#riskprediction
LightNews LightNews
kristalentine.bsky.social
Our #KDIGOCoronaryValve workgroup debates criteria for cardiac eval before #KidneyTransplant, surveillance after listing, novel #RiskPrediction tools, & #perioperative care. Appreciate multidisciplinary brainstorming at reception. Thanks to @wolfgang for welcome address. @goKDIGO
November 28, 2024 at 8:12 AM
kristalentine.bsky.social
Our #KDIGOCoronaryValve workgroup debates criteria for cardiac eval before #KidneyTransplant, surveillance after listing, novel #RiskPrediction tools, & #perioperative care. Appreciate multidisciplinary brainstorming at reception. Thanks to @wolfgang for welcome address. @goKDIGO
November 28, 2024 at 8:12 AM
kihear.bsky.social
Long awaited peer review finally completed!! Our paper comparing quantitative metabolomics disease risk prediction with PGS is accepted in Nature Comms!! 🥳🥳
@nightingalehealth.com #riskprediction #metabolomics #nmr #genomics #polygenicscore

www.nature.com/articles/s41...
Metabolomic and genomic prediction of common diseases in 700,217 participants in three national biobanks - Nature Communications
Identifying individuals at high risk for chronic diseases can improve prevention. Here, the authors show that blood metabolomics scores effectively stratify disease risk and compare favorably to genet...
www.nature.com
December 4, 2024 at 11:46 AM
iwashyna.bsky.social
#NotEvenTrying

New in @sccmcriticalcare.bsky.social Crit Care Med, @hauschildt.bsky.social + @ajadmon.bsky.social review 120 ML or AI studies predicting sepsis, sepsis-related outcomes or sepsis treatment in adult populations

NONE reported formal fairness metrics

pubmed.ncbi.nlm.nih.gov/40488579/
Abstract text: Consideration of Sociodemographics in Machine Learning-Driven Sepsis Risk Prediction OBJECTIVES: Use of machine learning (ML) and artificial intelligence (AI) in prediction of sepsis and related outcomes is growing. Guidelines call for explicit reporting of study data demographics and stratified performance analyses to assess potential sociodemographic bias. We assessed reporting of sociodemographic data and other considerations, such as use of stratified analyses or use of so-called “fairness metrics", among AI and ML models in sepsis. DATA SOURCES: PubMed identified systematic and narrative reviews from which studies were extracted using PubMed and Google Scholar. STUDY SELECTION: Studies were extracted from selected review articles published between January 1, 2023, and June 30, 2024, and related to sepsis, riskprediction, and ML; we extracted studies predicting sepsis, sepsis-related outcomes, or sepsis treatment in adult populations. DATA EXTRACTION: Data were extracted by two reviewers using predefined forms, and included study type, outcome of interest, setting, dataset used, reporting of sample sociodemographics, inclusion of sociodemographics as predictors, stratification by sociodemographics or assessment of fairness metrics, and reporting a lack of sociodemographic considerations as a limitation. DATA SYNTHESIS: Thirteen of 96 review studies (14%) met inclusion criteria: 6 systematic reviews and 7 narrative reviews. 120 of 170 studies (71%) extracted from these review articles were included in our review. 99 of 120 studies (83%) reported a measure of geography or where data was collected. Eighty (67%) reported sex/gender, 24 (20%) reported race/ethnicity, and 4 (3%) reported other sociodemographics. Only three stratified performance results (2%) by sociodemographics; none reported formal fairness metrics. Beyond a lack of geographic heterogeneity (39/120, 33%), few studies reported a lack of sociodemographic consideration as a limitation
June 9, 2025 at 8:46 PM
larsjuhljensen.bsky.social
How is genetic epidemiology evolving in the era of big data and AI?
Read our recap of key trends and takeaways from IGES 2025 here: medium.com/zs-associate...
#IGES2025 #GeneticEpidemiology #MultiOmics #AIinGenomics #DiversityInResearch #RiskPrediction #Innovation #ZS
IGES 2025: Causality, diversity, and innovation
Read about the 2025 International Genetic Epidemiology Society conference and learn why genomics research is entering a new era.
medium.com
September 18, 2025 at 12:22 PM
pittcp3.bsky.social
Congrats to @walidgellad.bsky.social & the mPROVEN study team on a new award to create a playbook for ethical use of #machinelearning based #opioid #riskprediction models, building on years of expertise developing & deploying these tools in a variety of care settings.

www.cp3.pitt.edu/mproven
August 29, 2025 at 2:03 PM
erinltempleman.bsky.social
🚨Big news! Excited to share my first PhD paper!🎉
We validated & improved a T1D risk model using TrialNet data (originally from TEDDY), boosting accuracy 📈
bmcmedicine.biomedcentral.com/articles/10....
Try the web tool 👉 t1dpredictor.diabetesgenes.org
#T1D #RiskPrediction #PrecisionMedicine #TrialNet
Development and recalibration of a multivariable type 1 diabetes prediction model for type 1 diabetes across multiple screening studies - BMC Medicine
Background Accurate type 1 diabetes prediction is important to facilitate screening for pre-clinical type 1 diabetes to enable potential early disease-modifying interventions and to reduce the risk of...
bmcmedicine.biomedcentral.com
July 23, 2025 at 1:50 PM
respirology.bsky.social
Development and Validation of a #RiskPrediction Model to Identify Women With Chronic Obstructive Pulmonary Disease for Proactive #PalliativeCare
onlinelibrary.wiley.com/doi/10.1111/...

#COPD
onlinelibrary.wiley.com
March 5, 2025 at 1:00 AM
florinaerbeli.bsky.social
#DYSLEXIA AND #GENETICS
🧬~70% genetic influence confirmed by twin studies
🧬no single "dyslexia gene"; many small genetic effects contribute
🧬shared genetic risks with ADHD, dyscalculia, and DLD
🧬GWAS studies identify multiple associated genetic variants, improving riskprediction

🔗 shorturl.at/dZ1nJ
Insights into Dyslexia Genetics Research from the Last Two Decades
Dyslexia, a specific reading disability, is a common (up to 10% of children) and highly heritable (~70%) neurodevelopmental disorder. Behavioral and molecular genetic approaches are aimed towards diss...
shorturl.at
January 31, 2025 at 12:15 AM
arbisoft.bsky.social
AI is making credit decisions more adaptive, transparent, and fair than ever before.
🔗 Explore the 8 steps for building a deep learning credit scoring system: https://f.mtr.cool/iegmtazfeq

#DeepLearning #FintechInnovation #RiskPrediction #ArbisoftBlogs
October 15, 2025 at 11:51 AM
tumscvdri.bsky.social
The simple LENT index—using length of stay, prior ED visits, and NT-proBNP—best predicts 30-day death or readmission after #HeartFailure hospitalization. Accurate, easy, and practical! #RiskPrediction @drrajivsankar.bsky.social @mmamas1973.bsky.social onlinelibrary.wiley.com/doi/10.1002/...
Comparative performance of risk prediction indices for mortality or readmission following heart failure hospitalization
Comparative performance of 7 risk prediction indices in patients hospitalized for heart failure. In this cohort of 1206 patients, the LENT index offered the greatest discrimination, calibration, and ...
onlinelibrary.wiley.com
July 9, 2025 at 6:02 AM
marianaraniere.bsky.social
Clinicians often decide treatment based only on symptoms and clinical history. Our study combines risk prediction and decision models to guide more cost-effective treatment choices.

medrxiv.org/cgi/content/...

#RiskPrediction #DecisionMaking #CostEffectiveness #MachineLearning
https://medrxiv.org/content/10.110…
August 12, 2025 at 5:28 PM
moorejh.bsky.social
The development and evaluation of Polygenic Risk Score reports: A systematised review of the literature www.sciencedirect.com/science/arti... #genetics #genomics #PRS #riskprediction
The development and evaluation of Polygenic Risk Score reports: A systematised review of the literature
The return of polygenic risk scores (PGS) is currently being assessed in research settings for clinical utility and validity, and it is anticipated th…
www.sciencedirect.com
April 8, 2025 at 5:45 PM
premierscience.bsky.social
doi.org/10.70389/PJC...

#machinelearning #injury #riskprediction #sport
Machine Learning Approaches to Injury Risk Prediction in Sport - Premier Science
Injury risk prediction, Machine learning models, Sports analytics, Athlete monitoring, Random Forest and xgboost.
doi.org
September 11, 2025 at 5:21 PM
jenniejlin.bsky.social
Forgot to hashtag this: #MachineLearning #riskprediction #notmyareaofexpertise
November 23, 2024 at 2:13 AM
diabetologiajnl.bsky.social
Sleep duration & insomnia associated with ↑ #T2D risk but addition of these sleep traits to #QDiabetes risk prediction model offers no clinically meaningful predictive gain. #riskprediction #DiabetesResearch link.springer.com/article/10.1... 🔓
Clinical utility of self-reported sleep duration and insomnia symptoms in type 2 diabetes prediction - Diabetologia
Aims/hypothesis Suboptimal sleep health is linked to higher risks for incident type 2 diabetes. We aimed to assess the clinical utility of adding self-reported sleep traits to a type 2 diabetes predic...
link.springer.com
August 11, 2025 at 12:02 PM
pittcp3.bsky.social
The PROTECT study builds on CP3's extensive experience in creating #RiskPrediction #algorithms and deploying them in practice with paired decision support tools to help clinicians make informed decisions for safer prescribing.

www.cp3.pitt.edu/research/ris...

2/2
Risk Prediction Projects | Center for Pharmaceutical Policy and Prescribing | University of Pittsburgh
Our group has conducted pivotal work that addresses the opioid epidemic by developing overdose risk prediction tools using machine learning and building the foundation for implementing these tools in ...
www.cp3.pitt.edu
August 8, 2025 at 3:45 PM
ajpcardio.bsky.social
🧬 New research alert: Comparison of PREVENT Score versus the Pooled Cohort Equation for estimating ASCVD risk in patients with Rheumatoid Arthritis. Explore the full study 👉 https://ow.ly/zrxH50XjT5h

#Cardiology #RA #ASCVD #RiskPrediction #PreventiveCardiology #CardioSky #MedSky
October 30, 2025 at 1:50 PM
susannbeier.bsky.social
🧠 No stenosis? No problem. Left main artery shape alone may act as a surrogate for disease risk.

First study to link anatomy + haemodynamics in patients without overt disease.
👉 www.nature.com/articles/s41...

#RiskPrediction #Cardiology #MedImageAI
Assessing left main bifurcation anatomy and haemodynamics as a potential surrogate for disease risk in suspected coronary artery disease without stenosis - Scientific Reports
Scientific Reports - Assessing left main bifurcation anatomy and haemodynamics as a potential surrogate for disease risk in suspected coronary artery disease without stenosis
www.nature.com
July 23, 2025 at 10:46 AM