Predictive Performance of Advanced-DiaRem for Diabetes Remission after Roux-en-Y Gastric Bypass Surgery - Obesity Surgery Background The global epidemics of obesity and type II diabetes highlight the need for reliable tools to predict surgical outcomes, particularly diabetes remission. The applicability of the Advanced D...

The Advanced-DiaRem score showed limited accuracy for predicting diabetes remission after RYGB in Iranian patients (AUC = 66.7%). Population-specific models are needed.
#BariatricSurgery #DiabetesRemission #PredictiveModel link.springer.com/article/10.1...

Predictive Model of Acupuncture Adherence in Alzheimer Disease: Secondary Analysis of Randomized Controlled Trials Background: The therapeutic efficacy of acupuncture in treating Alzheimer’s disease (AD) largely depends on consistent treatment adherence. Therefore, identifying key factors influencing adherence and developing targeted interventions are crucial for enhancing clinical outcomes. Objective: To develop and validate a predictive model for identifying patients with AD who are likely to maintain good adherence to acupuncture treatment. Methods: This secondary analysis included 108 patients with probable AD, aged 50–85 years, from two independent randomized controlled trials conducted at Guang’anmen Hospital, China Academy of Chinese Medical Sciences. Sixty-six patients were assigned to the development cohort and 42 to the external validation cohort. Acupuncture adherence was defined as the proportion of completed sessions relative to scheduled sessions, with good adherence defined as ≥80% completion. Baseline data included demographic, clinical, cognitive, functional, psychological, and caregiving variables. Multivariable logistic regression with backward stepwise selection was used to identify significant predictors, and a nomogram was constructed based on the final model. Model performance was assessed using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis, with external validation performed by ROC analysis. Results: The number of treatments in the first month, caregiving role, and disease duration were identified as significant predictors of adherence. The nomogram incorporating these variables demonstrated excellent discrimination in the development cohort (AUC = 0.914) and good performance in the external validation cohort (AUC = 0.838). Conclusions: This study is the first to develop and validate a predictive model for acupuncture adherence in patients with AD. The model offers valuable clinical and research implications. Early identification of patients at high risk for non-adherence enables the implementation of targeted interventions or the use of stratified analyses to reduce bias and improve study integrity. Moreover, the identified predictors provide actionable insights for clinicians to enhance adherence and optimize treatment outcomes.

New in JMIR Aging: Predictive Model of Acupuncture Adherence in Alzheimer Disease: Secondary Analysis of Randomized Controlled Trials #Acupuncture #Alzheimers #ADResearch #PredictiveModel #Healthcare

Development of a health literacy prediction model: Using HLS-EU-Q16 questionnaire data from a population-based survey
Choi, M. et al.
Paper
Details
#HealthLiteracy #PredictiveModel #HLS_EU_Q16

Analysis of influencing factors of concurrent primary liver cancer in hepatitis B patients and construction of column chart prediction model | Epidemiology & Infection | Cambridge Core Analysis of influencing factors of concurrent primary liver cancer in hepatitis B patients and construction of column chart prediction model - Volume 153

A new predictive chart shows promise for assessing liver cancer risk in hepatitis B patients 🧬

Key factors: cirrhosis, HBV DNA load, alcohol use & family history. Model performed well across multiple hospitals.

🔗 https://cup.org/4o9es7n

#LiverCancer #HepatitisB #PredictiveModel #PublicHealth

A Data-Driven Approach to Assessing Hepatitis B Mother-to-Child Transmission Risk Prediction Model: Machine Learning Perspective Background: Hepatitis B virus (HBV) can be transmitted from mother to child either through transplacental infection or via blood-to-blood contact during or immediately after delivery. Early and accurate risk assessments are essential for guiding clinical decisions and implementing effective preventive measures. Data mining techniques are powerful tools for identifying key predictors in medical diagnostics. Objective: This study aims to develop a robust predictive model for mother-to-child transmission (MTCT) of HBV using decision tree algorithms, specifically Iterative Dichotomiser 3 (ID3) and classification and regression trees (CART). The study identifies clinically and paraclinically relevant predictors, particularly hepatitis B e antigen (HBeAg) status and peripheral blood mononuclear cell (PBMC) concentration, for effective risk stratification and prevention. Additionally, we will assess the model’s reliability and generalizability through cross-validation with various training-test split ratios, aiming to enhance its applicability in clinical settings and inform improved preventive strategies against HBV MTCT. Methods: This study used decision tree algorithms—ID3 and CART—on a data set of 60 hepatitis B surface antigen (HBsAg)–positive pregnant women. Samples were collected either before or at the time of delivery, enabling the inclusion of patients who were undiagnosed or had limited access to treatment. We analyzed both clinical and paraclinical parameters, with a particular focus on HBeAg status and PBMC concentration. Additional biochemical markers were evaluated for their potential contributory or inhibitory effects on MTCT risk. The predictive models were validated using multiple training-test split ratios to ensure robustness and generalizability. Results: Our analysis showed that 20 out of 48 (based on a split ratio of 0.8 from a total of 60 cases, 42%) to 27 out of 57 (based on a split ratio of 0.95 from a total of 60 cases, 47%) training cases with HBeAg-positive status were associated with a significant risk of MTCT of HBV (χ28=21.16, P=.007, df=8). Among HBeAg-negative women, those with PBMC concentrations ≥8 × 106 cells/mL exhibited a low risk of MTCT, whereas individuals with PBMC concentrations

JMIR Formative Res: A Data-Driven Approach to Assessing Hepatitis B Mother-to-Child Transmission Risk Prediction Model: Machine Learning Perspective #HepatitisB #MTCT #MachineLearning #DataMining #PredictiveModel

New artificial intelligence model personalizes bladder cancer treatment – BioNews Central A predictive model for chemotherapy response in muscle-invasive bladder cancer was developed by combining tumor imaging and gene expression data, potentially personalizing treatment and preventing unnecessary bladder removal. ...

A #PredictiveModel for #ChemotherapyResponse in muscle-invasive #BladderCancer was developed by combining #TumorImaging and #GeneExpression data, potentially personalizing treatment and preventing unnecessary #bladder removal.
#ArtificialIntelligence #PersonalizedTreatment

💻 The #Dashboard went 3-0 in the #NBA yesterday. The hot streak continues🔥

#DataDriven #FreePicks #Algorithm #SportsBetting #PredictiveModel #Gambling #MarchMadness

4/ 💡 Why does this matter? The Cr/CysC ratio is a simple, cost-effective measure that may serve as a proxy for muscle mass, a known predictor of better outcomes in dialysis patients. #HealthcareInnovation #PredictiveModel #RenalCare

Want to learn how to create a predictive model for your sports data story? We created one to predict the winner of the 4 Nations Face-Off tournament. #nhl #4nationsfaceoff #hockey #datastory #sportsdatastory #hockeyanalytics #datapunkhockey #predictivemodel youtu.be/qhETzicm2uw

Between my #NHL, #NBA and #CBB models yesterday, I went 9-5. Not a bad day in the #SportsBetting world...

#DataDriven #Analytics #PredictiveModel #Algorithm #Betting #Gambling

After 3 #winning days in a row, my #NBA model finally had a #losing day...

#Gambling #PredictiveModel #Data #Analytics #SportsHandicapping

My #NBA model continues its #winningstreak, going 2-0 yesterday and 9-2 over the past 3 days...

#Winning #DataDriven #PredictiveModel #Data #Analytics #SportsBetting

Just 1 pick from my #NHL model today. I made some slight tweaks/improvements to the model yesterday, so it should improve on that 55% winning percentage.

#TexasHockey #Utah #Hockey #UtahHockeyClub #DataDriven #PredictiveModel

No picks today from my #NHL model. It just doesn't feel confident in any of tonight's 4 games...

#Algorithm #PredictiveModel #Data #Analytics #PowerBI

One week left for my #CFB model. It will be tough to hit my 60% goal for the season, but it's been a #winning season nonetheless.

#DataDriven #CollegeFootball #BetSky #PredictiveModel

Could really use a 2-0 day from my #NBA model today. Both the #Kings and #Nets are playing the second game of a back to back.

#NBASky #Data #Analytics #PowerBI #PredictiveModel

Only one game across the #NHL today, and my model doesn't have enough confidence to make a pick either way...

#SportsBetting #PredictiveModel #Algorithm

My #NFL model projects the #Buccaneers to get off the schneid and easily hit the over.

#Giants #NewYork #BetSky #NFLSky #PredictiveModel

Hidden Landscape - Interpreting #Buried #Archaeological #Site Potential, #WhiteRiverValley, #Indiana
-
doi.org/10.5406/2327...
-
#GIS #spatial #mapping #geoarchaeology #predictivemodel #soils #model #spatialanalysis #sampling #FirstNation #indigeneous #settlements #geochronology #dating #age