard for evaluating the effectiveness of clinical interventions. To address the limitations of RCTs on real-world populations, we developed a methodology that uses a large observational electronic health record (EHR) dataset. Principles of regression discontinuity (rd) were used to derive randomized data subsets to test expert-driven interventions using dynamic Bayesian Networks (DBNs) do-operations. This combined method was applied to a chronic kidney disease (CKD) cohort of more than two million individuals and used to understand the associational and causal relationships of CKD variables with respect to a surrogate outcome of >=40% decline in estimated glomerular filtration rate (eGFR). The associational and causal analyses depicted similar findings across DBNs from two independent healthcare systems. The associational analysis showed that the most influential variables were eGFR, urine albumin-to-creatinine ratio, and pulse pressure, whereas the causal analysis showed eGFR as the most influential variable, followed by modifiable factors such as medications that may impact kidney function over time. This methodology demonstrates how real-world EHR data can be used to provide population-level insights to inform improved healthcare delivery.
The estimated Glomerular Filtration Rate (eGFR) is an essential indicator of kidney function in clinical practice. Although traditional equations and Machine Learning (ML) models using clinical and laboratory data can estimate eGFR, accurately predicting future eGFR levels remains a significant challenge for nephrologists and ML researchers. Recent advances demonstrate that Large Language Models (LLMs) and Large Multimodal Models (LMMs) can serve as robust foundation models for diverse applications. This study investigates the potential of LMMs to predict future eGFR levels with a dataset consisting of laboratory and clinical values from 50 patients. By integrating various prompting techniques and ensembles of LMMs, our findings suggest that these models, when combined with precise prompts and visual representations of eGFR trajectories, offer predictive performance comparable to existing ML models. This research extends the application of foundation models and suggests avenues for future studies to harness these models in addressing complex medical forecasting challenges.
The shortage of nephrologists and the growing public health concern over renal failure have spurred the demand for AI systems capable of autonomously detecting kidney abnormalities. Renal failure, marked by a gradual decline in kidney function, can result from factors like cysts, stones, and tumors. Chronic kidney disease may go unnoticed initially, leading to untreated cases until they reach an advanced stage. The dataset, comprising 12,427 images from multiple hospitals in Dhaka, was categorized into four groups: cyst, tumor, stone, and normal. Our methodology aims to enhance CT scan image quality using Cropping, Resizing, and CALHE techniques, followed by feature extraction with our proposed Adaptive Local Binary Pattern (A-LBP) feature extraction method compared with the state-of-the-art local binary pattern (LBP) method. Our proposed features fed into classifiers such as Random Forest, Decision Tree, Naive Bayes, K-Nearest Neighbor, and SVM. We explored an ensemble model with soft voting to get a more robust model for our task. We got the highest of more than 99% in accuracy using our feature descriptor and ensembling five classifiers (Random Forest, Decision Tree, Naive Bayes, K-Nearest Neighbor, Support Vector Machine) with the soft voting method.
The relationship between acute kidney injury (AKI) prediction and nephrotoxic drugs, or drugs that adversely affect kidney function, is one that has yet to be explored in the critical care setting. One contributing factor to this gap in research is the limited investigation of drug modalities in the intensive care unit (ICU) context, due to the challenges of processing prescription data into the corresponding drug representations and a lack in the comprehensive understanding of these drug representations. This study addresses this gap by proposing a novel approach that leverages patient prescription data as a modality to improve existing models for AKI prediction. We base our research on Electronic Health Record (EHR) data, extracting the relevant patient prescription information and converting it into the selected drug representation for our research, the extended-connectivity fingerprint (ECFP). Furthermore, we adopt a unique multimodal approach, developing machine learning models and 1D Convolutional Neural Networks (CNN) applied to clinical drug representations, establishing a procedure which has not been used by any previous studies predicting AKI. The findings showcase a notable improvement in AKI prediction through the integration of drug embeddings and other patient cohort features. By using drug features represented as ECFP molecular fingerprints along with common cohort features such as demographics and lab test values, we achieved a considerable improvement in model performance for the AKI prediction task over the baseline model which does not include the drug representations as features, indicating that our distinct approach enhances existing baseline techniques and highlights the relevance of drug data in predicting AKI in the ICU setting
Kidneys are the filter of the human body. About 10 % of the global population is thought to be affected by Chronic Kidney Disease (CKD), which causes kidney function to decline. To protect in danger patients from additional kidney damage, effective risk evaluation of CKD and appropriate CKD monitoring are crucial. Due to quick and precise detection capabilities, Machine Learning models can help practitioners accomplish this goal efficiently therefore an enormous number of diagnosis systems and processes in the healthcare sector nowadays are relying on machine learning due to its disease prediction capability. In this study, we designed and suggested disease predictive computer-aided designs for the diagnosis of CKD. The dataset for CKD is attained from the repository of machine learning of UCL, with a few missing values; those are filled in using “mean/mode” and “Random sampling method” strategies. After successfully achieving the missing data, eight ML techniques (Random Forest, SVM, Naive Bayes, Logistic Regression, KNN, XG _Boost, Decision Tree and AdaBoost) were used to establish models and the performance evaluation comparisons among the result accuracies are measured by the techniques to find the machine learning models with highest accuracies. Among them, Random Forest as well as Logistic Regression showed an outstanding 99% accuracy, followed by the Ada Boost, XG-Boost, Naive Bayes, Decision Tree, and SVM whereas the KNN classifier model stands last with an accuracy of 73%.
In vitro models play a crucial role in advancing our understanding of biological processes, disease mechanisms, and developing screening platforms for drug discovery. Kidneys play an instrumental role in transport and elimination of drugs and toxins. However, despite the well-established patient-to-patient differences in kidney function and disease manifestation, progression and prognostic, few studies take this variability into consideration. In particular, the discrepancies between female and male biology warrants a better representation within kidney in vitro models. The omission of sex as a biological variable poses the significant risk of overlooking sex-specific mechanisms in health and disease and potential differences in drug efficacy and toxicity between males and females. This review aims to highlight the importance of incorporating sex dimorphism in kidney in vitro models by examining the sexual characteristics in the context of the current state-of-the-art. Furthermore, this review underscores opportunities for improving kidney models by incorporating sex-specific traits. Ultimately, this roadmap to incorporating sex-dimorphism in kidney in vitro models will facilitate the creation of better models for studying sex-specific mechanisms in the kidney and their impact on drug efficacy and safety.
Peritoneal dialysis (PD) is becoming more popular as a result of a rising interest in home dialysis, lower intrusion in social life and longer preservation of residual kidney function. However, PD has several important drawbacks: small solute clearance is relatively low compared to hemodialysis and technique survival is limited. Application of continuous flow, sorbent-based dialysate regeneration and novel glucose-sparing PD solutions are some solutions proposed to address the limitations of PD. To optimize and personalize current and novel PD therapies, patient peritoneal characteristics interacting with PD techniques need to be studied together and separately as they interplay. However, considering the multitude of parameters, it would be difficult, expensive, and time consuming to optimize all parameter settings only with the help of clinical trials. Mathematical modelling is an exciting tool to dissect these interacting processes and comprehend PD techniques better at a patient specific level. In this review, we look at the history of computational PD models, explore the many ways a computational PD model can be constructed and review the various existing PD models that can be used to optimize and personalize PD treatment.
Medical applications of machine learning (ML) have experienced a surge in popularity in recent years. The intensive care unit (ICU) is a natural habitat for ML given the abundance of available data from electronic health records. Models have been proposed to address numerous ICU prediction tasks like the early detection of complications. While authors frequently report state-of-the-art performance, it is challenging to verify claims of superiority. Datasets and code are not always published, and cohort definitions, preprocessing pipelines, and training setups are difficult to reproduce. This work introduces Yet Another ICU Benchmark (YAIB), a modular framework that allows researchers to define reproducible and comparable clinical ML experiments; we offer an end-to-end solution from cohort definition to model evaluation. The framework natively supports most open-access ICU datasets (MIMIC III/IV, eICU, HiRID, AUMCdb) and is easily adaptable to future ICU datasets. Combined with a transparent preprocessing pipeline and extensible training code for multiple ML and deep learning models, YAIB enables unified model development. Our benchmark comes with five predefined established prediction tasks (mortality, acute kidney injury, sepsis, kidney function, and length of stay) developed in collaboration with clinicians. Adding further tasks is straightforward by design. Using YAIB, we demonstrate that the choice of dataset, cohort definition, and preprocessing have a major impact on the prediction performance - often more so than model class - indicating an urgent need for YAIB as a holistic benchmarking tool. We provide our work to the clinical ML community to accelerate method development and enable real-world clinical implementations. Software Repository: https://github.com/rvandewater/YAIB.
Urine output is a vital parameter to gauge kidney health. Current monitoring methods include manually written records, invasive urinary catheterization or ultrasound measurements performed by highly skilled personnel. Catheterization bears high risks of infection while intermittent ultrasound measures and manual recording are time consuming and might miss early signs of kidney malfunction. Bioimpedance (BI) measurements may serve as a non-invasive alternative for measuring urine volume in vivo. However, limited robustness have prevented its clinical translation. Here, a deep learning-based algorithm is presented that processes the local BI of the lower abdomen and suppresses artefacts to measure the bladder volume quantitatively, non-invasively and without the continuous need for additional personnel. A tetrapolar BI wearable system called ANUVIS was used to collect continuous bladder volume data from three healthy subjects to demonstrate feasibility of operation, while clinical gold standards of urodynamic (n=6) and uroflowmetry tests (n=8) provided the ground truth. Optimized location for electrode placement and a model for the change in BI with changing bladder volume is deduced. The average error for full bladder volume estimation and for residual volume estimation was -29 +/-87.6 ml, thus, comparable to commercial portable ultrasound devices (Bland Altman analysis showed a bias of -5.2 ml with LoA between 119.7 ml to -130.1 ml), while providing the additional benefit of hands-free, non-invasive, and continuous bladder volume estimation. The combination of the wearable BI sensor node and the presented algorithm provides an attractive alternative to current standard of care with potential benefits in providing insights into kidney function.
Head and neck cancers are the fifth most common cancer worldwide, and recently, analysis of Positron Emission Tomography (PET) and Computed Tomography (CT) images has been proposed to identify patients with a prognosis. Even though the results look promising, more research is needed to further validate and improve the results. This paper presents the work done by team MLC for the 2022 version of the HECKTOR grand challenge held at MICCAI 2022. For Task 1, the automatic segmentation task, our approach was, in contrast to earlier solutions using 3D segmentation, to keep it as simple as possible using a 2D model, analyzing every slice as a standalone image. In addition, we were interested in understanding how different modalities influence the results. We proposed two approaches; one using only the CT scans to make predictions and another using a combination of the CT and PET scans. For Task 2, the prediction of recurrence-free survival, we first proposed two approaches, one where we only use patient data and one where we combined the patient data with segmentations from the image model. For the prediction of the first two approaches, we used Random Forest. In our third approach, we combined patient data and image data using XGBoost. Low kidney function might worsen cancer prognosis. In this approach, we therefore estimated the kidney function of the patients and included it as a feature. Overall, we conclude that our simple methods were not able to compete with the highest-ranking submissions, but we still obtained reasonably good scores. We also got interesting insights into how the combination of different modalities can influence the segmentation and predictions.
Apelin is a neuro-vasoactive peptide that plays a major role in the control of cardiovascular functions and water balance, but has an in-vivo half-life in the minute range, limiting its therapeutic use. We previously developed LIT01-196, a systemically active metabolically stable apelin-17 analog, produced by chemical addition of a fluorocarbon chain to the N-terminal part of apelin-17. LIT01-196 behaves as a potent full agonist for the apelin receptor and has an in vivo half-life in the bloodstream of 28 min after intravenous (i.v.) and 156 min after subcutaneous (s.c.) administrations in conscious normotensive rats. We aimed to investigate the effects of LIT01-196 following systemic administrations on arterial blood pressure, heart rate, fluid balance and electrolytes in conscious normotensive and hypertensive deoxycorticosterone acetate (DOCA)-salt rats. Acute i.v. LIT01-196 administration, in increasing doses, dose-dependently decreases arterial blood pressure with ED 50 values of 9.8 and 3.1 nmol/kg in normotensive and hypertensive rats, respectively. This effect occurs for both via a nitric oxide-dependent mechanism. Moreover, acute s.c. LIT01-196 administration (90 nmol/kg) normalizes arterial blood pressure in conscious hypertensive DOCA-salt rats for more than 7 h. The LIT01-196-induced blood pressure decrease remains unchanged after 4 consecutive daily s.c. administrations of 90 nmol/kg, and does not induce any alteration of plasma sodium and potassium levels and kidney function as shown by the lack of change in plasma creatinine and urea nitrogen levels. Activating the apelin receptor with LIT01-196 may constitute a novel approach for the treatment of hypertension.
Vlahos et al., Ref. 1, NPJ Clean water. 4, 50 (2021) have reported the presence of pesticide contamination above safe levels in a "single time-point analysis" of well water in a region in Sri Lanka where chronic kidney disease of unknown etiology (CKDu) is endemic. They conclude "that agrochemical use in paddy and other agricultural practices ... of the Green Revolution in Sri Lanka may now be contributing to ill health, rapid progression of disease, and mortality". The authors also propose "reducing ... agrochemical contaminants in Sri Lanka and other tropical countries to reduce ... CKDu". These conclusions, based on what they call a "single time-point analysis", tantamount to an identification of the etiology of CKDu are unsupported by the evidence presented by Vlahos et al. They do not satisfy, say, even the simplest of Bradford-Hill criteria for causation. In particular, (i) similar but non-persistent pesticide excesses have been detected sporadically in most parts of the country including where there is no CKDu; (ii) the pesticides reported in (1) cause both hepatotoxicity and nephrotoxicity; the latter with glomerular damage while CKDu is associated with tubulo-interstitial damage where no hepatotoxic symptoms have been reported; (iii) the pesticides detected have short half-lives and are used over short periods during farming; so the one time-point analysis is inadequate and misleading; (iv) farming communities that use pesticides in the same way but remain essentially without CKDu are found to exist adjacent to communities with CKDu; (v) the CKDu prevalence seems to correlate with local geomorphology but without correlation to agriculture which is practiced in most parts of the country. .
The recent success of machine learning methods applied to time series collected from Intensive Care Units (ICU) exposes the lack of standardized machine learning benchmarks for developing and comparing such methods. While raw datasets, such as MIMIC-IV or eICU, can be freely accessed on Physionet, the choice of tasks and pre-processing is often chosen ad-hoc for each publication, limiting comparability across publications. In this work, we aim to improve this situation by providing a benchmark covering a large spectrum of ICU-related tasks. Using the HiRID dataset, we define multiple clinically relevant tasks in collaboration with clinicians. In addition, we provide a reproducible end-to-end pipeline to construct both data and labels. Finally, we provide an in-depth analysis of current state-of-the-art sequence modeling methods, highlighting some limitations of deep learning approaches for this type of data. With this benchmark, we hope to give the research community the possibility of a fair comparison of their work.
Existing burn resuscitation protocols exhibit large variability in treatment efficacy. Hence, they must be further optimized based on comprehensive knowledge of burn pathophysiology. A physics-based mathematical model that can replicate physiological responses in diverse burn patients can serve as an attractive basis to perform non-clinical testing of burn resuscitation protocols and to expand knowledge on burn pathophysiology. We intend to develop, optimize, validate, and analyze a mathematical model to replicate physiological responses in burn patients. Using clinical datasets collected from 233 burn patients receiving burn resuscitation, we developed and validated a mathematical model applicable to computer-aided in-human burn resuscitation trial and knowledge expansion. Using the validated mathematical model, we examined possible physiological mechanisms responsible for the cohort-dependent differences in burn pathophysiology between younger versus older patients, female versus male patients, and patients with versus without inhalational injury. We demonstrated that the mathematical model could replicate physiological responses in burn patients associated with wide demographic characteristics and injury severity and that an increased inflammatory response to injury may be a key contributing factor in increasing the mortality risk of older patients and patients with inhalation injury via an increase in the fluid retention. The mathematical model may provide an attractive platform to conduct non-clinical testing of burn resuscitation protocols and test new hypotheses on burn pathophysiology.
Kidney DCE-MRI aims at both qualitative assessment of kidney anatomy and quantitative assessment of kidney function by estimating the tracer kinetic (TK) model parameters. Accurate estimation of TK model parameters requires an accurate measurement of the arterial input function (AIF) with high temporal resolution. Accelerated imaging is used to achieve high temporal resolution, which yields under-sampling artifacts in the reconstructed images. Compressed sensing (CS) methods offer a variety of reconstruction options. Most commonly, sparsity of temporal differences is encouraged for regularization to reduce artifacts. Increasing regularization in CS methods removes the ambient artifacts but also over-smooths the signal temporally which reduces the parameter estimation accuracy. In this work, we propose a single image trained deep neural network to reduce MRI under-sampling artifacts without reducing the accuracy of functional imaging markers. Instead of regularizing with a penalty term in optimization, we promote regularization by generating images from a lower dimensional representation. In this manuscript we motivate and explain the lower dimensional input design. We compare our approach to CS reconstructions with multiple regularization weights. Proposed approach results in kidney biomarkers that are highly correlated with the ground truth markers estimated using the CS reconstruction which was optimized for functional analysis. At the same time, the proposed approach reduces the artifacts in the reconstructed images.
Chronic Kidney Disease (CKD), where delayed recognition implies premature mortality, is currently experiencing a globally increasing incidence and high cost to health systems. Data mining allows discovering subtle patterns in CKD indicators to contribute to an early diagnosis. This work presents the development and evaluation of an explainable prediction model that would support clinicians in the early diagnosis of CKD patients. The model development is based on a data management pipeline that detects the best combination of ensemble trees algorithms and features selected concerning classification performance. Furthermore, the main contribution of the paper involves an explainability-driven approach that allows selecting the best predictive model maintaining a balance between accuracy and explainability. Therefore, the most balanced explainable predictive model implements an extreme gradient boosting classifier over 3 features (packed cell value, specific gravity, and hypertension), achieving an accuracy of 99.2% and 97.5% with cross-validation technique and with new unseen data respectively. In addition, an analysis of the model's explainability shows that the packed cell value is the most relevant feature that influences the prediction results of the model, followed by specific gravity and hypertension. This small number of feature selected results in a reduced cost of the early diagnosis of CKD implying a promising solution for developing countries.
The pressure in the renal interstitium is an important factor for normal kidney function. Here we develop a computational model of the rat kidney and use it to investigate the relationship between arterial blood pressure and interstitial fluid pressure. In addition, we investigate how tissue flexibility influences this relationship. Due to the complexity of the model, the large number of parameters, and the inherent uncertainty of the experimental data, we utilize Monte Carlo sampling to study the model's behavior under a wide range of parameter values and to compute first- and total-order sensitivity indices. Characteristically, at elevated arterial blood pressure, the model predicts cases with increased or reduced interstitial pressure. The transition between the two cases is controlled mostly by the compliance of the blood vessels located before the afferent arterioles.
Multiple myeloma (MM), a plasma cell cancer, is associated with many health challenges, including damage to the kidney by tubulointerstitial fibrosis. We develop a mathematical model which captures the qualitative behavior of the cell and protein populations involved. Specifically, we model the interaction between cells in the proximal tubule of the kidney, free light chains, renal fibroblasts, and myeloma cells. We analyze the model for steady-state solutions to find a mathematically and biologically relevant stable steady-state solution. This foundational model provides a representation of dynamics between key populations in tubulointerstitial fibrosis that demonstrates how these populations interact to affect patient prognosis in patients with MM and renal impairment.
The UK Biobank is collecting extensive data on health-related characteristics of over half a million volunteers. The biological samples of blood and urine can provide valuable insight on kidney function, with important links to cardiovascular and metabolic health. Further information on kidney anatomy could be obtained by medical imaging. In contrast to the brain, heart, liver, and pancreas, no dedicated Magnetic Resonance Imaging (MRI) is planned for the kidneys. An image-based assessment is nonetheless feasible in the neck-to-knee body MRI intended for abdominal body composition analysis, which also covers the kidneys. In this work, a pipeline for automated segmentation of parenchymal kidney volume in UK Biobank neck-to-knee body MRI is proposed. The underlying neural network reaches a relative error of 3.8%, with Dice score 0.956 in validation on 64 subjects, close to the 2.6% and Dice score 0.962 for repeated segmentation by one human operator. The released MRI of about 40,000 subjects can be processed within two days, yielding volume measurements of left and right kidney. Algorithmic quality ratings enabled the exclusion of outliers and potential failure cases. The resulting measurements can be studied and shared for large-scale investigation of associations and longitudinal changes in parenchymal kidney volume.