Prediction of Chinese suitable habitats of Panax notoginseng under climate change based on MaxEnt and chemometric methods.

Notoginseng saponin R1; ginsenosides Rg1, Re, Rb1, and Rd; the sum of the five saponins; and underground-part fresh weight (UPFW) of single plants were used as quality evaluation indices for Panax notoginseng (Burk.) F. H. Chen (P. notoginseng). Comprehensive evaluation of P. notoginseng samples from 30 production areas was performed using that MaxEnt model. Spatial pattern changes in suitable P. notoginseng habitats were predicted for current and future periods (2050s, 2070s, and 2090s) using SSP126 and SSP585 models. The results revealed that temperature, precipitation, and solar radiation were important environmental variables. Suitable habitats were located mainly in Yunnan, Guizhou, and Sichuan Provinces. The distribution core of P. notoginseng is predicted to shift southeast in the future. The saponin content decreased from the southeast to the northwest of Yunnan Province, which was contrary to the UPFW trend. This study provides the necessary information for the protection and sustainable utilization of P. notoginseng resources, and a theoretical reference for its application in the quality evaluation of Chinese medicinal products.

Risk prediction models for diabetic nephropathy among type 2 diabetes patients in China: a systematic review and meta-analysis.

Objective: This study systematically reviews and meta-analyzes existing risk prediction models for diabetic kidney disease (DKD) among patients with type 2 diabetes, aiming to provide references for scholars in China to develop higher-quality risk prediction models. Methods: We searched databases including China National Knowledge Infrastructure (CNKI), Wanfang Data, VIP Chinese Science and Technology Journal Database, Chinese Biomedical Literature Database (CBM), PubMed, Web of Science, Embase, and the Cochrane Library for studies on the construction of DKD risk prediction models among type 2 diabetes patients, up until 28 December 2023. Two researchers independently screened the literature and extracted and evaluated information according to a data extraction form and bias risk assessment tool for prediction model studies. The area under the curve (AUC) values of the models were meta-analyzed using STATA 14.0 software. Results: A total of 32 studies were included, with 31 performing internal validation and 22 reporting calibration. The incidence rate of DKD among patients with type 2 diabetes ranged from 6.0% to 62.3%. The AUC ranged from 0.713 to 0.949, indicating the prediction models have fair to excellent prediction accuracy. The overall applicability of the included studies was good; however, there was a high overall risk of bias, mainly due to the retrospective nature of most studies, unreasonable sample sizes, and studies conducted in a single center. Meta-analysis of the models yielded a combined AUC of 0.810 (95% CI: 0.780-0.840), indicating good predictive performance. Conclusion: Research on DKD risk prediction models for patients with type 2 diabetes in China is still in its initial stages, with a high overall risk of bias and a lack of clinical application. Future efforts could focus on constructing high-performance, easy-to-use prediction models based on interpretable machine learning methods and applying them in clinical settings. Registration: This systematic review and meta-analysis was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement, a recognized guideline for such research. Systematic review registration: https://www.crd.york.ac.uk/prospero/, identifier CRD42024498015.

A cloud-based medical device for predicting cardiac risk in suspected coronary artery disease: a rapid review and conceptual economic model.

Background: The CaRi-Heart® device estimates risk of 8-year cardiac death, using a prognostic model, which includes perivascular fat attenuation index, atherosclerotic plaque burden and clinical risk factors. Objectives: To provide an Early Value Assessment of the potential of CaRi-Heart Risk to be an effective and cost-effective adjunctive investigation for assessment of cardiac risk, in people with stable chest pain/suspected coronary artery disease, undergoing computed tomography coronary angiography. This assessment includes conceptual modelling which explores the structure and evidence about parameters required for model development, but not development of a full executable cost-effectiveness model. Data sources: Twenty-four databases, including MEDLINE, MEDLINE In-Process and EMBASE, were searched from inception to October 2022. Methods: Review methods followed published guidelines. Study quality was assessed using Prediction model Risk Of Bias ASsessment Tool. Results were summarised by research question: prognostic performance; prevalence of risk categories; clinical effects; costs of CaRi-Heart. Exploratory searches were conducted to inform conceptual cost-effectiveness modelling. Results: The only included study indicated that CaRi-Heart Risk may be predictive of 8 years cardiac death. The hazard ratio, per unit increase in CaRi-Heart Risk, adjusted for smoking, hypercholesterolaemia, hypertension, diabetes mellitus, Duke index, presence of high-risk plaque features and epicardial adipose tissue volume, was 1.04 (95% confidence interval 1.03 to 1.06) in the model validation cohort. Based on Prediction model Risk Of Bias ASsessment Tool, this study was rated as having high risk of bias and high concerns regarding its applicability to the decision problem specified for this Early Value Assessment. We did not identify any studies that reported information about the clinical effects or costs of using CaRi-Heart to assess cardiac risk. Exploratory searches, conducted to inform the conceptual cost-effectiveness modelling, indicated that there is a deficiency with respect to evidence about the effects of changing existing treatments or introducing new treatments, based on assessment of cardiac risk (by any method), or on measures of vascular inflammation (e.g. fat attenuation index). A de novo conceptual decision-analytic model that could be used to inform an early assessment of the cost effectiveness of CaRi-Heart is described. A combination of a short-term diagnostic model component and a long-term model component that evaluates the downstream consequences is anticipated to capture the diagnosis and the progression of coronary artery disease. Limitations: The rapid review methods and pragmatic additional searches used to inform this Early Value Assessment mean that, although areas of potential uncertainty have been described, we cannot definitively state where there are evidence gaps. Conclusions: The evidence about the clinical utility of CaRi-Heart Risk is underdeveloped and has considerable limitations, both in terms of risk of bias and applicability to United Kingdom clinical practice. There is some evidence that CaRi-Heart Risk may be predictive of 8-year risk of cardiac death, for patients undergoing computed tomography coronary angiography for suspected coronary artery disease. However, whether and to what extent CaRi-Heart represents an improvement relative to current standard of care remains uncertain. The evaluation of the CaRi-Heart device is ongoing and currently available data are insufficient to fully inform the cost-effectiveness modelling. Future work: A large (n = 15,000) ongoing study, NCT05169333, the Oxford risk factors and non-invasive imaging study, with an estimated completion date of February 2030, may address some of the uncertainties identified in this Early Value Assessment. Study registration: This study is registered as PROSPERO CRD42022366496. Funding: This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR135672) and is published in full in Health Technology Assessment; Vol. 28, No. 31. See the NIHR Funding and Awards website for further award information.

Coronary artery disease affects around 2.3 million people in the United Kingdom. It is caused by a build-up of fatty plaques on the walls of the blood vessels that supply the heart muscle. This can reduce the flow of blood to the heart and result in people experiencing chest pain (angina), especially when they exercise. Over time, the fatty plaques can grow and block more or all of the artery and blood clots can also form, causing blockage. A heart attack happens when the supply of blood to the heart muscle is blocked. People who have episodes of chest pain, whose doctors think that they may have coronary artery disease, can have a type of imaging (computed tomography coronary angiography) which shows whether there is any narrowing of their coronary arteries. When offering treatment, specialist heart doctors are likely to consider a person's symptoms and other risk factors (such as family history of heart disease, diabetes and smoking history), as well as how much narrowing of the arteries has happened. CaRi-Heart® is a computer programme that uses information about inflammation in a person's coronary arteries, together with recognised risk factors, such as age, sex, smoking, high cholesterol levels, high blood pressure and diabetes, to estimate an individual's risk of dying from a heart attack in the next 8 years. There is evidence that CaRi-Heart® is better at estimating this risk than using information recognised risk factors alone. However, there is a lack of information about how treatment could change as a result of using CaRi-Heart® and whether any changes would improve outcomes for patients. There is also a lack of information about how much CaRi-Heart® would cost the National Health Service.

Prediction model of malnutrition in hospitalized patients with acute stroke.

OBJECTIVE: The prognosis of stroke patients is greatly threatened by malnutrition. However, there is no model to predict the risk of malnutrition in hospitalized stroke patients. This study developed a predictive model for identifying high-risk malnutrition in stroke patients. METHODS: Stroke patients from two tertiary hospitals were selected as the objects. Binary logistic regression was used to build the model. The model's performance was evaluated using various metrics including the receiver operating characteristic curve, Hosmer-Lemeshow test, sensitivity, specificity, Youden index, clinical decision curve, and risk stratification. RESULTS: A total of 319 stroke patients were included in the study. Among them, 27% experienced malnutrition while in the hospital. The prediction model included all independent variables, including dysphagia, pneumonia, enteral nutrition, Barthel Index, upper arm circumference, and calf circumference (all p < 0.05). The AUC area in the modeling group was 0.885, while in the verification group, it was 0.797. The prediction model produces greater net clinical benefit when the risk threshold probability is between 0% and 80%, as revealed by the clinical decision curve. All p values of the Hosmer test were > 0.05. The optimal cutoff value for the model was 0.269, with a sensitivity of 0.849 and a specificity of 0.804. After risk stratification, the MRS scores and malnutrition incidences increased significantly with escalating risk levels (p < 0.05) in both modeling and validation groups. CONCLUSIONS: This study developed a prediction model for malnutrition in stroke patients. It has been proven that the model has good differentiation and calibration.

Gut microbes on the risk of advanced adenomas.

BACKGROUND: More than 90% of colorectal cancer (CRC) arises from advanced adenomas (AA) and gut microbes are closely associated with the initiation and progression of both AA and CRC. OBJECTIVE: To analyze the characteristic microbes in AA. METHODS: Fecal samples were collected from 92 AA and 184 negative control (NC). Illumina HiSeq X sequencing platform was used for high-throughput sequencing of microbial populations. The sequencing results were annotated and compared with NCBI RefSeq database to find the microbial characteristics of AA. R-vegan package was used to analyze α diversity and ß diversity. α diversity included box diagram, and ß diversity included Principal Component Analysis (PCA), principal co-ordinates analysis (PCoA), and non-metric multidimensional scaling (NMDS). The AA risk prediction models were constructed based on six kinds of machine learning algorithms. In addition, unsupervised clustering methods were used to classify bacteria and viruses. Finally, the characteristics of bacteria and viruses in different subtypes were analyzed. RESULTS: The abundance of Prevotella sp900557255, Alistipes putredinis, and Megamonas funiformis were higher in AA, while the abundance of Lilyvirus, Felixounavirus, and Drulisvirus were also higher in AA. The Catboost based model for predicting the risk of AA has the highest accuracy (bacteria test set: 87.27%; virus test set: 83.33%). In addition, 4 subtypes (B1V1, B1V2, B2V1, and B2V2) were distinguished based on the abundance of gut bacteria and enteroviruses (EVs). Escherichia coli D, Prevotella sp900557255, CAG-180 sp000432435, Phocaeicola plebeiuA, Teseptimavirus, Svunavirus, Felixounavirus, and Jiaodavirus are the characteristic bacteria and viruses of 4 subtypes. The results of Catboost model indicated that the accuracy of prediction improved after incorporating subtypes. The accuracy of discovery sets was 100%, 96.34%, 100%, and 98.46% in 4 subtypes, respectively. CONCLUSION: Prevotella sp900557255 and Felixounavirus have high value in early warning of AA. As promising non-invasive biomarkers, gut microbes can become potential diagnostic targets for AA, and the accuracy of predicting AA can be improved by typing.

Risk assessment tool for anemia of chronic disease in systemic lupus erythematosus: a prediction model.

OBJECTIVE: This study aims to develop a predictive model for estimating the likelihood of anemia of chronic disease (ACD) in patients with systemic lupus erythematosus (SLE) and to elucidate the relationship between various factors and ACD METHODS: Individuals diagnosed with SLE for at least one year were enrolled and categorized into two groups: those with ACD and those without anemia symptoms. Patients were randomly assigned to training and test sets at an 8:2 ratio. The least absolute shrinkage and selection operator (LASSO) method was used to select predictors, followed by logistic regression for modeling. Model performance was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) for both training and test sets. RESULTS: The study included a total of 216 patients, with 172 in the training set and 44 in the test set. LASSO identified 6 variables for constructing the predictive model, resulting in an area under the curve (AUC) of 0.833 (95% CI, 0.773-0.892) in the training set and 0.861 (95% CI, 0.750-0.972) in the test set. Calibration curves indicated consistency between expected and observed probabilities. DCA indicated that the model yielded a net benefit with threshold probabilities ranging from 20% to 90% in the training set and from 10% to 80% in the test set. CONCLUSION: This study presents a predictive model for assessing the risk of ACD in SLE patients. The model effectively captures the underlying mechanism of ACD in SLE and empowers clinicians to make well-informed treatment adjustments. Key Points • Development of a New Predictive Model: This study introduces a new predictive model to evaluate the likelihood of anemia of chronic disease (ACD) in patients with systemic lupus erythematosus (SLE). The model utilizes routine laboratory parameters to identify high-risk individuals, addressing a significant gap in current clinical practice. • Reflection of Potential Mechanisms for ACD Development: By incorporating the factors needed to construct the predictive model, this study also sheds light on the potential mechanisms of ACD development in SLE patients.

Identifying Dementia Severity Among People Living With Dementia Using Administrative Claims Data.

OBJECTIVES: There is currently no reliable tool for classifying dementia severity level based on administrative claims data. We aimed to develop a claims-based model to identify patients with severe dementia among a cohort of patients with dementia. DESIGN: Retrospective cohort study. SETTING AND PARTICIPANTS: We identified people living with dementia (PLWD) in US Medicare claims data linked with the Minimum Data Set (MDS) and Outcome and Assessment Information Set (OASIS). METHODS: Severe dementia was defined based on cognitive and functional status data available in the MDS and OASIS. The dataset was randomly divided into training (70%) and validation (30%) sets, and a logistic regression model was developed to predict severe dementia using baseline (assessed in the prior year) features selected by generalized linear mixed models (GLMMs) with least absolute shrinkage and selection operator (LASSO) regression. We assessed model performance by area under the receiver operating characteristic curve (AUROC), area under precision-recall curve (AUPRC), and precision and recall at various cutoff points, including Youden Index. We compared the model performance with and without using Synthetic Minority Oversampling Technique (SMOTE) to reduce the imbalance of the dataset. RESULTS: Our study cohort included 254,410 PLWD with 17,907 (7.0%) classified as having severe dementia. The AUROC of our primary model, without SMOTE, was 0.81 in the training and 0.80 in the validation set. In the validation set at the optimized Youden Index, the model had a sensitivity of 0.77 and specificity of 0.70. Using a SMOTE-balanced validation set, the model had an AUROC of 0.83, AUPRC of 0.80, sensitivity of 0.79, specificity of 0.74, positive predictive value of 0.75, and negative predictive value of 0.78 when at the optimized Youden Index. CONCLUSIONS AND IMPLICATIONS: Our claims-based algorithm to identify patients living with severe dementia can be useful for claims-based pharmacoepidemiologic and health services research.

Prioritising deteriorating patients using time-to-event analysis: prediction model development and internal-external validation.

BACKGROUND: Binary classification models are frequently used to predict clinical deterioration, however they ignore information on the timing of events. An alternative is to apply time-to-event models, augmenting clinical workflows by ranking patients by predicted risks. This study examines how and why time-to-event modelling of vital signs data can help prioritise deterioration assessments using lift curves, and develops a prediction model to stratify acute care inpatients by risk of clinical deterioration. METHODS: We developed and validated a Cox regression for time to in-hospital mortality. The model used time-varying covariates to estimate the risk of clinical deterioration. Adult inpatient medical records from 5 Australian hospitals between 1 January 2019 and 31 December 2020 were used for model development and validation. Model discrimination and calibration were assessed using internal-external cross validation. A discrete-time logistic regression model predicting death within 24 h with the same covariates was used as a comparator to the Cox regression model to estimate differences in predictive performance between the binary and time-to-event outcome modelling approaches. RESULTS: Our data contained 150,342 admissions and 1016 deaths. Model discrimination was higher for Cox regression than for discrete-time logistic regression, with cross-validated AUCs of 0.96 and 0.93, respectively, for mortality predictions within 24 h, declining to 0.93 and 0.88, respectively, for mortality predictions within 1 week. Calibration plots showed that calibration varied by hospital, but this can be mitigated by ranking patients by predicted risks. CONCLUSION: Time-varying covariate Cox models can be powerful tools for triaging patients, which may lead to more efficient and effective care in time-poor environments when the times between observations are highly variable.

Thrombotic Prediction Model Based on Epigenetic Regulator Mutations in Essential Thrombocythemia Patients Using Survival Analysis in Recurrent Events.

INTRODUCTION: Essential thrombocythemia (ET) involves the proliferation of megakaryocytes and platelets and is associated with an increased risk of thrombosis. We aimed to evaluate thrombotic risks in patients with epigenetic regulator mutations and generate a model to predict thrombosis in ET. MATERIALS AND METHODS: This cohort study enrolled patients aged > 15 years diagnosed with ET at the Songklanakarind Hospital between January 2002 and December 2019. Twenty-five targeted gene mutations, including somatic driver mutations (JAK2, CALR, MPL), epigenetic regulator mutations (TET2, DNMT3A, IDH1, IDH2, TET2, ASXL1, EZH2, SF3B1, SRSF2) and other genes relevant to myeloid neoplasms, were identified using next-generation sequencing. Thrombotic events were confirmed based on clinical condition and imaging findings, and thrombotic risks were analyzed using five survival models with the recurrent event method. RESULTS: Ninety-six patients were enrolled with a median follow-up of 6.91 years. Of these, 15 patients experienced 17 arterial thrombotic events in total. Patients with JAK2 mutation and IDH1 mutation had the highest frequency of thrombotic events with somatic driver mutations (17.3%) and epigenetic regulator mutations (100%). The 10-year thrombosis-free survival rate was 81.3% (95% confidence interval: 72.0-91.8%). IDH1 mutation was a significant factor for thrombotic risk in the multivariate analysis for all models. The Prentice, William, and Peterson (PWP) gap-time model was the most appropriate prediction model. CONCLUSIONS: The PWP gap-time model was a good predictive model for thrombotic risk in patients with ET. IDH1 mutation was significant risk factors for thrombosis; however, further studies with a larger sample size should confirm this and provide more insight.

Nomogram Model for Cardiac Surgery-Associated Acute Kidney Injury Based on Clinical Characteristics Combined with Plasma suPAR.

Objective: Analyze risk factors for cardiac surgery-associated acute kidney injury (CSA-AKI) in adults and establish a nomogram model for CSA-AKI based on plasma soluble urokinase-type plasminogen activator receptor (suPAR) and clinical characteristics. Methods: In a study of 170 patients undergoing cardiac surgery with cardiopulmonary bypass, enzyme-linked immunosorbent assay (ELISA) measured plasma suPAR levels. Multivariable logistic regression analysis identified risk factors associated with CSA-AKI. Subsequently, the CSA-AKI nomogram model was developed using R software. Predictive performance was evaluated using a receiver operating characteristic (ROC) curve and the area under the curve (AUC). Internal validation was performed through the Bootstrap method with 1000 repeated samples. Additionally, decision curve analysis (DCA) assessed the clinical applicability of the model. Results: Multivariable logistic regression analysis revealed that being male, age ≥ 50 years, operation time ≥ 290 minutes, postoperative plasma suPAR at 2 hours, and preoperative left ventricular ejection fraction (LVEF) were independent risk factors for CSA-AKI. Employing these variables as predictive factors, a nomogram model was constructed, an ROC curve was generated, and the AUC was computed as 0.817 (95% CI 0.726-0.907). The calibration curve indicated the accuracy of the model, and the results of DCA demonstrated that the model could benefit the majority of patients. Conclusion: Being male, age ≥ 50 years, operation time ≥ 290 minutes, low preoperative LVEF, and elevated plasma suPAR at 2 hours are independent risk factors for CSA-AKI. The nomogram model established based on these risk factors has high accuracy and clinical value, serving as a predictive tool for assessing the risk of CSA-AKI.

A nomogram prediction model for short-term aortic-related adverse events in patients with acute Stanford type B aortic intramural hematoma: development and validation.

Background: This study is to examine the factors associated with short-term aortic-related adverse events in patients with acute type B aortic intramural hematoma (IMH). Additionally, we develop a risk prediction nomogram model and evaluate its accuracy. Methods: This study included 197 patients diagnosed with acute type B IMH. The patients were divided into stable group (n = 125) and exacerbation group (n = 72) based on the occurrence of aortic-related adverse events. Logistic regression and the Least Absolute Shrinkage and Selection Operator (LASSO) method for variables based on baseline assessments with significant differences in clinical and image characteristics were employed to identify independent predictors. A nomogram risk model was constructed based on these independent predictors. The nomogram model was evaluated using various methods such as the receiver operating characteristic curve, calibration curve, decision analysis curve, and clinical impact curve. Internal validation was performed using the Bootstrap method. Results: A nomogram risk prediction model was established based on four variables: absence of diabetes, anemia, maximum descending aortic diameter (MDAD), and ulcer-like projection (ULP). The model demonstrated a discriminative ability with an area under the curve (AUC) of 0.813. The calibration curve indicated a good agreement between the predicted probabilities and the actual probabilities. The Hosmer-Lemeshow goodness of fit test showed no significant difference (χ 2 = 7.040, P = 0.532). The decision curve analysis (DCA) was employed to further confirm the clinical effectiveness of the nomogram. Conclusion: This study introduces a nomogram prediction model that integrates four important risk factors: ULP, MDAD, anemia, and absence of diabetes. The model allows for personalized prediction of patients with type B IMH.

Artificial intelligence in ischemic stroke images: current applications and future directions.

This paper reviews the current research progress in the application of Artificial Intelligence (AI) based on ischemic stroke imaging, analyzes the main challenges, and explores future research directions. This study emphasizes the application of AI in areas such as automatic segmentation of infarct areas, detection of large vessel occlusion, prediction of stroke outcomes, assessment of hemorrhagic transformation risk, forecasting of recurrent ischemic stroke risk, and automatic grading of collateral circulation. The research indicates that Machine Learning (ML) and Deep Learning (DL) technologies have tremendous potential for improving diagnostic accuracy, accelerating disease identification, and predicting disease progression and treatment responses. However, the clinical application of these technologies still faces challenges such as limitations in data volume, model interpretability, and the need for real-time monitoring and updating. Additionally, this paper discusses the prospects of applying large language models, such as the transformer architecture, in ischemic stroke imaging analysis, emphasizing the importance of establishing large public databases and the need for future research to focus on the interpretability of algorithms and the comprehensiveness of clinical decision support. Overall, AI has significant application value in the management of ischemic stroke; however, existing technological and practical challenges must be overcome to achieve its widespread application in clinical practice.

Retrospective clinical study analysis of skin adverse reactions related to epidermal growth factor receptor inhibitors.

Background: Epidermal growth factor receptor inhibitors (EGFRIs) represent a cornerstone in the targeted therapy of malignant tumors. While effective, dermatological adverse events (dAEs) associated with EGFRIs pose a significant challenge, often necessitating treatment discontinuation due to their severity and potential to impede the continuity of cancer therapy. Despite extensive research, the specific mechanisms and predictors of these adverse events remain poorly understood, particularly in diverse populations. This gap in knowledge underscores the need for targeted studies to better predict and manage these events, enhancing patient outcomes and adherence to life-saving therapies. Methods: This observational study was conducted at The First Affiliated Hospital of Guangxi Medical University, covering cancer patients treated with EGFRIs from 2020 to 2022. We analyzed clinical data including patient demographics, treatment specifics, and the development and timing of dAEs. The study employed SPSS 26.0 software for data analysis, focusing on the incidence of dAEs and factors influencing their occurrence. We used Kaplan-Meier and Cox regression methods to establish a predictive model for dAEs, tracking their onset and impact on treatment continuity. Results: In our study of 120 patients treated with EGFR inhibitors at The First Affiliated Hospital of Guangxi Medical University, we found a high prevalence of dAEs, with 84.2% of patients experiencing such effects. The most common manifestations were papulopustular rashes, observed as pustules in 52.5% and papules in 57.4% of cases, followed by nail lesions in 62.4% of patients, oral or other mucosal ulcers in 34.7%, and hair changes in 26.7%. The median incubation time (MIT) for dAEs was 5 weeks. We identified drug type, ethnicity, and occupation as statistically significant risk factors (P<0.05 for all) that influenced the MIT, which the Cox regression model further identified as protective factors. Nomograms were developed to assess the risk of dAEs, although it is important to note that these models have only been internally validated, lacking external validation data at this stage. Conclusions: The study highlights the high incidence of EGFRIs-associated dAEs, with specific dermatological manifestations posing significant challenges in cancer therapy. The identification of drug type, ethnicity, and occupation as influential factors on the MIT for dAEs informs clinical decisions. Our prediction model serves as a practical tool for evaluating the risk of developing dAEs over time, aiming to optimize patient management and mitigate treatment interruptions.

Development of a prediction model for the association between thyroid dysfunction and breast cancer.

Background: Thyroid dysfunction is associated with the risk of benign and malignant breast tumors, but currently there is a lack of model studies to demonstrate the predictive role of thyroid dysfunction in benign and malignant breast tumors. This study aims to establish a model for predicting the association between thyroid dysfunction and breast cancer. Methods: This retrospective study enrolled breast tumor patients from the Affiliated Tumor Hospital of Xinjiang Medical University from 2015 to 2019. Their baseline data and laboratory data were collected. Python was used for data processing and analysis. Data preparation, feature selection, model construction, and model evaluation were conducted. We utilized the classification probabilities generated by the model as scores and further conducted a least absolute shrinkage and selection operator analysis. Results: Analysis of the laboratory data revealed statistically significant differences in thyroid-stimulating hormone, thyroxine, free thyroxine, free triiodothyronine, and thyronine levels between patients with benign and malignant tumors. Based on age, ethnicity, thyroid function, and estrogen levels, the predictive model for breast tumor malignancy indicated that the factors with the greatest importance ranking were age > follicle-stimulating hormone > luteinizing hormone > prolactin > thyroxine > testosterone > ethnicity. The model showed an accuracy rate of 83.70%, precision of 90.69%, sensitivity of 84.74%, and specificity of 81.50%. The area under the receiver operating characteristic curve was 0.9012, close to 1, indicating good predictive performance of the model. Conclusions: The predictive model based on factors such as age, ethnicity, thyroid function, and estrogen levels performs well in predicting the occurrence and development of benign and malignant breast tumors.

Development of a machine learning-based model for the prediction and progression of diabetic kidney disease: A single centred retrospective study.

BACKGROUND: Diabetic kidney disease (DKD) is a diabetic microvascular complication often characterized by an unpredictable progression. Hence, early detection and recognition of patients vulnerable to progression is crucial. OBJECTIVE: To develop a prediction model to identify the stages of DKD and the factors contributing to progression to each stage using machine learning. METHODOLOGY: A retrospective study was conducted in a South Indian tertiary care hospital and collected the details of patients diagnosed with DKD from January 2017 to January 2022. Bayesian optimization-based machine learning techniques such as classification and regression were employed. The model was developed with the help of an optimization framework that effectively balances classification, prediction accuracy, and explainability. RESULTS: Of the 311 patients diagnosed with DKD, 227 were selected for the study. A system for predicting DKD has been created for a patient dataset utilizing a variety of machine-learning approaches. The eXtreme gradient (XG) Boost method excelled, achieving 88.75% accuracy, 88.57% precision, 91.4% sensitivity,100% specificity, and 89.49% F1-score. An interpretable data-driven method highlights significant features for early DKD diagnosis. The best explainable prediction model uses the XG Boost classifier, revealing serum uric acid, urea, phosphorous, red blood cells, calcium, and absolute eosinophil count as the major predictors influencing the progression of DKD. In the case of regression models, the gradient boost regressor performed the best, with an R2 score of 0.97. CONCLUSION: Machine learning algorithms can effectively predict the stages of DKD and thus help physicians in providing patients with personalized care at the right time.

Cross-Combination Analyses of Random Forest Feature Selection and Decision Tree Model for Predicting Intraoperative Hypothermia in Total Joint Arthroplasty.

BACKGROUND: In total joint arthroplasty patients, intraoperative hypothermia (IOH) is associated with perioperative complications and an increased economic burden. Previous models have some limitations and mainly focus on regression modeling. Random forest (RF) algorithms and decision tree modeling are effective for eliminating irrelevant features and making predictions that aid in accelerating modeling and reducing application difficulty. METHODS: We conducted this prospective observational study using convenience sampling and collected data from 327 total joint arthroplasty patients in a tertiary hospital from March 4, 2023 to September 11, 2023. Of those, 229 patients were assigned to the training and 98 to the testing sets. The Chi-square, Mann-Whitney U, and t-tests were used for baseline analyses. The feature variables selection used the RF algorithms, and the decision tree model was trained on 299 examples and validated on 98. The sensitivity, specificity, recall, F1 score, and area under the curve (AUC) were used to test the model's performance. RESULTS: The RF algorithms identified the preheating time, the volume of flushing fluids, the intraoperative infusion volume, the anesthesia time, the surgical time, and the core temperature after intubation as risk factors for IOH. The decision tree was grown to five levels with nine terminal nodes. The overall incidence of IOH was 42.13%. The sensitivity, specificity, recall, F1 score, and AUC were 0.651, 0.907, 0.916, 0.761, and 0.810, respectively. The model indicated strong internal consistency and predictive ability. CONCLUSIONS: The preheating time, the volume of flushing fluids, the intraoperative infusion volume, the anesthesia time, the surgical time, and the core temperature after intubation could accurately predict IOH in total joint arthroplasty patients. By monitoring these factors, the clinical staff could achieve early detection and intervention of IOH in total joint arthroplasty patients.

Implementation of a machine learning model in acute coronary syndrome and stroke risk assessment for patients with lower urinary tract symptoms.

OBJECTIVE: The global population is aging and the burden of lower urinary tract symptoms (LUTS) is expected to increase. According to the National Health Insurance Research Database, our previous studies have showed LUTS may predispose patients to cardiovascular disease. However, it is difficult to provide a personalized risk assessment in the context of "having acute coronary syndrome (ACS) and stroke." This study aimed to develop an artificial intelligence (AI)-based prediction model for patients with LUTS. MATERIAL AND METHODS: We retrospectively reviewed the electronic medical records of 1799 patients with LUTS at Chi Mei Medical Center between January 1, 2001 and December, 31, 2018. Features with >10 cases and high correlations with outcomes were imported into six machine learning algorithms. The study outcomes included ACS and stroke. Model performances was evaluated using the area under the receiver operating characteristic curve (AUC). The model with the highest AUC was used to implement the clinical risk prediction application. RESULTS: Age, systemic blood pressure, diastolic blood pressure, creatinine, glycated hemoglobin, hypertension, diabetes mellitus and hyperlipidemia were the most relevant features that affect the outcomes. Based on the AUC, our optimal model was built using multilayer perception (AUC = 0.803) to predict ACS and stroke events within 3 years. CONCLUSION: We successfully built an AI-based prediction system that can be used as a prediction model to achieve time-saving, precise, personalized risk evaluation; it can also be used to offer warning, enhance patient adherence, early intervention and better health care outcomes.

Prediction models for the risk of ventilator-associated pneumonia in patients on mechanical ventilation: A systematic review and meta-analysis.

BACKGROUND: Identifying patients at risk for ventilator-associated pneumonia (VAP) through prediction models can facilitate medical decision-making. Our objective was to systematically evaluate the current models for VAP in patients with mechanical ventilation (MV). METHODS: Nine databases systematically retrieved from establishment to March 6, 2024. Two independent reviewers performed study selection, data extraction, and quality assessment, respectively. The Prediction Model Risk of Bias Assessment Tool was used to evaluate the risk of model bias and applicability. Stata 17.0 was used for conducting a meta-analysis of discrimination of model validation. RESULTS: The total of 34 studies were included, with reported 52 prediction models. More than 50% of the models were developed using logistic regression, and the AUCs of the included models ranged from 0.509 to 0.982. Predictors that appeared more frequently in the models were MV duration, length of ICU stay, age. Each study was essentially considered having an overall high risk of bias. A meta-analysis of 17 studies containing 33 models with validated and complete data was performed with a pooled AUC of 0.80 (95% CI: 0.78-0.83). CONCLUSION: Despite the relatively excellent performance of the models, there is a high risk of bias of the model development process. Enhancing the methodological quality and revealing the details of study process, especially the external validation, practical application and optimization of the models need urgent attention.

Drug exposure as a predictor in diabetic retinopathy risk prediction models; a systematic review and meta-analysis.

PURPOSE: To conduct a systematic review to assess drug exposure handling in diabetic retinopathy (DR) risk prediction models, a network-meta-analysis to identify drugs associated with DR and a meta-analysis to determine which drugs contributed to enhanced model performance. DESIGN: Systematic review and meta-analysis. METHODS: We included studies presenting DR models incorporating drug exposure as a predictor. We searched EMBASE, MEDLINE and SCOPUS from inception to December 2023. We evaluated the quality of studies using the Prediction model Risk of Bias Assessment Tool and certainty using GRADE. We conducted network meta-analysis and meta-analysis to estimate the odds ratio (OR) and pooled C-statistic, respectively, and 95% confidence intervals (CI) (PROSPERO: CRD42022349764). RESULTS: Of 5,653 records identified, we included 28 studies of 678,837 type 1 or 2 diabetes participants, of which 38,579 (5.7%) had DR. A total of 19, 3 and 7 studies were at high, unclear, and low risk of bias, respectively. Drugs included in models as predictors were: insulin (n=24), antihypertensives (n=5), oral antidiabetics (n=12), lipid-lowering drugs (n=7), antiplatelets (n=2). Drug exposure was modelled primarily as a categorical variable (n=23 studies). Two studies handled drug exposure as time-varying covariates, and one as a time-dependent covariate. Insulin was associated with an increased risk of DR (OR= 2.50; 95%-CI: 1.61-3.86). Models that included insulin (n=9) had a higher pooled C-statistic (C-statistic=0.84, CI: 0.80-0.88), compared to models (n=9) that incorporated a combination of drugs alongside insulin (C-statistic= 0.79, CI:0.74-0.84), as well as models (n=3) not including insulin (C-statistic =0.70, CI: 0.64-0.75). Limitations include the high risk of bias and significant heterogeneity in reviewed studies. CONCLUSION: This is the first review assessing drug exposure handling in DR prediction models. Drug exposure was primarily modelled as a categorical variable, with insulin associated with improved model performance. However, due to suboptimal drug handling, associations between other drugs and model performance may have been overlooked. This review proposes the following for future DR prediction models: 1) evaluation of drug exposure as a variable, 2) use of time-varying methodologies, and 3) consideration of drug regimen details. Improving drug exposure handling could potentially unveil novel variables capable of significantly enhancing the predictive capability of prediction models.

Conventional and modern markers of pregnancy of unknown location: Update and narrative review.

Pregnancy of unknown location (PUL) is a temporary pathologic or physiologic phenomenon of early pregnancy that requires follow up to determine the final pregnancy outcome. Evidence indicated that PUL patients suffer a remarkably higher rate of adverse pregnancy outcomes, represented by ectopic gestation and early pregnancy loss, than the general population. In the past few decades, discussion about PUL has never stopped, and a variety of markers have been widely investigated for the early and accurate evaluation of PUL, including serum biomarkers, ultrasound imaging features, multivariate analysis, and the diagnosis of ectopic pregnancy based on risk stratification. So far, machine learning (ML) methods represented by M4 and M6 logistic regression have gained a level of recognition and are continually improving. Nevertheless, the heterogeneity of PUL markers, mainly caused by the limited sample size, the differences in population and technical maturity, etc., have hampered the management of PUL. With the advancement of multidisciplinary integration and cutting-edge technologies (e.g. artificial intelligence, prediction model development, and telemedicine), novel markers, and strategies for the management of PUL are expected to be developed. In this review, we summarize both conventional and novel markers (represented by artificial intelligence) for PUL assessment and management, investigate their advancements, limitations and challenges, and propose insights on future research direction and clinical application.