More Like this

1. Confidence-Aware Severity Assessment of Lung Disease from Chest X-Rays Using Deep Neural Network on a Multi-Reader Dataset

   https://doi.org/10.1007/s10278-024-01151-5  

   Zandehshahvar, Mohammadreza; van_Assen, Marly; Kim, Eun; Kiarashi, Yashar; Keerthipati, Vikranth; Tessarin, Giovanni; Muscogiuri, Emanuele; Stillman, Arthur E; Filev, Peter; Davarpanah, Amir H; et al (August 2024, Journal of Imaging Informatics in Medicine)

   In this study, we present a method based on Monte Carlo Dropout (MCD) as Bayesian neural network (BNN) approximation for confidence-aware severity classification of lung diseases in COVID-19 patients using chest X-rays (CXRs). Trained and tested on 1208 CXRs from Hospital 1 in the USA, the model categorizes severity into four levels (i.e., normal, mild, moderate, and severe) based on lung consolidation and opacity. Severity labels, determined by the median consensus of five radiologists, serve as the reference standard. The model’s performance is internally validated against evaluations from an additional radiologist and two residents that were excluded from the median. The performance of the model is further evaluated on additional internal and external datasets comprising 2200 CXRs from the same hospital and 1300 CXRs from Hospital 2 in South Korea. The model achieves an average area under the curve (AUC) of 0.94 ± 0.01 across all classes in the primary dataset, surpassing human readers in each severity class and achieves a higher Kendall correlation coefficient (KCC) of 0.80 ± 0.03. The performance of the model is consistent across varied datasets, highlighting its generalization. A key aspect of the model is its predictive uncertainty (PU), which is inversely related to the level of agreement among radiologists, particularly in mild and moderate cases. The study concludes that the model outperforms human readers in severity assessment and maintains consistent accuracy across diverse datasets. Its ability to provide confidence measures in predictions is pivotal for potential clinical use, underscoring the BNN’s role in enhancing diagnostic precision in lung disease analysis through CXR. 

   more » « less
2. A vital sign-based prediction algorithm for differentiating COVID-19 versus seasonal influenza in hospitalized patients

   https://doi.org/10.1038/s41746-021-00467-8  

   Yanamala, Naveena; Krishna, Nanda H; Hathaway, Quincy A; Radhakrishnan, Aditya; Sunkara, Srinidhi; Patel, Heenaben; Farjo, Peter; Patel, Brijesh; Sengupta, Partho P (December 2021, npj Digital Medicine)

   Abstract Patients with influenza and SARS-CoV2/Coronavirus disease 2019 (COVID-19) infections have a different clinical course and outcomes. We developed and validated a supervised machine learning pipeline to distinguish the two viral infections using the available vital signs and demographic dataset from the first hospital/emergency room encounters of 3883 patients who had confirmed diagnoses of influenza A/B, COVID-19 or negative laboratory test results. The models were able to achieve an area under the receiver operating characteristic curve (ROC AUC) of at least 97% using our multiclass classifier. The predictive models were externally validated on 15,697 encounters in 3125 patients available on TrinetX database that contains patient-level data from different healthcare organizations. The influenza vs COVID-19-positive model had an AUC of 98.8%, and 92.8% on the internal and external test sets, respectively. Our study illustrates the potentials of machine-learning models for accurately distinguishing the two viral infections. The code is made available athttps://github.com/ynaveena/COVID-19-vs-Influenzaand may have utility as a frontline diagnostic tool to aid healthcare workers in triaging patients once the two viral infections start cocirculating in the communities. 

   more » « less
3. Initiation of Continuous Glucose Monitoring Is Linked to Improved Glycemic Control and Fewer Clinical Events in Type 1 and Type 2 Diabetes in the Veterans Health Administration

   https://doi.org/10.2337/dc22-2189  

   Reaven, Peter D.; Newell, Michelle; Rivas, Salvador; Zhou, Xinkai; Norman, Gregory J.; Zhou, Jin J. (February 2023, Diabetes Care)

   OBJECTIVETo determine the benefit of starting continuous glucose monitoring (CGM) in adult-onset type 1 diabetes (T1D) and type 2 diabetes (T2D) with regard to longer-term glucose control and serious clinical events. RESEARCH DESIGN AND METHODSA retrospective observational cohort study within the Veterans Affairs Health Care System was used to compare glucose control and hypoglycemia- or hyperglycemia-related admission to an emergency room or hospital and all-cause hospitalization between propensity score overlap weighted initiators of CGM and nonusers over 12 months. RESULTSCGM users receiving insulin (n = 5,015 with T1D and n = 15,706 with T2D) and similar numbers of nonusers were identified from 1 January 2015 to 31 December 2020. Declines in HbA1c were significantly greater in CGM users with T1D (−0.26%; 95% CI −0.33, −0.19%) and T2D (−0.35%; 95% CI −0.40, −0.31%) than in nonusers at 12 months. Percentages of patients achieving HbA1c <8 and <9% after 12 months were greater in CGM users. In T1D, CGM initiation was associated with significantly reduced risk of hypoglycemia (hazard ratio [HR] 0.69; 95% CI 0.48, 0.98) and all-cause hospitalization (HR 0.75; 95% CI 0.63, 0.90). In patients with T2D, there was a reduction in risk of hyperglycemia in CGM users (HR 0.87; 95% CI 0.77, 0.99) and all-cause hospitalization (HR 0.89; 95% CI 0.83, 0.97). Several subgroups (based on baseline age, HbA1c, hypoglycemic risk, or follow-up CGM use) had even greater responses. CONCLUSIONSIn a large national cohort, initiation of CGM was associated with sustained improvement in HbA1c in patients with later-onset T1D and patients with T2D using insulin. This was accompanied by a clear pattern of reduced risk of admission to an emergency room or hospital for hypoglycemia or hyperglycemia and of all-cause hospitalization. 

   more » « less
4. A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients

   https://doi.org/10.3390/diagnostics14090954  

   Islam, Warid; Abdoli, Neman; Alam, Tasfiq E; Jones, Meredith; Mutembei, Bornface M; Yan, Feng; Tang, Qinggong (May 2024, Diagnostics)

   Background: At the time of cancer diagnosis, it is crucial to accurately classify malignant gastric tumors and the possibility that patients will survive. Objective: This study aims to investigate the feasibility of identifying and applying a new feature extraction technique to predict the survival of gastric cancer patients. Methods: A retrospective dataset including the computed tomography (CT) images of 135 patients was assembled. Among them, 68 patients survived longer than three years. Several sets of radiomics features were extracted and were incorporated into a machine learning model, and their classification performance was characterized. To improve the classification performance, we further extracted another 27 texture and roughness parameters with 2484 superficial and spatial features to propose a new feature pool. This new feature set was added into the machine learning model and its performance was analyzed. To determine the best model for our experiment, Random Forest (RF) classifier, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) (four of the most popular machine learning models) were utilized. The models were trained and tested using the five-fold cross-validation method. Results: Using the area under ROC curve (AUC) as an evaluation index, the model that was generated using the new feature pool yields AUC = 0.98 ± 0.01, which was significantly higher than the models created using the traditional radiomics feature set (p < 0.04). RF classifier performed better than the other machine learning models. Conclusions: This study demonstrated that although radiomics features produced good classification performance, creating new feature sets significantly improved the model performance. 

   more » « less
5. Type 1 Diabetes Genetic Risk in 109,954 Veterans With Adult-Onset Diabetes: The Million Veteran Program (MVP)

   https://doi.org/10.2337/dc23-1927  

   Yang, Peter K.; Jackson, Sandra L.; Charest, Brian R.; Cheng, Yiling J.; Sun, Yan V.; Raghavan, Sridharan; Litkowski, Elizabeth M.; Legvold, Brian T.; Rhee, Mary K.; Oram, Richard A.; et al (April 2024, Diabetes Care)

   OBJECTIVETo characterize high type 1 diabetes (T1D) genetic risk in a population where type 2 diabetes (T2D) predominates. RESEARCH DESIGN AND METHODSCharacteristics typically associated with T1D were assessed in 109,594 Million Veteran Program participants with adult-onset diabetes, 2011–2021, who had T1D genetic risk scores (GRS) defined as low (0 to <45%), medium (45 to <90%), high (90 to <95%), or highest (≥95%). RESULTST1D characteristics increased progressively with higher genetic risk (P < 0.001 for trend). A GRS ≥ 90% was more common with diabetes diagnoses before age 40 years, but 95% of those participants were diagnosed at age ≥40 years, and they resembled T2D in mean age (64.3 years) and BMI (32.3 kg/m2). Compared with the low risk group, the highest-risk group was more likely to have diabetic ketoacidosis (low 0.9% vs. highest GRS 3.7%), hypoglycemia prompting emergency visits (3.7% vs. 5.8%), outpatient plasma glucose <50 mg/dL (7.5% vs. 13.4%), a shorter median time to start insulin (3.5 vs. 1.4 years), use of a T1D diagnostic code (16.3% vs. 28.1%), low C-peptide levels if tested (1.8% vs. 32.4%), and glutamic acid decarboxylase antibodies (6.9% vs. 45.2%), all P < 0.001. CONCLUSIONSCharacteristics associated with T1D were increased with higher genetic risk, and especially with the top 10% of risk. However, the age and BMI of those participants resemble people with T2D, and a substantial proportion did not have diagnostic testing or use of T1D diagnostic codes. T1D genetic screening could be used to aid identification of adult-onset T1D in settings in which T2D predominates. 

   more » « less