The effect of fine grits and fine debris concentrations on the MLVSS/MLSS ratio of an activated sludge system.

This study embarks on an explorative investigation into the effects of typical concentrations and varying particle sizes of fine grits (FG, the involatile portion of suspended solids) and fine debris (FD, the volatile yet unbiodegradable fraction of suspended solids) within the influent on the mixed liquor volatile suspended solids (MLVSS)/mixed liquor suspended solids (MLSS) ratio of an activated sludge system. Through meticulous experimentation, it was discerned that the addition of FG or FD, the particle size of FG, and the concentration of FD bore no substantial impact on the pollutant removal efficiency (denoted by the removal rate of COD and ammonia nitrogen) under constant operational conditions. However, a notable decrease in the MLVSS/MLSS ratio was observed with a typical FG concentration of 20 mg/L, with smaller FG particle sizes exacerbating this reduction. Additionally, variations in FD concentrations influenced both MLSS and MLVSS/MLSS ratios; a higher FD concentration led to an increased MLSS and a reduced MLVSS/MLSS ratio, indicating FD accumulation in the system. A predictive model for MLVSS/MLSS was constructed based on quality balance calculations, offering a tool for foreseeing the MLVSS/MLSS ratio under stable long-term influent conditions of FG and FD. This model, validated using data from the BXH wastewater treatment plant (WWTP), showcased remarkable accuracy.

Construction of a risk prediction model for lung infection after chemotherapy in lung cancer patients based on the machine learning algorithm.

Purpose: The objective of this study was to create and validate a machine learning (ML)-based model for predicting the likelihood of lung infections following chemotherapy in patients with lung cancer. Methods: A retrospective study was conducted on a cohort of 502 lung cancer patients undergoing chemotherapy. Data on age, Body Mass Index (BMI), underlying disease, chemotherapy cycle, number of hospitalizations, and various blood test results were collected from medical records. We used the Synthetic Minority Oversampling Technique (SMOTE) to handle unbalanced data. Feature screening was performed using the Boruta algorithm and The Least Absolute Shrinkage and Selection Operator (LASSO). Subsequently, six ML algorithms, namely Logistic Regression (LR), Random Forest (RF), Gaussian Naive Bayes (GNB), Multi-layer Perceptron (MLP), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) were employed to train and develop an ML model using a 10-fold cross-validation methodology. The model's performance was evaluated through various metrics, including the area under the receiver operating characteristic curve (ROC), accuracy, sensitivity, specificity, F1 score, calibration curve, decision curves, clinical impact curve, and confusion matrix. In addition, model interpretation was performed by the Shapley Additive Explanations (SHAP) analysis to clarify the importance of each feature of the model and its decision basis. Finally, we constructed nomograms to make the predictive model results more readable. Results: The integration of Boruta and LASSO methodologies identified Gender, Smoke, Drink, Chemotherapy cycles, pleural effusion (PE), Neutrophil-lymphocyte count ratio (NLR), Neutrophil-monocyte count ratio (NMR), Lymphocytes (LYM) and Neutrophil (NEUT) as significant predictors. The LR model demonstrated superior performance compared to alternative ML algorithms, achieving an accuracy of 81.80%, a sensitivity of 81.1%, a specificity of 82.5%, an F1 score of 81.6%, and an AUC of 0.888(95%CI(0.863-0.911)). Furthermore, the SHAP method identified Chemotherapy cycles and Smoke as the primary decision factors influencing the ML model's predictions. Finally, this study successfully constructed interactive nomograms and dynamic nomograms. Conclusion: The ML algorithm, combining demographic and clinical factors, accurately predicted post-chemotherapy lung infections in cancer patients. The LR model performed well, potentially improving early detection and treatment in clinical practice.

Combining lymph node ratio to develop prognostic models for postoperative gastric neuroendocrine neoplasm patients.

BACKGROUND: Lymph node ratio (LNR) was demonstrated to play a crucial role in the prognosis of many tumors. However, research concerning the prognostic value of LNR in postoperative gastric neuroendocrine neoplasm (NEN) patients was limited. AIM: To explore the prognostic value of LNR in postoperative gastric NEN patients and to combine LNR to develop prognostic models. METHODS: A total of 286 patients from the Surveillance, Epidemiology, and End Results database were divided into the training set and validation set at a ratio of 8:2. 92 patients from the First Affiliated Hospital of Soochow University in China were designated as a test set. Cox regression analysis was used to explore the relationship between LNR and disease-specific survival (DSS) of gastric NEN patients. Random survival forest (RSF) algorithm and Cox proportional hazards (CoxPH) analysis were applied to develop models to predict DSS respectively, and compared with the 8th edition American Joint Committee on Cancer (AJCC) tumor-node-metastasis (TNM) staging. RESULTS: Multivariate analyses indicated that LNR was an independent prognostic factor for postoperative gastric NEN patients and a higher LNR was accompanied by a higher risk of death. The RSF model exhibited the best performance in predicting DSS, with the C-index in the test set being 0.769 [95% confidence interval (CI): 0.691-0.846] outperforming the CoxPH model (0.744, 95%CI: 0.665-0.822) and the 8th edition AJCC TNM staging (0.723, 95%CI: 0.613-0.833). The calibration curves and decision curve analysis (DCA) demonstrated the RSF model had good calibration and clinical benefits. Furthermore, the RSF model could perform risk stratification and individual prognosis prediction effectively. CONCLUSION: A higher LNR indicated a lower DSS in postoperative gastric NEN patients. The RSF model outperformed the CoxPH model and the 8th edition AJCC TNM staging in the test set, showing potential in clinical practice.

Development and validation of a predictive nomogram for the risk of MAFLD in postmenopausal women.

Background and aim: Metabolic-associated fatty liver disease (MAFLD) has gradually become one of the main health concerns regarding liver diseases. Postmenopausal women represent a high-risk group for MAFLD; therefore, it is of great importance to identify and intervene with patients at risk at an early stage. This study established a predictive nomogram model of MAFLD in postmenopausal women and to enhance the clinical utility of the new model, the researchers limited variables to simple clinical and laboratory indicators that are readily obtainable. Methods: Data of 942 postmenopausal women from January 2023 to October 2023 were retrospectively collected and divided into two groups according to the collection time: the training group (676 cases) and the validation group (226 cases). Significant indicators independently related to MAFLD were identified through univariate logistic regression and stepwise regression, and the MAFLD prediction nomogram was established. The C-index and calibration curve were used to quantify the nomogram performance, and the model was evaluated by measuring the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA). Results: Of 37 variables, 11 predictors were identified, including occupation (worker), body mass index, waist-to-hip ratio, number of abortions, anxiety, hypertension, hyperlipidemia, diabetes, hyperuricemia, and diet (meat and processed meat). The C-index of the training group predicting the related risk factors was 0.827 (95% confidence interval [CI] 0.794-0.860). The C-index of the validation group was 0.787 (95% CI 0.728-0.846). Calibration curves 1 and 2 (BS1000 times) were close to the diagonal, showing a good agreement between the predicted probability and the actual incidence in the two groups. The AUC of the training group was 0.827, the sensitivity was 0.784, and the specificity was 0.735. The AUC of the validation group was 0.787, the sensitivity was 0.674, and the specificity was 0.772. The DCA curve showed that the nomogram had a good net benefit in predicting MAFLD in postmenopausal women. Conclusions: A predictive nomogram for MAFLD in postmenopausal women was established and verified, which can assist clinicians in evaluating the risk of MAFLD at an early stage.

Predictive Models for Long Term Survival of AML Patients Treated with Venetoclax and Azacitidine or 7+3 Based on Post Treatment Events and Responses: Retrospective Cohort Study.

BACKGROUND: The treatment of acute myeloid leukemia (AML) in older or unfit patients typically involves a regimen of venetoclax plus azacitidine (ven/aza). Toxicity and treatment responses are highly variable following treatment initiation and clinical decision-making continually evolves in response to these as treatment progresses. To improve clinical decision support (CDS) following treatment initiation, predictive models based on evolving and dynamic toxicities, disease responses, and other features should be developed. OBJECTIVE: This study aims to generate machine learning (ML)-based predictive models that incorporate individual predictors of overall survival (OS) for patients with AML, based on clinical events occurring after the initiation of ven/aza or 7+3 regimen. METHODS: Data from 221 patients with AML, who received either the ven/aza (n=101 patients) or 7+3 regimen (n=120 patients) as their initial induction therapy, were retrospectively analyzed. We performed stratified univariate and multivariate analyses to quantify the association between toxicities, hospital events, and short-term disease responses and OS for the 7+3 and ven/aza subgroups separately. We compared the estimates of confounders to assess potential effect modifications by treatment. 17 ML-based predictive models were developed. The optimal predictive models were selected based on their predictability and discriminability using cross-validation. Uncertainty in the estimation was assessed through bootstrapping. RESULTS: The cumulative incidence of posttreatment toxicities varies between the ven/aza and 7+3 regimen. A variety of laboratory features and clinical events during the first 30 days were differentially associated with OS for the two treatments. An initial transfer to intensive care unit (ICU) worsened OS for 7+3 patients (aHR 1.18, 95% CI 1.10-1.28), while ICU readmission adversely affected OS for those on ven/aza (aHR 1.24, 95% CI 1.12-1.37). At the initial follow-up, achieving a morphologic leukemia free state (MLFS) did not affect OS for ven/aza (aHR 0.99, 95% CI 0.94-1.05), but worsened OS following 7+3 (aHR 1.16, 95% CI 1.01-1.31) compared to that of complete remission (CR). Having blasts over 5% at the initial follow-up negatively impacted OS for both 7+3 (P<.001) and ven/aza (P<.001) treated patients. A best response of CR and CR with incomplete recovery (CRi) was superior to MLFS and refractory disease after ven/aza (P<.001), whereas for 7+3, CR was superior to CRi, MLFS, and refractory disease (P<.001), indicating unequal outcomes. Treatment-specific predictive models, trained on 120 7+3 and 101 ven/aza patients using over 114 features, achieved survival AUCs over 0.70. CONCLUSIONS: Our findings indicate that toxicities, clinical events, and responses evolve differently in patients receiving ven/aza compared with that of 7+3 regimen. ML-based predictive models were shown to be a feasible strategy for CDS in both forms of AML treatment. If validated with larger and more diverse data sets, these findings could offer valuable insights for developing AML-CDS tools that leverage posttreatment clinical data.

Predictive model for novel subtypes of patients undergoing lower extremity amputation for peripheral artery disease: An unsupervised machine learning study.

Background: Peripheral artery disease (PAD) represents the frequently seen circulatory condition related to a risk of critical limb ischemia and amputation. Critical lower extremity ischemia may require amputation, and the outcomes vary. In this study, we developed an artificial intelligence (AI)-driven predictive model for PAD subtypes to assess risk among patients more precisely and accurately to predict disease progression. Methods: The present retrospective study examined clinical data in PAD patents undergoing lower extremity amputation. The data were analyzed using an unsupervised machine learning algorithm (UMLA) for subgroup identification and risk stratification. The clustering result accuracy was validated by analyzing the follow-up data of clusters. Finally, we built the prediction model with binary logistic regression. Results: In total, we enrolled 507 cases into this work. Two distinct subgroups, consisting of Clusters 1 and 2, were identified by UMLA; those from Cluster 1 showed markedly poorer conditions and prognostic outcomes compared with those from Cluster 2. With regard to the new PAD subtype, we established a nomogram with eight predictive factors, including gender, age, smoking history, diabetes and coronary heart disease history, albumin levels, endovascular intervention, and amputation level. The nomogram could accurately categorize patients into two identified clusters, and the area under receiver operating characteristic curve was 0.861 (95 % confidence interval: 0.830-0.893). Conclusion: In this study, UMLA was used to identify new phenotypic subgroups among PAD cases who showed different risks of amputation. Our constructed AI-driven predictive model for PAD subtypes showed that it can be used for risk stratification and clinical management with high accuracy and reliability.

Next generation sequencing reveals the mutation landscape of Chinese MDS patients and the association between mutations and AML transformations.

BACKGROUND/OBJECTIVE: Approximately 30% of patients with MDS eventually develop to acute myeloid leukemia (AML). Our study aimed to investigate the mutation landscape of Chinese MDS patients and identify the mutated genes which are closely implicated in the transformation of MDS to AML. METHODS: In total, 412 sequencing data collected from 313 patients were used for analysis. Mutation frequencies between different groups were compared by Fisher's exact. A predictive model for risk of transformation/death of newly diagnosed patients was constructed by logistic regression. RESULTS: The most frequently mutated genes in newly diagnosed patients were TP53, TET2, RUNX1, PIGA, and BCOR and mutations of RUNX1, TP53, BCORL1, TET2, and BCOR genes were more common in the treated MDS patients. Besides, we found that the mutation frequencies of IDH2, TET2, and EZH2 were significantly higher in MDS patients aged over 60 years. Moreover, two mutation sites, KRASG12A and TP53H140N were detected only at transformation in one patient, while not detected at diagnosis. In addition, the mutation frequencies of EZH2 V704F and TET2 I1873N were stable from diagnosis to transformation in two patients. Finally, we constructed a predictive model for risk of transformation/death of newly diagnosed patients combing detected data of 10 genes and the number of to leukocyte, with a sensitivity of 63.3% and a specificity of 84.6% in distinguishing individuals with and without risk of transformation/death. CONCLUSION: In summary, our study found several mutations associated with the transformation from MDS to AML, and constructed a predictive model for risk of transformation/death of MDS patients.

Development and validation of a predictive model for submucosal fibrosis in patients with early gastric cancer undergoing endoscopic submucosal dissection: experience from a large tertiary center.

BACKGROUND: Submucosal fibrosis is associated with adverse events of endoscopic submucosal dissection (ESD). The present study mainly aimed to establish a predictive model for submucosal fibrosis in patients with early gastric cancer (EGC) undergoing ESD. METHODS: Eligible patients with EGC, identified at Qilu Hospital of Shandong University from April 2013 to December 2023, were retrospectively included and randomly split into a training set and a validation set in a 7:3 ratio. Logistic regression analyses were used to pinpoint the risk factors for submucosal fibrosis. A nomogram was developed and confirmed using receiver operating characteristic (ROC) curves, calibration plots, Hosmer-Lemeshow (H-L) tests, and decision curve analysis (DCA) curves. Besides, a predictive model for severe submucosal fibrosis was further conducted and tested. RESULTS: A total of 516 cases in the training group and 220 cases in the validation group were recruited. The nomogram for submucosal fibrosis contained the following items: tumour location (long axis), tumour location (short axis), ulceration, and biopsy pathology. ROC curves showed high efficiency with an area under the ROC of 0.819 in the training group, and 0.812 in the validation group. Calibration curves and H-L tests indicated good consistency. DCA proved the nomogram to be clinically beneficial. Furthermore, the four items were also applicable for a nomogram predicting severe fibrosis, and the model performed well. CONCLUSION: The predictive models, initially constructed in this study, were validated as convenient and feasible for endoscopists to predict submucosal fibrosis and severe fibrosis in patients with EGC undergoing ESD.

Clinical Predictors of Medication Compliance in Patients With Acute Herpetic Neuralgia.

PURPOSE: Pain is one of the most common and harmful symptoms experienced by individuals with acute herpetic neuralgia (AHN). In this population, studies to determine the causes that affect patients taking medications compliance are rare. This study aimed to construct a predictive model for medication compliance of patients with AHN and to verify its performance. DESIGN AND METHODS: In this prospective study of 398 patients with AHN who were discharged from a tertiary hospital with medications from July 2020 to October 2022, we used logistic regression analysis to explore the predictive factors of medication compliance of patients with AHN and to construct a nomogram. The area under the curve was used to evaluate the predictive effect of the model. RESULTS: A predictive model of drug compliance of patients with AHN was constructed based on the following four factors: disease duration, pain severity before treatment, medication beliefs, and comorbidity of chronic diseases. The area under the curve of the model was 0.766 (95% confidence interval [0.713, 0.819]), with a maximum Youden's index of 0.431, sensitivity of 0.776, and specificity of 0.655. A linear calibration curve was found with a slope close to 1. CONCLUSIONS: The prediction model constructed in this study had good predictive performance and provided a reference for early clinical screening of independent factors that affected the medication compliance of patients with AHN.

Prediction of lateral lymph node metastasis in rectal cancer patients based on MRI using clinical, deep transfer learning, radiomic, and fusion models.

Introduction: Lateral lymph node (LLN) metastasis in rectal cancer significantly affects patient treatment and prognosis. This study aimed to comprehensively compare the performance of various predictive models in predicting LLN metastasis. Methods: In this retrospective study, data from 152 rectal cancer patients who underwent lateral lymph node (LLN) dissection were collected. The cohort was divided into a training set (n=86) from Tianjin Union Medical Center (TUMC), and two testing cohorts: testing cohort (TUMC) (n=37) and testing cohort from Gansu Provincial Hospital (GSPH) (n=29). A clinical model was established using clinical data; deep transfer learning models and radiomics models were developed using MRI images of the primary tumor (PT) and largest short-axis LLN (LLLN), visible LLN (VLLN) areas, along with a fusion model that integrates features from both deep transfer learning and radiomics. The diagnostic value of these models for LLN metastasis was analyzed based on postoperative LLN pathology. Results: Models based on LLLN image information generally outperformed those based on PT image information. Rradiomics models based on LLLN demonstrated improved robustness on external testing cohorts compared to those based on VLLN. Specifically, the radiomics model based on LLLN imaging achieved an AUC of 0.741 in the testing cohort (TUMC) and 0.713 in the testing cohort (GSPH) with the extra trees algorithm. Conclusion: Data from LLLN is a more reliable basis for predicting LLN metastasis in rectal cancer patients with suspicious LLN metastasis than data from PT. Among models performing adequately on the internal test set, all showed declines on the external test set, with LLLN_Rad_Models being less affected by scanning parameters and data sources.

Comparison of clinical outcomes and perinatal outcomes between natural cycle and hormone replacement therapy of frozen-thawed embryo transfer in patients with regular menstruation: a propensity score-matched analysis.

Purpose: To investigate potential differences in pregnancy outcomes among patients with regular menstruation who underwent frozen-thawed embryo transfer using natural cycle (NC) or hormone replacement therapy (HRT). Methods: This study retrospectively analyzed 2672 patients with regular menstruation who underwent FET from November 2015 to June 2021 at the single reproductive medical center. A one-to-one match was performed applying a 0.02 caliper with propensity score matching. Independent factors influencing the live birth and clinical pregnancy rates were screened and developed in the nomogram by logistic regression analysis. The efficacy of live birth rate and clinical pregnancy rate prediction models was assessed with the area under the ROC curve, and the live birth rate prediction model was internally validated within the bootstrap method. Results: The NC protocol outperformed the HRT protocol in terms of clinical pregnancy and live birth rates. The stratified analysis revealed consistently higher live birth and clinical pregnancy rates with the NC protocol across different variable strata compared to the HRT protocol. However, compared to the HRT treatment, perinatal outcomes indicated that the NC protocol was related to a higher probability of gestational diabetes. Multifactorial logistic regression analysis demonstrated independent risk factors for live birth rate and clinical pregnancy rate. To predict the two rates, nomogram prediction models were constructed based on these influencing factors. The receiver operating characteristic curve demonstrated moderate predictive ability with an area under curve (AUC) of 0.646 and 0.656 respectively. The internal validation of the model for live birth rate yielded an average AUC of 0.646 implying the stability of the nomogram model. Conclusion: This study highlighted that NC yielded higher live birth and clinical pregnancy rates in comparison to HRT in women with regular menstruation who achieved successful pregnancies through frozen-thawed embryo transfer. However, it might incur a higher risk of developing gestational diabetes.

A Predictive Model for Initial Platinum-Based Chemotherapy Efficacy in Patients with Postoperative Epithelial Ovarian Cancer Using Tissue-Derived Small Extracellular Vesicles.

Epithelial ovarian cancer (EOC) is an often-fatal malignancy marked by the development of resistance to platinum-based chemotherapy. Thus, accurate prediction of platinum drug efficacy is crucial for strategically selecting postoperative interventions to mitigate the risks associated with suboptimal therapeutic outcomes and adverse effects. Tissue-derived extracellular vesicles (tsEVs), in contrast to their plasma counterparts, have emerged as a powerful tool for examining distinctive attributes of EOC tissues. In this study, 4D data-independent acquisition (DIA) proteomic sequencing was performed on tsEVs obtained from 58 platinum-sensitive and 30 platinum-resistant patients with EOC. The analysis revealed a notable enrichment of differentially expressed proteins that were predominantly associated with immune-related pathways. Moreover, pivotal immune-related proteins (IRPs) were identified by LASSO regression. These factors, combined with clinical parameters selected through univariate logistic regression, were used for the construction of a model employing multivariate logistic regression. This model integrated three tsEV IRPs, CCR1, IGHV_35 and CD72, with one clinical parameter, the presence of postoperative residual lesions. Thus, this model could predict the efficacy of initial platinum-based chemotherapy in patients with EOC post-surgery, providing prognostic insights even before the initiation of chemotherapy.

A risk prediction model based on machine learning algorithm for parastomal hernia after permanent colostomy.

OBJECTIVE: To develop a machine learning-based risk prediction model for postoperative parastomal hernia (PSH) in colorectal cancer patients undergoing permanent colostomy, assisting nurses in identifying high-risk groups and devising preventive care strategies. METHODS: A case-control study was conducted on 495 colorectal cancer patients who underwent permanent colostomy at the Second Affiliated Hospital of Anhui Medical University from June 2017 to June 2023, with a 1-year follow-up period. Patients were categorized into PSH and non-PSH groups based on PSH occurrence within 1-year post-operation. Data were split into training (70%) and testing (30%) sets. Variable selection was performed using Least Absolute Shrinkage and Selection Operator (LASSO) regression, and binary classification prediction models were established using Logistic Regression (LR), Support Vector Classification (SVC), K Nearest Neighbor (KNN), Random Forest (RF), Light Gradient Boosting Machine (LGBM), and Extreme Gradient Boosting (XgBoost). The binary classification label denoted 1 for PSH occurrence and 0 for no PSH occurrence. Parameters were optimized via 5-fold cross-validation. Model performance was evaluated using Area Under Curve (AUC), specificity, sensitivity, accuracy, positive predictive value, negative predictive value, and F1-score. Clinical utility was evaluated using decision curve analysis (DCA), model explanation was enhanced using shapley additive explanation (SHAP), and model visualization was achieved using a nomogram. RESULTS: The incidence of PSH within 1 year was 29.1% (144 patients). Among the models tested, the RF model demonstrated the highest discrimination capability with an AUC of 0.888 (95% CI: 0.881-0.935), along with superior specificity, accuracy, sensitivity, and F1 score. It also showed the highest clinical net benefit on the DCA curve. SHAP analysis identified the top 10 influential variables associated with PSH risk: body mass index (BMI), operation duration, history and status of chronic obstructive pulmonary disease (COPD), prealbumin, tumor node metastasis (TNM) staging, stoma site, thickness of rectus abdominis muscle (TRAM), C-reactive protein CRP, american society of anesthesiologists physical status classification (ASA), and stoma diameter. These insights from SHAP plots illustrated how these factors influence individual PSH outcomes. The nomogram was used for model visualization. CONCLUSION: The Random Forest model demonstrated robust predictive performance and clinical relevance in forecasting colonic PSH. This model aids in early identification of high-risk patients and guides preventive care.

The risk stratification and predictive performance of a new combined polygenic risk score for hepatocellular carcinoma.

BACKGROUND: Recent genome-wide association studies (GWASs) in liver diseases have generated some polygenic risk scores (PRSs), but their predictive effectiveness on hepatocellular carcinoma (HCC) risk assessment remains unclear. METHODS: Here, we constructed a novel combined polygenic risk score and evaluated its increment to the well-established risk model. We used 15 HCC-associated genetic loci from two PRSs and FinnGen GWAS data to calculate a PRS-combined score and to fit the related PRS model in the UK Biobank cohort (N = 436,162). The PRS-combined score was further assessed for risk stratification for HCC integrating with the recommended clinical risk scores. RESULTS: The PRS-combined model achieved a better AUC (0.657) than that of PRS-HFC (0.637) and PRS-cirrhosis (0.645). The top 20% of the PRS-combined distribution had a 3.25 increased risk of HCC vs. the middle decile (45-55%). At the population level, the addition of PRS-combined to the CLivD score significantly increased the C-statistic (from 0.716 to 0.746) and provided a remarkable improvement in reclassification (NRI = 0.088) at the 10-year risk threshold of 0.2%. In clinic, additional assessment of PRS-combined would reclassify 34,647 intermediate-risk participants as high genetic risk, corresponding to an increase of 63.92% (62/97) of the HCC events classified at high risk using the Fibrosis-4 alone. CONCLUSIONS: The PRS may enhance HCC risk prediction effectiveness in the general population and refine risk stratification of the conventional clinical indicator.

Prediction of PSA Response after Dexamethasone Switch during Abiraterone Acetate + Prednisolone Treatment of Metastatic Castration-Resistant Prostate Cancer Patients.

BACKGROUND: The aim was to elaborate a predictive model to find responders for the corticosteroid switch (from prednisolone to dexamethasone) at the first prostate-specific antigen (PSA) progression (≥25% increase) during abiraterone acetate (AA) treatment of metastatic castration-resistant prostate cancer (mCRPC) patients. METHODS: If PSA has decreased (≥25%) after switch, patients were considered responders. Logistic regression of 19 dichotomized parameters from routine laboratory and patients' history was used to find the best model in a cohort of 67 patients. The model was validated in another cohort of 42 patients. RESULTS: The model provided 92.5% and 90.5% accuracy in the testing and the validation cohorts, respectively. Overall the accuracy was 91.7%. The AUC of ROC curve was 0.92 (95% CI 0.85-0.96). After a median follow-up of 27.9 (26.3-84) months, the median AA+dexamethasone treatment duration (TD) in non-responders and responders was 4.7 (3.1-6.5) and 11.1 (8.5-12.9) months and the median overall survival (OS) was 23.2 (15.6-25.8) and 33.5 (26.1-38) months, respectively. Multivariate Cox regression revealed that responsiveness was an independent marker of TD and OS. CONCLUSIONS: A high accuracy model was developed for mCRPC patients in predicting cases which might benefit from the switch. For non-responders, induction of the next systemic treatment is indicated.

Machine Learning Models Reliably Predict Clinical Outcomes in Medial Patellofemoral Ligament Reconstruction.

PURPOSE: To develop the machine learning model to predict clinical outcomes following MPFLR and identify the important predictive indicators. METHODS: This study included patients who underwent MPFLR from January 2018 to December 2022. The exclusion criteria were as follows: 1) concurrent bony procedures, 2) history of other knee surgeries, and 3) follow-up period of less than 12 months. Forty-two predictive models were constructed for seven clinical outcomes (failure to achieve MCID of clinical scores, return to pre-injury sports, pivoting sports, and recurrent instability) using six machine learning algorithms (Random Forest, Logistic Regression, Support Vector Machine, Decision Tree, implemented multilayer perceptron, and K-nearest neighbor). The performance of the model was evaluated using metrics such as the area under the receiver operating characteristic curve (AUC), accuracy, specificity, and sensitivity. Additionally, Shapley Additive Explanation summary plot was employed to identify the important predictive factors of the best-performing model. RESULTS: A total of 218 patients met criteria. For the best-performing models in predicting failure to achieve the MCID for Lysholm, IKDC, Kujala, and Tegner scores, the AUCs and accuracies were 0.884 (good) and 87.3%, 0.859 (good) and 86.2%, 0.969 (excellent) and 97.0%, and 0.760 (fair) and 76.8%, respectively; 0.952 (excellent) and 95.2% for return to pre-injury sports; 0.756 (fair) and 75.4% for return to pivoting sports; and 0.943 (excellent) and 94.9% for recurrent instability. Low preoperative Tegner score, shorter time to surgery, and absence of severe trochlear dysplasia were significant predictors for return to pre-injury sports, while absence of severe trochlear dysplasia and patellar alta were significant predictors for return to pivoting sports. Older age, female sex, and low preoperative Lysholm score were highly predictive of recurrent instability. CONCLUSION: The predictive models developed using machine learning algorithms can reliably forecast the clinical outcomes of MPFLR, particularly demonstrating excellent performance in predicting recurrent instability. LEVEL OF EVIDENCE: Level III, case-control study.

Environmental Geomarker to Assess Impact on Hospitalization.

By linking medical real-world data with geographic information, it is possible to evaluate the impact on hospitalization based on these characteristics, such as patient residence information and disease and medical information. In this study, environmental exposure to air pollutants was reported as a risk factor, and predictive models were used to examine factors affecting health. The importance of the characteristics appeared according to the disease, and overall, the patient profile at the time of admission, such as ADL, was shown to be high, but for respiratory diseases, the cumulative concentration of air pollutants NO2, SPM, and NOx for one year before the onset of admission was the top risk factor for long-term hospitalization, suggesting the influence of exposure due to environmental factors.

Comparison of Regression Methods to Predict the First Spike Latency in Response to an External Stimulus in Intracellular Recordings for Cerebellar Cells.

The significance of intracellular recording in neurophysiology is emphasized in this article, with considering the functions of neurons, particularly the role of first spike latency in response to external stimuli. The study employs advanced machine learning techniques to predict first spike latency from whole cell patch recording data. Experiments were conducted on Control (Salin) and Experiment (Harmaline) groups, generating a dataset for developing predictive models. Because the dataset has a limited number of samples, we utilized models that are effective with small datasets. Among different groups of regression models (linear, ensemble, and tree models), the ensemble models, specifically the LGB method, can achieve better performance. The results demonstrate accurate prediction of first spike latency, with an average mean squared error of 0.0002 and mean absolute error of 0.01 in 10-fold cross-validation. The research suggests the potential of machine learning in forecasting the first spike latency, allowing reliable estimation without the need for extensive animal testing. This intelligent predictive system facilitates efficient analysis of first spike latency changes in both healthy and unhealthy brain cells, streamlining experimentation and providing more detailed insights into the captured signals.

A predictive model for 28-day mortality after discharge in patients with sepsis associated with cerebrovascular disease.

BACKGROUND: The present study investigated the association between cerebrovascular diseases and sepsis, including its occurrence, progression, and impact on mortality. However, there is currently a lack of predictive models for 28-day mortality in patients with cerebrovascular disease associated with sepsis. OBJECTIVE: The objective of this study is to examine the mortality rate within 28 days after discharge in this population, while concurrently developing a corresponding predictive model. METHODS: The data for this retrospective cohort study were obtained from the MIMIC-IV database. Patients with sepsis and cerebrovascular disease in the ICU were included. Laboratory indicators, vital signs, and demographic data were collected within 24 hours of ICU admission. Mortality rates within 28 days after discharge were calculated based on patient death times. Logistic regression analysis was used to identify potential variables for a predictive model. A nomogram visualized the prediction model. The performance of the model was evaluated using ROC curves, Calibration plots, and DCA. RESULTS: The study enrolled a total of 2660 patients diagnosed with cerebrovascular disease complicated by sepsis, consisting of 1434 males (53.91%) with a median age of 70.97 (59.60, 80.73). Among this cohort of patients, a total of 751 fatalities occurred within 28 days following discharge. The multivariate regression analysis revealed that age, creatinine, arterial oxygen partial pressure (Pa O2), arterial carbon dioxide partial pressure (Pa CO2), respiratory rate, white blood cell (WBC) count, Body Mass Index (BMI), and race demonstrated potential predictive variables. The aforementioned model yielded an area under the ROC curve of 0.744, accompanied by a sensitivity of 66.2% and specificity of 71.2%. Furthermore, both calibration plots and DCA demonstrated robust performance in practical applications. CONCLUSION: The proposed prediction model allows clinicians to promptly assess the mortality risk in patients with cerebrovascular disease complicated by sepsis within 28 days after discharge, facilitating early intervention strategies. Consequently, clinicians can implement additional advantageous medical interventions for individuals with cerebrovascular disease and sepsis.