Prediction of diabetic kidney disease with machine learning algorithms, upon the initial diagnosis of type 2 diabetes mellitus.

INTRODUCTION: Diabetic kidney disease (DKD) accounts for the majority of increased risk of mortality for patients with diabetes, and eventually manifests in approximately half of those patients diagnosed with type 2 diabetes mellitus (T2DM). Although increased screening frequency can avoid delayed diagnoses, this is not uniformly implemented. The purpose of this study was to develop and retrospectively validate a machine learning algorithm (MLA) that predicts stages of DKD within 5 years upon diagnosis of T2DM. RESEARCH DESIGN AND METHODS: Two MLAs were trained to predict stages of DKD severity, and compared with the Centers for Disease Control and Prevention (CDC) risk score to evaluate performance. The models were validated on a hold-out test set as well as an external dataset sourced from separate facilities. RESULTS: The MLAs outperformed the CDC risk score in both the hold-out test and external datasets. Our algorithms achieved an area under the receiver operating characteristic curve (AUROC) of 0.75 on the hold-out set for prediction of any-stage DKD and an AUROC of over 0.82 for more severe endpoints, compared with the CDC risk score with an AUROC <0.70 on all test sets and endpoints. CONCLUSION: This retrospective study shows that an MLA can provide timely predictions of DKD among patients with recently diagnosed T2DM.

A comparative analysis of machine learning approaches to predict C. difficile infection in hospitalized patients.

BACKGROUND: Interventions to better prevent or manage Clostridioides difficile infection (CDI) may significantly reduce morbidity, mortality, and healthcare spending. METHODS: We present a retrospective study using electronic health record data from over 700 United States hospitals. A subset of hospitals was used to develop machine learning algorithms (MLAs); the remaining hospitals served as an external test set. Three MLAs were evaluated: gradient-boosted decision trees (XGBoost), Deep Long Short Term Memory neural network, and one-dimensional convolutional neural network. MLA performance was evaluated with area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, diagnostic odds ratios and likelihood ratios. RESULTS: The development dataset contained 13,664,840 inpatient encounters with 80,046 CDI encounters; the external dataset contained 1,149,088 inpatient encounters with 7,107 CDI encounters. The highest AUROCs were achieved for XGB, Deep Long Short Term Memory neural network, and one-dimensional convolutional neural network via abstaining from use of specialized training techniques, resampling in isolation, and resampling and output bias in combination, respectively. XGBoost achieved the highest AUROC. CONCLUSIONS: MLAs can predict future CDI in hospitalized patients using just 6 hours of data. In clinical practice, a machine-learning based tool may support prophylactic measures, earlier diagnosis, and more timely implementation of infection control measures.

Early prediction of severe acute pancreatitis using machine learning.

BACKGROUND: Acute pancreatitis (AP) is one of the most common causes of gastrointestinal-related hospitalizations in the United States. Severe AP (SAP) is associated with a mortality rate of nearly 30% and is distinguished from milder forms of AP. Risk stratification to identify SAP cases needing inpatient treatment is an important aspect of AP diagnosis. METHODS: We developed machine learning algorithms to predict which patients presenting with AP would require treatment for SAP. Three models were developed using logistic regression, neural networks, and XGBoost. Models were assessed in terms of area under the receiver operating characteristic (AUROC) and compared to the Harmless Acute Pancreatitis Score (HAPS) and Bedside Index for Severity in Acute Pancreatitis (BISAP) scores for AP risk stratification. RESULTS: 61,894 patients were used to train and test the machine learning models. With an AUROC value of 0.921, the model developed using XGBoost outperformed the logistic regression and neural network-based models. The XGBoost model also achieved a higher AUROC than both HAPS and BISAP for identifying patients who would be diagnosed with SAP. CONCLUSIONS: Machine learning may be able to improve the accuracy of AP risk stratification methods and allow for more timely treatment and initiation of interventions.

Semisupervised Deep Learning Techniques for Predicting Acute Respiratory Distress Syndrome From Time-Series Clinical Data: Model Development and Validation Study.

BACKGROUND: A high number of patients who are hospitalized with COVID-19 develop acute respiratory distress syndrome (ARDS). OBJECTIVE: In response to the need for clinical decision support tools to help manage the next pandemic during the early stages (ie, when limited labeled data are present), we developed machine learning algorithms that use semisupervised learning (SSL) techniques to predict ARDS development in general and COVID-19 populations based on limited labeled data. METHODS: SSL techniques were applied to 29,127 encounters with patients who were admitted to 7 US hospitals from May 1, 2019, to May 1, 2021. A recurrent neural network that used a time series of electronic health record data was applied to data that were collected when a patient's peripheral oxygen saturation level fell below the normal range (<97%) to predict the subsequent development of ARDS during the remaining duration of patients' hospital stay. Model performance was assessed with the area under the receiver operating characteristic curve and area under the precision recall curve of an external hold-out test set. RESULTS: For the whole data set, the median time between the first peripheral oxygen saturation measurement of <97% and subsequent respiratory failure was 21 hours. The area under the receiver operating characteristic curve for predicting subsequent ARDS development was 0.73 when the model was trained on a labeled data set of 6930 patients, 0.78 when the model was trained on the labeled data set that had been augmented with the unlabeled data set of 16,173 patients by using SSL techniques, and 0.84 when the model was trained on the entire training set of 23,103 labeled patients. CONCLUSIONS: In the context of using time-series inpatient data and a careful model training design, unlabeled data can be used to improve the performance of machine learning models when labeled data for predicting ARDS development are scarce or expensive.

A machine learning approach to predicting risk of myelodysplastic syndrome.

BACKGROUND: Early myelodysplastic syndrome (MDS) diagnosis can allow physicians to provide early treatment, which may delay advancement of MDS and improve quality of life. However, MDS often goes unrecognized and is difficult to distinguish from other disorders. We developed a machine learning algorithm for the prediction of MDS one year prior to clinical diagnosis of the disease. METHODS: Retrospective analysis was performed on 790,470 patients over the age of 45 seen in the United States between 2007 and 2020. A gradient boosted decision tree model (XGB) was built to predict MDS diagnosis using vital signs, lab results, and demographics from the prior two years of patient data. The XGB model was compared to logistic regression (LR) and artificial neural network (ANN) models. The models did not use blast percentage and cytogenetics information as inputs. Predictions were made one year prior to MDS diagnosis as determined by International Classification of Diseases (ICD) codes, 9th and 10th revisions. Performance was assessed with regard to area under the receiver operating characteristic curve (AUROC). RESULTS: On a hold-out test set, the XGB model achieved an AUROC value of 0.87 for prediction of MDS one year prior to diagnosis, with a sensitivity of 0.79 and specificity of 0.80. The XGB model was compared against LR and ANN models, which achieved an AUROC of 0.838 and 0.832, respectively. CONCLUSIONS: Machine learning may allow for early MDS diagnosis MDS and more appropriate treatment administration.

Sterilization effects on ultrathin film polymer coatings for silicon-based implantable medical devices.

Novel biomaterials for medical device applications must be stable throughout all stages of preparation for surgery, including sterilization. There is a paucity of information on the effects of sterilization on sub-10 nm-thick polymeric surface coatings suitable for silicon-based bioartificial organs. This study explores the effect of five standard sterilization methods on three surface coatings applied to silicon: polyethylene glycol (PEG), poly(sulfobetaine methacrylate) (pSBMA), and poly (2-methacryloyloxyethyl phosphorylcholine) (pMPC). Autoclave, dry heat, hydrogen peroxide (H2 O2 ) plasma, ethylene oxide gas (EtO), and electron beam (E-beam) treated coatings were analyzed to determine possible polymer degradation with sterilization. Poststerilization, there were significant alterations in contact angle, maximum change resulting from H2 O2 (Δ - 14°), autoclave (Δ + 15°), and dry heat (Δ + 23°) treatments for PEG, pSBMA, and pMPC, respectively. Less than 5% coating thickness change was found with autoclave and EtO on PEG-silicon, E-beam on pSBMA-silicon and EtO treatment on pMPC-silicon. H2 O2 treatment resulted in at least 30% decrease in thickness for all coatings. Enzyme-linked immunosorbent assays showed significant protein adsorption increase for pMPC-silicon following all sterilization methods. E-beam on PEG-silicon and dry-heat treatment on pSBMA-silicon exhibited maximum protein adsorption in each coating subset. Overall, the data suggest autoclave and EtO treatments are well-suited for PEG-silicon, while E-beam is best suited for pSBMA-silicon. pMPC-silicon was least impacted by EtO treatment. H2 O2 treatment had a negative effect on all three coatings. These results can be used to determine which surface modifications and sterilization processes to utilize for devices in vivo. © 2017 Wiley Periodicals, Inc. J Biomed Mater Res Part B: Appl Biomater, 106B: 2327-2336, 2018.

Diffusive Silicon Nanopore Membranes for Hemodialysis Applications.

Hemodialysis using hollow-fiber membranes provides life-sustaining treatment for nearly 2 million patients worldwide with end stage renal disease (ESRD). However, patients on hemodialysis have worse long-term outcomes compared to kidney transplant or other chronic illnesses. Additionally, the underlying membrane technology of polymer hollow-fiber membranes has not fundamentally changed in over four decades. Therefore, we have proposed a fundamentally different approach using microelectromechanical systems (MEMS) fabrication techniques to create thin-flat sheets of silicon-based membranes for implantable or portable hemodialysis applications. The silicon nanopore membranes (SNM) have biomimetic slit-pore geometry and uniform pores size distribution that allow for exceptional permeability and selectivity. A quantitative diffusion model identified structural limits to diffusive solute transport and motivated a new microfabrication technique to create SNM with enhanced diffusive transport. We performed in vitro testing and extracorporeal testing in pigs on prototype membranes with an effective surface area of 2.52 cm2 and 2.02 cm2, respectively. The diffusive clearance was a two-fold improvement in with the new microfabrication technique and was consistent with our mathematical model. These results establish the feasibility of using SNM for hemodialysis applications with additional scale-up.

Preliminary Diffusive Clearance of Silicon Nanopore Membranes in a Parallel Plate Configuration for Renal Replacement Therapy.

Silicon nanopore membranes (SNMs) with compact geometry and uniform pore size distribution have demonstrated a remarkable capacity for hemofiltration. These advantages could potentially be used for hemodialysis. Here, we present an initial evaluation of the SNM's mechanical robustness, diffusive clearance, and hemocompatibility in a parallel plate configuration. Mechanical robustness of the SNM was demonstrated by exposing membranes to high flows (200 ml/min) and pressures (1,448 mm Hg). Diffusive clearance was performed in an albumin solution and whole blood with blood and dialysate flow rates of 25 ml/min. Hemocompatibility was evaluated using scanning electron microscopy and immunohistochemistry after 4 hours in an extracorporeal porcine model. The pressure drop across the flow cell was 4.6 mm Hg at 200 ml/min. Mechanical testing showed that SNM could withstand up to 775.7 mm Hg without fracture. Urea clearance did not show an appreciable decline in blood versus albumin solution. Extracorporeal studies showed blood was successfully driven via the arterial-venous pressure differential without thrombus formation. Bare silicon showed increased cell adhesion with a 4.1-fold increase and 1.8-fold increase over polyethylene glycol (PEG)-coated surfaces for tissue plasminogen factor (t-PA) and platelet adhesion (CD41), respectively. These initial results warrant further design and development of a fully scaled SNM-based parallel plate dialyzer for renal replacement therapy.