1
|
Golestani A, Malekpour MR, Khosravi S, Rashidi MM, Ataei SMN, Nasehi MM, Rezaee M, Akbari Sari A, Rezaei N, Farzadfar F. A decision rule algorithm for the detection of patients with hypertension using claims data. J Diabetes Metab Disord 2025; 24:21. [PMID: 39712338 PMCID: PMC11659550 DOI: 10.1007/s40200-024-01519-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/23/2024] [Accepted: 11/03/2024] [Indexed: 12/24/2024]
Abstract
Objectives Claims data covers a large population and can be utilized for various epidemiological and economic purposes. However, the diagnosis of prescriptions is not determined in the claims data of many countries. This study aimed to develop a decision rule algorithm using prescriptions to detect patients with hypertension in claims data. Methods In this retrospective study, all Iran Health Insurance Organization (IHIO)-insured patients from 24 provinces between 2012 and 2016 were analyzed. A list of available antihypertensive drugs was generated and a literature review and an exploratory analysis were performed for identifying additional usages. An algorithm with 13 decision rules, using variables including prescribed medications, age, sex, and physician specialty, was developed and validated. Results Among all the patients in the IHIO database, a total of 4,590,486 received at least one antihypertensive medication, with a total of 79,975,134 prescriptions issued. The algorithm detected that 76.89% of patients had hypertension. Among 20.43% of all prescriptions the algorithm detected as issued for hypertension, mainly were prescribed by general practitioners (55.78%) and hypertension specialists (30.42%). The validity assessment of the algorithm showed a sensitivity of 100.00%, specificity of 48.91%, positive predictive value of 69.68%, negative predictive value of 100.00%, and accuracy of 76.50%. Conclusion The algorithm demonstrated good performance in detecting patients with hypertension using claims data. Considering the large-scale and passively aggregated nature of claims data compared to other surveillance surveys, applying the developed algorithm could assist policymakers, insurers, and researchers in formulating strategies to enhance the quality of personalized care. Supplementary Information The online version contains supplementary material available at 10.1007/s40200-024-01519-y.
Collapse
Affiliation(s)
- Ali Golestani
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Mohammad-Reza Malekpour
- Endocrinology and Metabolism Research Center, Endocrinology and Metabolism Clinical Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Sepehr Khosravi
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Mohammad-Mahdi Rashidi
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Seyed Mohammad-Navid Ataei
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Mohammad Mahdi Nasehi
- National Center for Health Insurance Research, Tehran, Iran
- Pediatric Neurology Research Center, Research Institute for Children Health, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Mehdi Rezaee
- National Center for Health Insurance Research, Tehran, Iran
- Department of Orthopedics, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - Ali Akbari Sari
- Department of Health Management and Economics, School of Public Health, Tehran University of Medical Sciences, Tehran, Iran
| | - Negar Rezaei
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
- Digestive Disease Research Center (DDRC), Digestive Disease Research Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Farshad Farzadfar
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
- Endocrinology and Metabolism Research Center, Endocrinology and Metabolism Clinical Sciences Institute, Tehran University of Medical Sciences, Tehran, Iran
| |
Collapse
|
2
|
Hu WH, Sun HM, Wei YY, Hao YT. Global infectious disease early warning models: An updated review and lessons from the COVID-19 pandemic. Infect Dis Model 2025; 10:410-422. [PMID: 39816751 PMCID: PMC11731462 DOI: 10.1016/j.idm.2024.12.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2024] [Revised: 08/29/2024] [Accepted: 12/01/2024] [Indexed: 01/18/2025] Open
Abstract
An early warning model for infectious diseases is a crucial tool for timely monitoring, prevention, and control of disease outbreaks. The integration of diverse multi-source data using big data and artificial intelligence techniques has emerged as a key approach in advancing these early warning models. This paper presents a comprehensive review of widely utilized early warning models for infectious diseases around the globe. Unlike previous review studies, this review encompasses newly developed approaches such as the combined model and Hawkes model after the COVID-19 pandemic, providing a thorough evaluation of their current application status and development prospects for the first time. These models not only rely on conventional surveillance data but also incorporate information from various sources. We aim to provide valuable insights for enhancing global infectious disease surveillance and early warning systems, as well as informing future research in this field, by summarizing the underlying modeling concepts, algorithms, and application scenarios of each model.
Collapse
Affiliation(s)
- Wei-Hua Hu
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University, 38 Xueyuan Road, Beijing, 100191, China
| | - Hui-Min Sun
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University, 38 Xueyuan Road, Beijing, 100191, China
| | - Yong-Yue Wei
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University, 38 Xueyuan Road, Beijing, 100191, China
- Peking University Center for Public Health and Epidemic Preparedness & Response, Peking University, 38 Xueyuan Road, Beijing, 100191, China
- Key Laboratory of Epidemiology of Major Diseases (Peking University), Ministry of Education, China
| | - Yuan-Tao Hao
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University, 38 Xueyuan Road, Beijing, 100191, China
- Peking University Center for Public Health and Epidemic Preparedness & Response, Peking University, 38 Xueyuan Road, Beijing, 100191, China
- Key Laboratory of Epidemiology of Major Diseases (Peking University), Ministry of Education, China
| |
Collapse
|
3
|
Barrera Morelli J, McGoverin C, Nieuwoudt M, Holroyd SE, Pilkington LI. Chemometric techniques for the prediction of milk composition from MIR spectral data: A review. Food Chem 2025; 469:142465. [PMID: 39724702 DOI: 10.1016/j.foodchem.2024.142465] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2024] [Revised: 11/14/2024] [Accepted: 12/11/2024] [Indexed: 12/28/2024]
Abstract
Chemometrics; use of statistical models to characterise and understand complex chemical systems/samples, is an advancing field. In the dairy industry, the accurate prediction of milk composition involves combining mid-infrared spectroscopy with chemometric techniques for the evaluation of major constituents of milk. The increased interest in determination of detailed composition of dairy products, alongside emerging and more-widespread use of chemometric methodologies, have generated continuous improvement in predictive models for this application. Herein the main chemometric techniques employed for the study of milk composition are described, compared and discussed. The capability of emerging technologies to improve predictive accuracy of models, over the gold standard technique Partial Least-Squares Regression, to provide recommendation for future directions in this area are particularly emphasised. This review will be of particular interest to researchers involved in milk and dairy product composition, alongside all working in application of statistical methodologies to complex chemical systems.
Collapse
Affiliation(s)
- Josefina Barrera Morelli
- School of Chemical Sciences, The University of Auckland, 23 Symonds St., Auckland 1142, New Zealand; Te Pūnaha Matatini, Auckland, 1142, New Zealand; MacDiarmid Institute for Advanced Materials and Nanotechnology, New Zealand; The Dodd Walls Centre for Photonic and Quantum Technologies, New Zealand.
| | - Cushla McGoverin
- The Dodd Walls Centre for Photonic and Quantum Technologies, New Zealand; Department of Physics, The University of Auckland, 23 Symonds St., Auckland 1142, New Zealand
| | - Michel Nieuwoudt
- School of Chemical Sciences, The University of Auckland, 23 Symonds St., Auckland 1142, New Zealand; MacDiarmid Institute for Advanced Materials and Nanotechnology, New Zealand
| | - Stephen E Holroyd
- Fonterra Research & Development Centre, Private Bag, 11029, Palmerston North, New Zealand
| | - Lisa I Pilkington
- School of Chemical Sciences, The University of Auckland, 23 Symonds St., Auckland 1142, New Zealand; Te Pūnaha Matatini, Auckland, 1142, New Zealand.
| |
Collapse
|
4
|
Hua Y, Beam A, Chibnik LB, Torous J. From statistics to deep learning: Using large language models in psychiatric research. Int J Methods Psychiatr Res 2025; 34:e70007. [PMID: 39777756 PMCID: PMC11707704 DOI: 10.1002/mpr.70007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/12/2024] [Revised: 09/28/2024] [Accepted: 10/13/2024] [Indexed: 01/11/2025] Open
Abstract
BACKGROUND Large Language Models (LLMs) hold promise in enhancing psychiatric research efficiency. However, concerns related to bias, computational demands, data privacy, and the reliability of LLM-generated content pose challenges. GAP: Existing studies primarily focus on the clinical applications of LLMs, with limited exploration of their potentials in broader psychiatric research. OBJECTIVE This study adopts a narrative review format to assess the utility of LLMs in psychiatric research, beyond clinical settings, focusing on their effectiveness in literature review, study design, subject selection, statistical modeling, and academic writing. IMPLICATION This study provides a clearer understanding of how LLMs can be effectively integrated in the psychiatric research process, offering guidance on mitigating the associated risks and maximizing their potential benefits. While LLMs hold promise for advancing psychiatric research, careful oversight, rigorous validation, and adherence to ethical standards are crucial to mitigating risks such as bias, data privacy concerns, and reliability issues, thereby ensuring their effective and responsible use in improving psychiatric research.
Collapse
Affiliation(s)
- Yining Hua
- Department of EpidemiologyHarvard T.H. Chan School of Public HealthBostonMassachusettsUSA
- Department of PsychiatryBeth Israel Deaconess Medical CenterBostonMassachusettsUSA
| | - Andrew Beam
- Department of EpidemiologyHarvard T.H. Chan School of Public HealthBostonMassachusettsUSA
- The CAUSALabHarvard T.H. Chan School of Public HealthBostonMassachusettsUSA
| | - Lori B. Chibnik
- Department of EpidemiologyHarvard T.H. Chan School of Public HealthBostonMassachusettsUSA
- Department of NeurologyMassachusetts General Hospital and Harvard Medical SchoolBostonMassachusettsUSA
| | - John Torous
- Department of PsychiatryBeth Israel Deaconess Medical CenterBostonMassachusettsUSA
- Department of PsychiatryHarvard Medical SchoolBostonMassachusettsUSA
| |
Collapse
|
5
|
Hossain MM, Roy K. The development of classification-based machine-learning models for the toxicity assessment of chemicals associated with plastic packaging. JOURNAL OF HAZARDOUS MATERIALS 2025; 484:136702. [PMID: 39637787 DOI: 10.1016/j.jhazmat.2024.136702] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/05/2024] [Revised: 11/24/2024] [Accepted: 11/26/2024] [Indexed: 12/07/2024]
Abstract
Assessing chemical toxicity in materials like plastic packaging is critical to safeguarding public health. This study presents the development of classification-based machine learning models to predict the toxicity of chemicals associated with plastic packaging. Using an extensive dataset of chemical structures, we trained multiple machine learning models-Random Forest, Support Vector Machine, Linear Discriminant Analysis, and Logistic Regression-targeting endpoints such as Neurotoxicity, Hepatotoxicity, Dermatotoxicity, Carcinogenicity, Reproductive Toxicity, Skin Sensitization, and Toxic Pneumonitis. The dataset was pre-processed by selecting 2D molecular descriptors as feature inputs, with resampling methods (ADASYN, Borderline SMOTE, Random Over-sampler, SVMSMOTE Cluster Centroid, Near Miss, Random Under Sampler) applied to balance classes for accurate classification. A five-fold cross-validation technique was used to optimize model performance, with model parameters fine-tuned using grid search. The model performance was evaluated using accuracy (Acc), sensitivity (Se), specificity (Sp), and area under the receiver operating characteristic curve (AUC-ROC) metrics. In most of the cases, the model accuracy was 0.8 or above for both training and test sets. Additionally, SHAP (SHapley Additive exPlanations) values were utilized for feature importance analysis, highlighting significant descriptors contributing to toxicity predictions. The models were ranked using the Sum of Ranking Differences (SRD) method to systematically select the most effective model. The optimal models demonstrated high predictive accuracy and interpretability, providing a scalable and efficient solution for toxicity assessment compared to traditional methods. This approach offers a valuable tool for rapidly screening potentially hazardous chemicals in plastic packaging.
Collapse
Affiliation(s)
- Md Mobarak Hossain
- Drug Theoretics and Cheminformatics (DTC) Laboratory, Department of Pharmaceutical Technology, Jadavpur University, Kolkata 700032, India
| | - Kunal Roy
- Drug Theoretics and Cheminformatics (DTC) Laboratory, Department of Pharmaceutical Technology, Jadavpur University, Kolkata 700032, India.
| |
Collapse
|
6
|
Kelkay JM, Anteneh DS, Wubneh HD, Gessesse AD, Gebeyehu GF, Aweke KK, Ejigu MB, Sendeku MA, Barkneh KA, Demissie HG, Negash WD, Mihret BG. Ensemble learning to predict short birth interval among reproductive-age women in Ethiopia: evidence from EDHS 2016-2019. BMC Pregnancy Childbirth 2025; 25:121. [PMID: 39910491 DOI: 10.1186/s12884-025-07248-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2024] [Accepted: 01/28/2025] [Indexed: 02/07/2025] Open
Abstract
BACKGROUND A birth interval of less than 33 months was considered short, and in low- income countries like Ethiopia, a short birth interval is the primary cause of approximately 822 maternal deaths every day. Due to that this study aimed to predict short birth interval and associated factors among women (15-49) in Ethiopia using ensemble learning algorithms. METHODS A secondary data analysis of Ethiopian demographic health servey from 2016 to 2019 was performed. a total of weighted sample of 12,573 women in the reproductive age group was included in this study. Data have been extracted and processed with Stata version 17. The dataset was then imported into a Jupyter notebook for further detailed analysis and visualization. An ensemble Machin learning algorithm using different classification models were implemented. All analysis and calculation were performed using Python 3 programming language in Jupyter Notebook using imblearn, sklearn, and xgboost pakages. RESULTS Random forest demonstrated the best performance with an accuracy 97.84%, recall of 99.70%, F1-score of 97.81%, 98.95% precision on test data and AUC (98%). Region, residency, age of women, sex of child, respondent education, distance health facility, husband education and religion were top predicting factors of short birth interval among women in Ethiopia. CONCLUSION Random forest was best predictive models with improved performance. "The most significant features that contribute to the accuracy of the top-performing models, notably the Random Forest should be highlighted because they outperformed the other model in the analysis.In general, ensemble learning algorithms can accurately predict short birth interval status, making them potentially useful as decision-support tools for the pertinent stakeholders.
Collapse
Affiliation(s)
| | - Deje Sendek Anteneh
- Department of Health Informatics, Institute of Public Health, College of Medicine and Health Science, University of Gondar, Gondar, Ethiopia
| | - Henok Dessie Wubneh
- Department of Health Informatics, Institute of Public Health, College of Medicine and Health Science, University of Gondar, Gondar, Ethiopia
| | - Abraham Dessie Gessesse
- Department of Pediatric and Child Health Nursing, College of Health Sciences, Woldia University, Woldia, Ethiopia
| | - Gebeyehu Fassil Gebeyehu
- School of Medicine, College of Medicine and Health Sciences, Bahir Dar University, Bahir Dar, Ethiopia
| | - Kalkidan Kassahun Aweke
- School of Medicine, College of Medicine and Health Sciences, Bahir Dar University, Bahir Dar, Ethiopia
| | - Mikiyas Birhanu Ejigu
- School of Medicine, College of Medicine and Health Sciences, Bahir Dar University, Bahir Dar, Ethiopia
| | - Mathias Amare Sendeku
- School of Medicine, College of Medicine and Health Sciences, Bahir Dar University, Bahir Dar, Ethiopia
| | - Kirubel Adrissie Barkneh
- School of Medicine, College of Medicine and Health Sciences, Bahir Dar University, Bahir Dar, Ethiopia
| | - Hasset Girma Demissie
- School of Medicine, College of Medicine and Health Sciences, Bahir Dar University, Bahir Dar, Ethiopia
| | - Wubshet D Negash
- Department of Health Systems and Policy, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia
- National Centre for Epidemiology and Population Health, The Australian National University, Canberra, Australia
| | - Birku Getie Mihret
- Department of Computer Sciences, College of Natural and Computational Sciences, Debark University, Debark, Ethiopia
| |
Collapse
|
7
|
Boyd SS, Slawson C, Thompson JA. AMEND 2.0: module identification and multi-omic data integration with multiplex-heterogeneous graphs. BMC Bioinformatics 2025; 26:39. [PMID: 39910456 DOI: 10.1186/s12859-025-06063-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2024] [Accepted: 01/22/2025] [Indexed: 02/07/2025] Open
Abstract
BACKGROUND Multi-omic studies provide comprehensive insight into biological systems by evaluating cellular changes between normal and pathological conditions at multiple levels of measurement. Biological networks, which represent interactions or associations between biomolecules, have been highly effective in facilitating omic analysis. However, current network-based methods lack generalizability to accommodate multiple data types across a range of diverse experiments. RESULTS We present AMEND 2.0, an updated active module identification method which can analyze multiplex and/or heterogeneous networks integrated with multi-omic data in a highly generalizable framework, in contrast to existing methods, which are mostly appropriate for at most two specific omic types. It is powered by Random Walk with Restart for multiplex-heterogeneous networks, with additional capabilities including degree bias adjustment and biased random walk for multi-objective module identification. AMEND was applied to two real-world multi-omic datasets: renal cell carcinoma data from The cancer genome atlas and an O-GlcNAc Transferase knockout study. Additional analyses investigate the performance of various subroutines of AMEND on tasks of node ranking and degree bias adjustment. CONCLUSIONS While the analysis of multi-omic datasets in a network context is poised to provide deeper understanding of health and disease, new methods are required to fully take advantage of this increasingly complex data. The current study combines several network analysis techniques into a single versatile method for analyzing biological networks with multi-omic data that can be applied in many diverse scenarios. Software is freely available in the R programming language at https://github.com/samboyd0/AMEND .
Collapse
Affiliation(s)
- Samuel S Boyd
- Department of Biostatistics and Data Science, University of Kansas Medical Center, Kansas City, KS, 66160, USA.
| | - Chad Slawson
- Department of Biochemistry, University of Kansas Medical Center, Kansas City, KS, 66160, USA
- University of Kansas Cancer Center, Kansas City, KS, 66160, USA
- University of Kansas Alzheimer's Disease Research Center, Fairway, KS, 66205, USA
| | - Jeffrey A Thompson
- Department of Biostatistics and Data Science, University of Kansas Medical Center, Kansas City, KS, 66160, USA
- University of Kansas Cancer Center, Kansas City, KS, 66160, USA
| |
Collapse
|
8
|
Allerdice MEJ, Shooter SL, Galletti MFBM, Hecht JA, Karpathy SE, Paddock CD. Molecular identification and antibiotic clearance of Mycoplasma arginini and Mycoplasma orale from cell cultures infected with Rickettsia or Ehrlichia species. Microbiol Spectr 2025; 13:e0174324. [PMID: 39817787 PMCID: PMC11792515 DOI: 10.1128/spectrum.01743-24] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2024] [Accepted: 12/02/2024] [Indexed: 01/18/2025] Open
Abstract
Mycoplasma (Class: Mollicutes) contamination in cell cultures is a universal concern for research laboratories. Some estimates report contamination in up to 35% of continuous cell lines. Various commercial antibiotic treatments can successfully decontaminate clean cell lines in vitro; however, in vitro decontamination of bacterial cultures remains challenging. Intracellular bacteria like those in the genera Rickettsia and Ehrlichia require cell culture for primary isolation and propagation and are thus vulnerable to contamination with mycoplasmas. Some analyses have reported successful antibiotic clearance of contaminating mycoplasmas in Rickettsia cultures; however, many of these studies do not identify the contaminating mycoplasma species and often include only a few isolates. To our knowledge, there are no published studies reporting decontamination of mycoplasmas from Ehrlichia cultures. In this study, we developed a specific multiplex assay to identify two of the most common mycoplasma culture contaminants, Mycoplasma arginini and Mycoplasma orale, in cell cultures infected with Rickettsia or Ehrlichia species. We further describe the successful in vitro decontamination of M. arginini, M. orale, and co-contaminations with both mycoplasmas from multiple Rickettsia and Ehrlichia cultures using daptomycin and clindamycin.IMPORTANCEMycoplasma contamination is a frequent problem in bacterial cell culture. These prolific organisms thrive in the extracellular environment in vitro and can persist in cell lines indefinitely without treatment. Historically, mycoplasma-contaminated Rickettsia cultures were cleared of contaminants by inoculating laboratory mice and re-isolating mycoplasma-free Rickettsia from brain endothelial cells. However, this method requires the sacrifice of live animals and is not always effective. Mycoplasma clearance via mouse inoculation requires a patent infection of murine central nervous system endothelial cells, which may not occur with some mildly pathogenic or nonpathogenic rickettsial species. In vitro antibiotic treatment represents an alternate method to eliminate contaminating mycoplasmas from rickettsial cultures. This method requires minimal adjustment of laboratories that already maintain rickettsial cultures and is not dependent on the use of laboratory animals. As such, the comprehensive strategy for Mycoplasma arginini and Mycoplasma orale elimination presented here can improve laboratory efficiency for in vitro research with intracellular bacteria.
Collapse
Affiliation(s)
- Michelle E. J. Allerdice
- Division of Vector-borne Diseases, Centers for Disease Control and Prevention, U.S. Department of Health and Human Services, Atlanta, Georgia, USA
| | - Savannah L. Shooter
- Rickettsial Zoonoses Branch, Centers for Disease Control and Prevention, U.S. Department of Health and Human Services, Atlanta, Georgia, USA
| | - Maria F. B. M. Galletti
- Rickettsial Zoonoses Branch, Centers for Disease Control and Prevention, U.S. Department of Health and Human Services, Atlanta, Georgia, USA
| | - Joy A. Hecht
- Rickettsial Zoonoses Branch, Centers for Disease Control and Prevention, U.S. Department of Health and Human Services, Atlanta, Georgia, USA
| | - Sandor E. Karpathy
- Rickettsial Zoonoses Branch, Centers for Disease Control and Prevention, U.S. Department of Health and Human Services, Atlanta, Georgia, USA
| | - Christopher D. Paddock
- Rickettsial Zoonoses Branch, Centers for Disease Control and Prevention, U.S. Department of Health and Human Services, Atlanta, Georgia, USA
| |
Collapse
|
9
|
Gregory LE, Driscoll RMH, Parker BJ, Brisson JA. Impacts of Body Colour, Symbionts and Genomic Regions on the Pea Aphid Wing Plasticity Variation. Mol Ecol 2025:e17660. [PMID: 39903065 DOI: 10.1111/mec.17660] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2024] [Revised: 01/08/2025] [Accepted: 01/10/2025] [Indexed: 02/06/2025]
Abstract
Adaptive phenotypic plasticity describes the phenomenon in which a single genotype can produce a variety of phenotypes that match their environments. Like any trait, plasticity is a phenotype that can exhibit variation, but despite the ecological importance of plasticity variation, little is known about its genetic basis. Here we use the pea aphid to investigate the genetic basis of wing plasticity variation. Previous reports have suggested an ecological association between body coloration and wing plasticity strength in the pea aphid, so we tested the hypothesis that the body colour determination locus (tor) associated with wing plasticity variation. We discover that there is no relationship between body colour and wing plasticity in natural populations or in a genetic mapping population. We also localise the tor locus to the third autosome, whereas it was previously thought to be on the first autosome, a finding that will be important for future studies of the locus. We find that the presence of the bacterial symbiont Regiella is associated with higher levels of wing plasticity. Genome-wide association analysis of wing plasticity variation did not reveal an impact of the tor locus, consistent with independence of body colour and wing plasticity. This analysis implicated one possible candidate gene-a Hox gene, abdominal-A-underlying wing plasticity variation, although SNPs do not reach the level of genome-wide significance and therefore will require further study. Our study highlights that plasticity variation is complex, impacted by a bacterial symbiont and genetic variation, but not influenced by body colour.
Collapse
Affiliation(s)
- Lauren E Gregory
- Department of Biology, University of Rochester, Rochester, New York, USA
| | - Rose M H Driscoll
- Department of Biology, University of Rochester, Rochester, New York, USA
| | - Benjamin J Parker
- Department of Biology, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA
| | - Jennifer A Brisson
- Department of Biology, University of Rochester, Rochester, New York, USA
| |
Collapse
|
10
|
Zhang Y, Li S, Mai P, Yang Y, Luo N, Tong C, Zeng K, Zhang K. A machine learning-based model for predicting paroxysmal and persistent atrial fibrillation based on EHR. BMC Med Inform Decis Mak 2025; 25:51. [PMID: 39901121 PMCID: PMC11792530 DOI: 10.1186/s12911-025-02880-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2024] [Accepted: 01/20/2025] [Indexed: 02/05/2025] Open
Abstract
BACKGROUND There is no effective way to accurately predict paroxysmal and persistent atrial fibrillation (AF) subtypes unless electrocardiogram (ECG) observation is obtained. We aim to develop a predictive model using a machine learning algorithm for identification of paroxysmal and persistent AF, and investigate the influencing factors. METHODS We collected demographic data, medication use, serological indicators, and baseline cardiac ultrasound data of all included subjects, totaling 50 variables. The diagnosis of AF subtypes is confirmed by ECG observation for at least more than 7 days. Variable selection was performed by spearman correlation analysis, recursive feature elimination, and least absolute shrinkage and selection operator regression. We built a prediction model for AF using three machine learning methods. Finally, the significance of each variable was analyzed by Shapley additive explanations method. RESULTS After screening, we found the optimal variable set consisting of 10 variables. The model we built achieved good predictive performance (AUC = 0.870, 95%CI 0.858 to 0.882), and had specificity of 0.851 (95%CI 0.844 to 0.858) and sensitivity of 0.716 (95%CI 0.676 to 0.755). Good predictive performance was stably achieved in different age subgroups and different gender subgroups. LA and NT-proBNP were the two most important variables for predicting paroxysmal and persistent AF in all models, except for the female subgroup aged less than 60 years. CONCLUSIONS Our model makes it possible to predict paroxysmal and persistent AF based on baseline data at admission. Early and individualized intervention strategies based on our model may help to improve clinical outcomes in AF patients.
Collapse
Affiliation(s)
- Yuqi Zhang
- School of Computer Science & Engineering, Beihang University, Beijing, China
- State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China
| | - Sijin Li
- Department of Cardiology, Joint Laboratory of Guangdong-Hong Kong-Macao Universities for Nutritional Metabolism and Precise Prevention and Control of Major Chronic Diseases, The Eighth Affiliated Hospital, Sun Yat-Sen University, Shenzhen, China
- Department of Cardiovascular Surgery, The Eighth Affiliated Hospital, Sun Yat-Sen University, Shenzhen, China
| | - Peibiao Mai
- Department of Cardiology, Fuwai Hospital, Chinese Academy of Medical Sciences (Shenzhen Sun Yat-Sen Cardiovascular Hospital), Shenzhen, China
- Department of Cardiology, Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University, Guangzhou, China
| | - Yanqi Yang
- Department of Cardiovascular Surgery, The Eighth Affiliated Hospital, Sun Yat-Sen University, Shenzhen, China
- Department of Cardiothoracic Surgery, University Hospital, University Linköping, Linköping, Sweden
| | - Niansang Luo
- Department of Cardiology, Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University, Guangzhou, China
| | - Chao Tong
- School of Computer Science & Engineering, Beihang University, Beijing, China.
- State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China.
| | - Kuan Zeng
- Department of Cardiovascular Surgery, The Eighth Affiliated Hospital, Sun Yat-Sen University, Shenzhen, China.
| | - Kun Zhang
- Department of Cardiology, Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University, Guangzhou, China.
- Department of Cardiology, The Seventh Affiliated Hospital, Sun Yat-Sen University, Shenzhen, China.
| |
Collapse
|
11
|
Phogat A, Krishnan SR, Pandey M, Gromiha MM. ZFP-CanPred: Predicting the effect of mutations in zinc-finger proteins in cancers using protein language models. Methods 2025:S1046-2023(25)00029-5. [PMID: 39909391 DOI: 10.1016/j.ymeth.2025.01.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2024] [Revised: 01/21/2025] [Accepted: 01/27/2025] [Indexed: 02/07/2025] Open
Abstract
Zinc-finger proteins (ZNFs) constitute the largest family of transcription factors and play crucial roles in various cellular processes. Missense mutations in ZNFs significantly alter protein-DNA interactions, potentially leading to the development of various types of cancers. This study presents ZFP-CanPred, a novel deep learning-based model for predicting cancer-associated driver mutations in ZNFs. The representations derived from protein language models (PLMs) from the structural neighbourhood of mutated sites were utilized to train ZFP-CanPred for differentiating between cancer-causing and neutral mutations. ZFP-CanPred, achieved a superior performance with an accuracy of 0.72, F1-score of 0.79, and area under the Receiver Operating Characteristics (ROC) Curve (AUC) of 0.74, on an independent test set. In a comparative analysis against 11 existing prediction tools using a curated dataset of 331 mutations, ZFP-CanPred demonstrated the highest AU-ROC of 0.74, outperforming both generic and cancer-specific methods. The model's balanced performance across specificity and sensitivity addresses a significant limitation of current methodologies. The source code and other related files are available on GitHub at https://github.com/amitphogat/ZFP-CanPred.git. We envisage that the present study contributes to understand the oncogenic processes and developing targeted therapeutic strategies.
Collapse
Affiliation(s)
- Amit Phogat
- Department of Biotechnology, Bhupat and Jyoti Mehta School of Biosciences, Indian Institute of Technology Madras, Chennai 600036 India
| | - Sowmya Ramaswamy Krishnan
- Department of Biotechnology, Bhupat and Jyoti Mehta School of Biosciences, Indian Institute of Technology Madras, Chennai 600036 India
| | - Medha Pandey
- Department of Biotechnology, Bhupat and Jyoti Mehta School of Biosciences, Indian Institute of Technology Madras, Chennai 600036 India
| | - M Michael Gromiha
- Department of Biotechnology, Bhupat and Jyoti Mehta School of Biosciences, Indian Institute of Technology Madras, Chennai 600036 India; International Research Frontiers Initiative, School of Computing, Tokyo Institute of Technology, Yokohama 226-8501 Japan.
| |
Collapse
|
12
|
Yu N, Qin Y, Kang W, Zhang J, Wang H, Wang X, Chen Y. Molecular characterization, B-cell linear epitopes identification and key amino acids selection of the sesame allergen Ses i 5. Int J Biol Macromol 2025:140635. [PMID: 39904425 DOI: 10.1016/j.ijbiomac.2025.140635] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2024] [Revised: 01/04/2025] [Accepted: 02/01/2025] [Indexed: 02/06/2025]
Abstract
Ses i 5 is an important sesame allergen and no studies have been reported on the epitope identification of this allergen. Epitopes are the antigenic determinants on the surface of allergens, which are the basis of intensive study on protein antigenicity. In this paper, we analyzed the secondary structure, tertiary structure, hydrophilicity, antigenic index, flexibility, surface accessibility, and homology of the Ses i 5. In addition, we designed and synthesized overlapping peptides covering the entire amino acid sequence of Ses i 5, each overlapping peptide contains 15 amino acids with 5 amino acid repeats. The IgE binding capacity of each peptide was assessed by immune slot blot microarray. Ultimately, we identified seven B-cell linear epitopes of Ses i 5. Furthermore, the key amino acids of Ses i 5 were predicted and mutated to alanine, the changes in the IgE-binding capacity of the mutated peptides were assessed by indirect competition-ELISA (ic-ELISA). At last glycine 104 was identified as the key amino acid for IgE binding in Ses i 5. These studies will contribute to the deep study of molecular characterization and more information on epitopes of Ses i 5, which will benefit for the further understanding of the sesame allergen.
Collapse
Affiliation(s)
- Ning Yu
- Chinese Academy of Inspection and Quarantine, Beijing 100176, China
| | - Yufei Qin
- Chinese Academy of Inspection and Quarantine, Beijing 100176, China; College of Food Science and Engineering, Nanjing University of Finance and Economics, Nanjing 210023, China
| | - Wenhan Kang
- Chinese Academy of Inspection and Quarantine, Beijing 100176, China
| | - Jiukai Zhang
- Chinese Academy of Inspection and Quarantine, Beijing 100176, China
| | - Hongtian Wang
- Food Allergy Department, Beijing Shijitan Hospital, Capital Medical University, Beijing 100038, China
| | - Xiaoyan Wang
- Food Allergy Department, Beijing Shijitan Hospital, Capital Medical University, Beijing 100038, China
| | - Ying Chen
- Chinese Academy of Inspection and Quarantine, Beijing 100176, China.
| |
Collapse
|
13
|
Mao J, Tan L, Tian C, Wang W, Zou Y, Zhu Z, Li Y. Systemic investigation of the mechanism underlying the therapeutic effect of Astragalus membranaceus in ulcerative colitis. Am J Med Sci 2025; 369:238-251. [PMID: 39009282 DOI: 10.1016/j.amjms.2024.07.019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2023] [Revised: 07/09/2024] [Accepted: 07/09/2024] [Indexed: 07/17/2024]
Abstract
BACKGROUND Whether Astragalus membranaceus is an effective drug in the treatment of ulcerative colitis (UC) is unknown and how it exhibits activity in UC is unclear. METHODS TCMSP, GeneCards, String, and DAVID databases were used to screen target genes in PPI network and we performed GO and KEGG pathway enrichment analysis. Molecular docking and animal experiments were performed. The body weight and disease activity index (DAI) of mice were recorded. ELISA kits were used to detect the levels of CAT, SOD, MDA and IL-6, IL-10, TNF-α in the blood of mice. Western blot kits were utilized to measure the expression of MAPK14, RB1, MAPK1, JUN, ATK1, and IL2 proteins. RESULTS The active components of Astragalus membranaceus mainly include 7-O-methylisomucronulatol, quercetin, kaempferol, formononetin and isrhamnetin. Astragalus membranaceus may inhibit the expression of TNF-α, IL-6, MDA, while promoting the expression of CAT, SOD, and IL-10. The expression levels of MAPK14, RB1, MAPK1, JUN and ATK1 proteins were significantly decreased while IL2 protein increased after administration of Astragalus membranaceus. CONCLUSIONS Astragalus membranaceus may be an effective drug in the treatment of UC by acting on targets with anti-UC effect via its antioxidant action and by regulating the balance of pro-inflammatory and anti-inflammatory factors.
Collapse
Affiliation(s)
- Jingxin Mao
- Department of Science and Technology Industry, Chongqing Medical and Pharmaceutical College, Chongqing 400030, China; College of Pharmaceutical Sciences, Southwest University, Chongqing 400715, China
| | - Lihong Tan
- Department of Science and Technology Industry, Chongqing Medical and Pharmaceutical College, Chongqing 400030, China; Chongqing Key Laboratory of High Active Traditional Chinese Drug Delivery System, Chongqing Medical and Pharmaceutical College, Chongqing 400030, China
| | - Cheng Tian
- Department of Science and Technology Industry, Chongqing Medical and Pharmaceutical College, Chongqing 400030, China; Chongqing Key Laboratory of High Active Traditional Chinese Drug Delivery System, Chongqing Medical and Pharmaceutical College, Chongqing 400030, China
| | - Wenxiang Wang
- College of pharmacy, Chongqing Three Gorges Medical College, Chongqing 404120, China
| | - YanLin Zou
- College of pharmacy, Chongqing Three Gorges Medical College, Chongqing 404120, China
| | - Zhaojing Zhu
- Department of Science and Technology Industry, Chongqing Medical and Pharmaceutical College, Chongqing 400030, China; Chongqing Key Laboratory of High Active Traditional Chinese Drug Delivery System, Chongqing Medical and Pharmaceutical College, Chongqing 400030, China
| | - Yan Li
- Department of Science and Technology Industry, Chongqing Medical and Pharmaceutical College, Chongqing 400030, China; Chongqing Key Laboratory of High Active Traditional Chinese Drug Delivery System, Chongqing Medical and Pharmaceutical College, Chongqing 400030, China.
| |
Collapse
|
14
|
Boyapati M, Aygun R. BalancerGNN: Balancer Graph Neural Networks for imbalanced datasets: A case study on fraud detection. Neural Netw 2025; 182:106926. [PMID: 39612688 DOI: 10.1016/j.neunet.2024.106926] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2023] [Accepted: 11/13/2024] [Indexed: 12/01/2024]
Abstract
Fraud detection for imbalanced datasets is challenging due to machine learning models inclination to learn the majority class. Imbalance in fraud detection datasets affects how graphs are built, an important step in many Graph Neural Networks (GNNs). In this paper, we introduce our BalancerGNN framework to tackle with imbalanced datasets and show its effectiveness on fraud detection. Our framework has three major components: (i) node construction with feature representations, (ii) graph construction using balanced neighbor sampling, and (iii) GNN training using balanced training batches leveraging a custom loss function with multiple components. For node construction, we have introduced (i) Graph-based Variable Clustering (GVC) to optimize feature selection and remove redundancies by analyzing multi-collinearity and (ii) Encoder-Decoder based Dimensionality Reduction (EDDR) using transformer-based techniques to reduce feature dimensions while keeping important information intact about textual embeddings. Our experiments on Medicare, Equifax, IEEE, and auto insurance fraud datasets highlight the importance of node construction with features representations. BalancerGNN trained with balanced batches consistently outperforms other methods, showing strong abilities in identifying fraud cases, with sensitivity rates ranging from 72.87% to 81.23% across datasets while balancing specificity. Additionally, BalancerGNN achieves impressive accuracy rates, ranging from 73.99% to 94.28%. These outcomes underscore the crucial role of graph representation and neighbor sampling techniques in optimizing BalancerGNN for fraud detection models in real-world applications.
Collapse
Affiliation(s)
- Mallika Boyapati
- School of Data Science and Analytics, Kennesaw State University, Kennesaw, 30144, GA, USA.
| | - Ramazan Aygun
- Department of Computer Science, Kennesaw State University, Kennesaw, 30144, GA, USA
| |
Collapse
|
15
|
Ding Z, Zhou Y, Dai AJ, Qian C, Zhong BL, Liu CL, Liu ZT. Speech based suicide risk recognition for crisis intervention hotlines using explainable multi-task learning. J Affect Disord 2025; 370:392-400. [PMID: 39528146 DOI: 10.1016/j.jad.2024.11.022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/12/2024] [Revised: 10/28/2024] [Accepted: 11/05/2024] [Indexed: 11/16/2024]
Abstract
BACKGROUND Crisis Intervention Hotline can effectively reduce suicide risk, but suffer from low connectivity rates and untimely crisis response. By integrating speech signals and deep learning to assist in crisis assessment, it is expected to enhanced the effectiveness of crisis intervention hotlines. METHODS In this study, a crisis intervention hotline suicide risk speech dataset was constructed, and the speech was labeled based on the Modified Suicide Risk Scale. On the dataset, the variability of speech duration between different callers and different speech high-level features were explored across callers. Finally, this study proposed a data-theoretically dual-driven, gender-assisted speech crisis recognition method based on multi-tasking and deep learning, and the results of the model were obtained through five-fold cross-validation. RESULTS Analysis of the dataset demonstrated gender differences in callers, with male callers speaking more in crisis calls compared to females. Feature analysis revealed significant differences between crisis callers in terms of emotional intensity of speech, speech rate and texture. The proposed method outperformed other methods with an F1 score of 96 % on the validation data, and feature visualization of the model also demonstrated the validity of the method. LIMITATIONS The sample size of this study was limited and ignored information from other modalities. CONCLUSION These findings demonstrated the effectiveness of the proposed model in speech crisis recognition, and the statistical data analysis enhanced the Interpretability of the model, while showing that the integration of data and theoretical knowledge facilitates the effectiveness of the method.
Collapse
Affiliation(s)
- Zhong Ding
- Psychological Science and Health Research Center, China University of Geosciences, Lumo Road, Wuhan 430074, Hubei, China; Institute of Education, China University of Geosciences, Lumo Road, Wuhan 430074, Hubei, China; School of Automation, China University of Geosciences, Lumo Road, Wuhan 430074, Hubei, China
| | - Yang Zhou
- Psychological Science and Health Research Center, China University of Geosciences, Lumo Road, Wuhan 430074, Hubei, China; Wuhan Mental Health Center, Jianshe Avenue, Wuhan 430032, Hubei, China; Wuhan Hospital for Psychotherapy, Jianshe Avenue, Wuhan 430032, Hubei, China
| | - An-Jie Dai
- School of Automation, China University of Geosciences, Lumo Road, Wuhan 430074, Hubei, China
| | - Chen Qian
- Wuhan Mental Health Center, Jianshe Avenue, Wuhan 430032, Hubei, China; Wuhan Hospital for Psychotherapy, Jianshe Avenue, Wuhan 430032, Hubei, China
| | - Bao-Liang Zhong
- Psychological Science and Health Research Center, China University of Geosciences, Lumo Road, Wuhan 430074, Hubei, China; Wuhan Mental Health Center, Jianshe Avenue, Wuhan 430032, Hubei, China; Wuhan Hospital for Psychotherapy, Jianshe Avenue, Wuhan 430032, Hubei, China.
| | - Chen-Ling Liu
- Psychological Science and Health Research Center, China University of Geosciences, Lumo Road, Wuhan 430074, Hubei, China; Institute of Education, China University of Geosciences, Lumo Road, Wuhan 430074, Hubei, China.
| | - Zhen-Tao Liu
- Psychological Science and Health Research Center, China University of Geosciences, Lumo Road, Wuhan 430074, Hubei, China; School of Automation, China University of Geosciences, Lumo Road, Wuhan 430074, Hubei, China.
| |
Collapse
|
16
|
Banc A, Muntean G, Biousse V, Kupersmith MJ, Newman NJ, Bruce BB. Nonarteritic Anterior Ischemic Optic Neuropathy in Black Patients. Am J Ophthalmol 2025; 270:192-202. [PMID: 39419251 PMCID: PMC11747939 DOI: 10.1016/j.ajo.2024.09.036] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2024] [Revised: 09/28/2024] [Accepted: 09/30/2024] [Indexed: 10/19/2024]
Abstract
PURPOSE Prior studies have shown that nonarteritic anterior ischemic optic neuropathy (NAION) is uncommon in persons of Black race compared with those of White race, but the reasons behind this discrepancy remain unknown. Our goal was to analyze the systemic and ocular features of Black patients with NAION compared with White patients. DESIGN Retrospective, cross-sectional study. METHODS Self-reported race was collected from all patients with NAION seen between 2014 and 2022 from a single US neuro-ophthalmology service. All Black patients with NAION and a randomly selected sample of White patients with NAION were included. We collected information on hypertension, hyperlipidemia, diabetes mellitus, hypothyroidism, obesity, ischemic heart disease, atrial fibrillation, pacemaker insertion, chronic kidney disease, dialysis, anemia, obstructive sleep apnea, deep vein thrombosis, stroke, use of phosphodiesterase inhibitors, and smoking status. We reviewed color fundus photographs and optic nerve OCT images to assess cup-to-disc ratio and document the presence of optic disc drusen. Counterfactual random forest was used to estimate associations for each characteristic of interest by race controlling for the other exposures. RESULTS We included 32 Black patients with NAION (mean age 57 ± 11 years, 38% men) and 69 of 432 White patients (mean age 57 ± 15 years, 59% men). Time between NAION onset and neuro-ophthalmic examination was significantly longer in Black patients (1.5 to <3 months: odds ratio [OR], 4.07, P = .03; 6 to <12 months: OR, 6.05, P = .007). Chronic kidney disease (OR, 7.53, P = .003) and hemodialysis (OR, 13.69, P = .02) were significantly more frequent in Black patients. No significant differences in cup-to-disc ratio were present (0.15 to <0.25: OR, 2.83, P = .09; 0.25 to <0.35: OR, 0.56, P = .46; ≥0.35: OR, 0.66, P = .44). CONCLUSIONS Referral delay occurs in Black patients with NAION, likely due to its relative rarity and concern for alternate diagnoses. Black patients with NAION were substantially more likely to have chronic kidney disease and be on dialysis than White patients. Despite known racial differences in cup-to-disc ratio, we found no difference between Black and White patients with NAION, suggesting that the underlying proposed compartment mechanism is the same between races.
Collapse
Affiliation(s)
- Ana Banc
- From the Department of Ophthalmology, Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca, Romania (A.B.)
| | - George Muntean
- Department of Ophthalmology, Emory University School of Medicine, Atlanta, Georgia, USA (G.M., V.B., N.J.N., B.B.B.)
| | - Valérie Biousse
- Department of Ophthalmology, Emory University School of Medicine, Atlanta, Georgia, USA (G.M., V.B., N.J.N., B.B.B.); Department of Neurology, Emory University School of Medicine, Atlanta, Georgia, USA (V.B., N.J.N., B.B.B.)
| | - Mark J Kupersmith
- Departments of Neurology and Ophthalmology, Icahn School of Medicine at Mount Sinai, New York, New York, USA (M.J.K.)
| | - Nancy J Newman
- Department of Ophthalmology, Emory University School of Medicine, Atlanta, Georgia, USA (G.M., V.B., N.J.N., B.B.B.); Department of Neurology, Emory University School of Medicine, Atlanta, Georgia, USA (V.B., N.J.N., B.B.B.); Department of Neurological Surgery, Emory University School of Medicine, Atlanta, Georgia, USA (N.J.N.)
| | - Beau B Bruce
- Department of Ophthalmology, Emory University School of Medicine, Atlanta, Georgia, USA (G.M., V.B., N.J.N., B.B.B.); Department of Neurology, Emory University School of Medicine, Atlanta, Georgia, USA (V.B., N.J.N., B.B.B.); Department of Epidemiology, Rollins School of Public Health, Emory, Atlanta, Georgia, USA (B.B.B.).
| |
Collapse
|
17
|
Molnar D, Björnson E, Hjelmgren O, Adiels M, Bäckhed F, Bergström G. Coronary artery calcifications are not associated with epicardial adipose tissue volume and attenuation on computed tomography in 1,945 individuals with various degrees of glucose disorders. IJC HEART & VASCULATURE 2025; 56:101613. [PMID: 39906627 PMCID: PMC11791301 DOI: 10.1016/j.ijcha.2025.101613] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2024] [Revised: 01/10/2025] [Accepted: 01/12/2025] [Indexed: 02/06/2025]
Abstract
Background The quantification of coronary artery calcifications (CAC) is a mainstay in radiological assessment of coronary atherosclerosis and cardiovascular risk, but reflect advanced, possibly late-stage changes in the arteries. Increased volume and changes in attenuation of the epicardial adipose tissue (EAT) on computed tomography (CT) have been linked to adverse cardiovascular events, and these changes in the EAT might reflect earlier stages of the processes leading to clinically manifest atherosclerosis. The relationship between EAT and CAC is subject to a knowledge gap, especially in individuals with no previously known coronary artery disease. Methods Fully automated EAT analysis with an artificial intelligence-based model was performed in a population sample enriched for pre-diabetics, comprising a total of 1,945 individuals aged 50-64 years, where non-contrast CT images, anthropometric and laboratory data was available on established cardiovascular risk factors. Uni- and multivariable linear regression, gradient-boosting and correlation analyses were performed to determine the explanatory value of EAT volume and attenuation data with regards to CAC data. Results Neither EAT volume nor EAT attenuation was associated with the presence or severity of CAC, when adjusting for established cardiovascular risk factors, and had only weak explanatory value in gradient-boosting and correlation analyses. Age was the strongest predictor of CAC in both sexes. Conclusion No independent association was found between CAC and total EAT volume or attenuation. Importantly, these findings do not rule out early stage or local effects on coronary atherosclerosis from the EAT immediately surrounding the coronary arteries.
Collapse
Affiliation(s)
- David Molnar
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Radiology, Sahlgrenska University Hospital, Region Västra Götaland, Gothenburg, Sweden
| | - Elias Björnson
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Ola Hjelmgren
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Pediatric Heart Centre, Queen Silvia Childreńs Hospital, Sahlgrenska University Hospital, Region Västra Götaland, Gothenburg, Sweden
| | - Martin Adiels
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Fredrik Bäckhed
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Clinical Physiology, Sahlgrenska University Hospital, Region Västra Götaland, Gothenburg, Sweden
| | - Göran Bergström
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Clinical Physiology, Sahlgrenska University Hospital, Region Västra Götaland, Gothenburg, Sweden
| |
Collapse
|
18
|
Sullivan TM, Kim MS, Sippel GJ, Gestrich-Thompson WV, Melhado CG, Griffin KL, Moody SM, Thakkar RK, Kotagal M, Jensen AR, Burd RS. Development and Validation of a Bayesian Network Predicting Intubation Following Hospital Arrival Among Injured Children. J Pediatr Surg 2025; 60:161888. [PMID: 39304486 PMCID: PMC11745935 DOI: 10.1016/j.jpedsurg.2024.161888] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/06/2024] [Revised: 07/30/2024] [Accepted: 08/27/2024] [Indexed: 09/22/2024]
Abstract
BACKGROUND Inadequate airway management can contribute to preventable trauma deaths. Current machine learning tools for predicting intubation in trauma are limited to adult populations and include predictors not readily available at the time of patient arrival. We developed a Bayesian network to predict intubation in injured children and adolescents using observable data available upon or immediately after patient arrival. METHODS We obtained patient demographic, injury, resuscitation, and transportation characteristics from trauma registries from four American College of Surgeons-verified level 1 pediatric trauma centers from January 2010 through December 2021. We trained and validated a Bayesian network to predict emergent intubation after pediatric injury. We evaluated model performance using the area under the receiver operating and calibration curves. RESULTS The final model, TITAN (Timing of Intubation in Trauma Analysis Network), incorporated five factors: Glasgow Coma Scale, mechanism of injury, injury type (e.g., penetrating, blunt), systolic blood pressure, and age. The model achieved an area under the receiver operating characteristic curve of 0.83 (95% CI 0.80, 0.85) and had a calibration curve slope of 0.98 (95% CI 0.67, 1.29). TITAN had high specificity (98%), negative predictive value (97%), and accuracy (96%) at a binary probability threshold of 22.6%. CONCLUSION The TITAN Bayesian network predicts the risk of intubation in pediatric trauma patients using five factors that are observable early in trauma resuscitation. Prospective validation of the model performance with patient outcomes is needed to assess real-life application benefits and risks. LEVEL OF EVIDENCE Prognostic and Epidemiological, Level III.
Collapse
Affiliation(s)
- Travis M Sullivan
- Division of Trauma and Burn Surgery, Children's National Hospital, Washington, DC, USA
| | - Mary S Kim
- Division of Trauma and Burn Surgery, Children's National Hospital, Washington, DC, USA
| | - Genevieve J Sippel
- Division of Trauma and Burn Surgery, Children's National Hospital, Washington, DC, USA
| | | | - Caroline G Melhado
- Department of Surgery, University of California San Francisco, San Francisco, CA, USA
| | | | - Suzanne M Moody
- Division of Pediatric General and Thoracic Surgery, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA
| | - Rajan K Thakkar
- Division of Pediatric Surgery, Nationwide Children's, Columbus, OH, USA
| | - Meera Kotagal
- Division of Pediatric General and Thoracic Surgery, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA; Department of Surgery, University of Cincinnati College of Medicine, Cincinnati, OH, USA
| | - Aaron R Jensen
- Department of Surgery, University of California San Francisco, San Francisco, CA, USA; Division of Pediatric Surgery, UCSF Benioff Children's Hospitals, San Francisco, CA, USA
| | - Randall S Burd
- Division of Trauma and Burn Surgery, Children's National Hospital, Washington, DC, USA.
| |
Collapse
|
19
|
Castro CA, Warren JR, Helgertz J. Distinctively black names and mechanisms of discrimination: Evidence from the early 20th century. SOCIAL SCIENCE RESEARCH 2025; 126:103136. [PMID: 39909625 DOI: 10.1016/j.ssresearch.2024.103136] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/09/2024] [Revised: 12/17/2024] [Accepted: 12/17/2024] [Indexed: 02/07/2025]
Abstract
What were the effects of having a distinctively African American-sounding name on educational attainment, occupation, income, marital status, and longevity in early 20th century America? How did those effects differ for people based on their phenotypical race/ethnicity? The findings of contemporary research have shown racialized names to be related to negative outcomes such as job interview callbacks, birth outcomes, and teacher expectations. Furthermore, previous research has shown that the consequences of race-specific names explain as much as 10% of the historical between-race mortality gap (Cook et al., 2016). Theoretically, we argue, names should have been less of a mechanism for racial discrimination in earlier eras of American history. Using a sibling comparison design and linked administrative records, we hypothesize that there was little racial discrimination based on people's names in early 20th century America. We find that men with more African American-sounding names do no worse (or better) with respect to education, wages, occupation, or longevity than their brothers with less African American-sounding names; this finding holds for white and black men. This does not imply the absence of race-based discrimination in early 20th century America. Instead, it implies that people in this era discriminated based on something other than names and the race implied by those names.
Collapse
Affiliation(s)
| | - John Robert Warren
- Department of Sociology, University of Michigan, Ann Arbor, MI, 48109, United States.
| | | |
Collapse
|
20
|
Jamalpour Z, Ghaderi S, Fathian-Kolahkaj M. High-risk patient profiles for ovarian cancer: A new approach using cluster analysis of tumor markers. J Gynecol Obstet Hum Reprod 2025; 54:102888. [PMID: 39617144 DOI: 10.1016/j.jogoh.2024.102888] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] |