Final Prediction Model Research Articles

Machine learning for detecting fake accounts and genetic algorithm-based feature selection

Abstract People rely extensively on online social networks (OSNs) in Africa, which aroused cyber attackers’ attention for various nefarious actions. This global trend has not spared African online communities, where the proliferation of OSNs has provided new opportunities and challenges. In Africa, as in many other regions, a burgeoning black-market industry has emerged, specializing in the creation and sale of fake accounts to serve various purposes, both malicious and deceptive. This paper aims to build a set of machine-learning models through feature selection algorithms to predict the fake account, increase performance, and reduce costs. The suggested approach is based on input data made up of features that describe the profiles being investigated. Our findings offer a thorough comparison of various algorithms. Furthermore, compared to machine learning without feature selection and Boruta, machine learning employing the suggested genetic algorithm-based feature selection offers a clear runtime advantage. The final prediction model achieves AUC values between 90% and 99.6%. The findings showed that the model based on the features chosen by the GA algorithm provides a reasonable prediction quality with a small number of input variables, less than 31% of the entire feature space, and therefore permits the accurate separation of fake from real users. Our results demonstrate exceptional predictive accuracy with a significant reduction in input variables using the genetic algorithm, reaffirming the effectiveness of our approach.

Immunogenic profiling of metastatic uveal melanoma discerns a potential signature related to prognosis

BackgroundUveal melanoma (UM) is an aggressive intraocular malignant tumor. The present study aimed to identify the key genes associated with UM metastasis and established a gene signature to analyze the relationship between the signature and prognosis and immune cell infiltration. Later, a predictive model combined with clinical variables was developed and validated.MethodsTwo UM gene expression profile chip datasets were downloaded from TCGA and GEO databases. Immune-related genes (IRGs) were obtained from IMPORT database. First, these mRNAs were intersected with IRGs, and weighted gene co-expression network analysis (WGCNA) was used to identify the co-expression of genes primarily associated with metastasis of UM. Univariate Cox regression analysis screened the genes related to prognosis. LASSO-Cox established a risk score to distinguish high-risk group and low-risk group. Then the GSEA enrichment pathway and immune cell infiltration of the two groups were compared. And combined with clinical variables, a predictive model was constructed. The time-dependent receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) curve were used to verify the stability and accuracy of the final predictive model, and a nomogram was then drawn.ResultsThe MEblack, MEpurple, and MEblue modules were significantly associated with the metastasis of UM patients (P value < 0.001, = 0.001, = 0.022, respectively). Four genes (UBXN2B, OTUD3, KAT8, LAMTOR2) were obtained by Pearson correlation analysis, weighted gene correlation network analysis (WGCNA), univariate Cox, and LASSO-Cox. And a novel prognostic risk score was established. Immune-related prognostic signature can well classify UM patients into high-risk and low-risk groups. Kaplan–Meier curve showed that the OS of high-risk patients was worse than that of low-risk patients. In addition, the risk score played an important role in evaluating the signaling pathway and immune cell infiltration of UM patients in high-risk and low-risk groups. Both the training set and validation set of the model showed good predictive accuracy in the degree of differentiation and calibration (e.g., 1-year overall survival: AUC = 0.930 (0.857–1.003)). Finally, a nomogram was established to serve in clinical practice.SignificanceUM key gene signature and prognosis predictive model might provide insights for further investigation of the pathogenesis and development of UM at the molecular level, and provide theoretical basis for determining new prognostic markers of UM and immunotherapy.

A stacking ensemble learning for Iberian pigs activity prediction: a time series forecasting approach

&lt;abstract&gt;&lt;p&gt;Automatic determination of abnormal animal activities can be helpful for the timely detection of signs of health and welfare problems. Usually, this problem is addressed as a classification problem, which typically requires manual annotation of behaviors. This manual annotation can introduce noise into the data and may not always be possible. This motivated us to address the problem as a time-series forecasting problem in which the activity of an animal can be predicted. In this work, different machine learning techniques were tested to obtain activity patterns for Iberian pigs. In particular, we propose a novel stacking ensemble learning approach that combines base learners with meta-learners to obtain the final predictive model. Results confirm the superior performance of the proposed method relative to the other tested strategies. We also explored the possibility of using predictive models trained on an animal to predict the activity of different animals on the same farm. As expected, the predictive performance degrades in this case, but it remains acceptable. The proposed method could be integrated into a monitoring system that may have the potential to transform the way farm animals are monitored, improving their health and welfare conditions, for example, by allowing the early detection of a possible health problem.&lt;/p&gt;&lt;/abstract&gt;

Developing a Prognostic Model for Primary Biliary Cholangitis Based on a Random Survival Forest Model.

Background: Primary biliary cholangitis (PBC) is a rare autoimmune liver disease with few effective treatments and a poor prognosis, and its incidence is on the rise. There is an urgent need for more targeted treatment strategies to accurately identify high-risk patients. The use of stochastic survival forest models in machine learning is an innovative approach to constructing a prognostic model for PBC that can improve the prognosis by identifying high-risk patients for targeted treatment. Method: Based on the inclusion and exclusion criteria, the clinical data and follow-up data of patients diagnosed with PBC-associated cirrhosis between January 2011 and December 2021 at Taizhou Hospital of Zhejiang Province were retrospectively collected and analyzed. Data analyses and random survival forest model construction were based on the R language. Result: Through a Cox univariate regression analysis of 90 included samples and 46 variables, 17 variables with p-values <0.1 were selected for initial model construction. The out-of-bag (OOB) performance error was 0.2094, and K-fold cross-validation yielded an internal validation C-index of 0.8182. Through model selection, cholinesterase, bile acid, the white blood cell count, total bilirubin, and albumin were chosen for the final predictive model, with a final OOB performance error of 0.2002 and C-index of 0.7805. Using the final model, patients were stratified into high- and low-risk groups, which showed significant differences with a P value <0.0001. The area under the curve was used to evaluate the predictive ability for patients in the first, third, and fifth years, with respective results of 0.9595, 0.8898, and 0.9088. Conclusion: The present study constructed a prognostic model for PBC-associated cirrhosis patients using a random survival forest model, which accurately stratified patients into low- and high-risk groups. Treatment strategies can thus be more targeted, leading to improved outcomes for high-risk patients.

Development and validation of a survival prediction model for patients with advanced non-small cell lung cancer based on LASSO regression.

A total of 523 patients were randomly divided into a training dataset (n=313) and a validation dataset (n=210). We conducted initial variable selection using three analytical methods: univariate Cox regression, LASSO regression, and random survival forest (RSF) analysis. Multivariate Cox regression was then performed on the variables selected by each method to construct the final predictive models. The optimal model was selected based on the highest bootstrap C-index observed in the validation dataset. Additionally, the predictive performance of the model was evaluated using time-dependent receiver operating characteristic (Time-ROC) curves, calibration plots, and decision curve analysis (DCA). The LASSO regression model, which included N stage, neutrophil-lymphocyte ratio (NLR), D-dimer, neuron-specific enolase (NSE), squamous cell carcinoma antigen (SCC), driver alterations, and first-line treatment, achieved a bootstrap C-index of 0.668 (95% CI: 0.626-0.722) in the validation dataset, the highest among the three models tested. The model demonstrated good discrimination in the validation dataset, with area under the ROC curve (AUC) values of 0.707 (95% CI: 0.633-0.781) for 1-year survival, 0.691 (95% CI: 0.616-0.765) for 2-year survival, and 0.696 (95% CI: 0.611-0.781) for 3-year survival predictions, respectively. Calibration plots indicated good agreement between predicted and observed survival probabilities. Decision curve analysis demonstrated that the model provides clinical benefit at a range of decision thresholds. The LASSO regression model exhibited robust performance in the validation dataset, predicting survival outcomes for patients with advanced NSCLC effectively. This model can assist clinicians in making more informed treatment decisions and provide a valuable tool for patient risk stratification and personalized management.

Combination of machine learning algorithms with natural language processing may increase the probability of bacteremia detection in the emergency department: A retrospective, big-data analysis of 94,482 patients.

Prompt diagnosis of bacteremia in the emergency department (ED) is of utmost importance. Nevertheless, the average time to first clinical laboratory finding range from 1 to 3 days. Alongside a myriad of scoring systems for occult bacteremia prediction, efforts for applying artificial intelligence (AI) in this realm are still preliminary. In the current study we combined an AI algorithm with a Natural Language Processing (NLP) algorithm that would potentially increase the yield extracted from clinical ED data. This study involved adult patients who visited our emergency department and at least one blood culture was taken to rule out bacteremia. Using both tabular and free text data, we built an ensemble model that leverages XGBoost for structured data, and logistic regression (LR) on a word-analysis technique called bag-of-words (BOW) Term Frequency-Inverse Document Frequency (TF-IDF), for textual data. All algorithms were designed in order to predict the risk for bacteremia with ED patients whose blood cultures were sent to the laboratory. The study cohort comprised 94,482 individuals, of whom 52% were males. The prevalence of bacteremia in the entire cohort was 9.7%. The model trained on the tabular data yielded an area under the curve (AUC) of 73.7% for XGBoost, while the LR that was trained on the free text achieved an AUC of 71.3%. After checking a range of weights, the best combination was for 55% weight on the XGBoost prediction and 45% weight on the LR prediction. The final model prediction yielded an AUC of 75.6%. Harnessing artificial intelligence to the task of bacteremia surveillance in the ED settings by a combination of both free text and tabular data analysis improved predictive performance compared to using tabular data alone. We recommend that future AI applications based on our findings should be assimilated into the clinical routines of ED physicians.

Prognostic factors and clinical nomogram for in-hospital mortality in traumatic brain injury

BackgroundTraumatic brain injury (TBI) is a major cause of death and functional disability in the general population. The nomogram is a clinical prediction tool that has been researched for a wide range of medical conditions. The purpose of this study was to identify prognostic factors associated with in-hospital mortality. The secondary objective was to develop a clinical nomogram for TBI patients' in-hospital mortality based on prognostic factors. MethodsA retrospective cohort study was conducted to analyze 14,075 TBI patients who were admitted to a tertiary hospital in southern Thailand. The total dataset was divided into the training and validation datasets. Several clinical characteristics and imaging findings were analyzed for in-hospital mortality in both univariate and multivariable analyses using the training dataset. Based on binary logistic regression, the nomogram was developed and internally validated using the final predictive model. Therefore, the predictive performances of the nomogram were estimated by the validation dataset. ResultsPrognostic factors associated with in-hospital mortality comprised age, hypotension, antiplatelet, Glasgow coma scale score, pupillary light reflex, basilar skull fracture, acute subdural hematoma, subarachnoid hemorrhage, midline shift, and basal cistern obliteration that were used for building nomogram. The predictive performance of the nomogram was estimated by the training dataset; the area under the receiver operating characteristic curve (AUC) was 0.981. In addition, the AUCs of bootstrapping and cross-validation methods were 0.980 and 0.981, respectively. For the temporal validation with an unseen dataset, the sensitivity, specificity, accuracy, and AUC of the nomogram were 0.90, 0.88, 0.88, and 0.89, respectively. ConclusionA nomogram developed from prognostic factors had excellent performance; thus, the tool had the potential to serve as a screening tool for prognostication in TBI patients. Furthermore, future research should involve geographic validation to examine the predictive performances of the clinical prediction tool.

Predictors of Reduced Left Ventricle Global Longitudinal Strain One Year After COVID-19 Pneumonia.

Aim To identify predictors of decreased left ventricular global longitudinal strain (LV GLS) using the method of speckle-tracking in gray scale one year after COVID-19-associated pneumonia in patients without ischemic heart disease (IHD), previous pulmonary embolism (PE), peripheral thrombosis, and atrial fibrillation (AF).Material and methods The study included 156 patients from the Prospective Registry of People After COVID-19-Associated Pneumonia, with optimal visualization quality according to echocardiography (EchoCG), without IHD, AF, history of pulmonary embolism (PE), and peripheral thrombosis. The patients underwent clinical examination in the hospital during the acute period and at 3 and 12 months after discharge from the hospital. To identify earlier predictors of LV GLS impairment, clinical, laboratory, and instrumental data obtained in the hospital and at 3 months of discharge were compared based on the presence of LV GLS impairment one year after discharge (43 patients with reduced LV GLS and 113 patients with normal LV GLS). An LV GLS value ≥18% was considered reduced.Results At 3 months after discharge from the hospital, LV GLS impairment was detected in 34 (21.8%) of 156 patients, and 12 months later, in 43 (27.6%; p=0.211) of 156 patients. In contrast to the group with normal LV GLS, the majority of the group with reduced LV GLS were men (74.4% vs. 37.2%; p=0.001). In this group, body mass index (BMI) was significantly higher (29.9±4.3 kg/m2 vs. 28.1±4.5 kg/m2; p=0.011), and biological (11.6% vs. 2.7%; p=0.024) and hormonal therapy was administered more frequently (38.1% vs. 22.3%; p=0.049). The final predictive model for LV GLS impairment included male gender (odds ratio (OR), 5.65; 95% confidence interval (CI), 1.22-14.37; p &lt;0.001), BMI (OR, 1.11; 95% CI, 1.01-1.23; p=0.040), left ventricular end-systolic volume index (LVESVI) (OR, 1.10; 95% CI, 1.01-1.22; p=0.046) and right ventricular outflow tract (RVOT) acceleration time (OR, 0.98; 95% CI, 0.95-0.99; p=0.027).Conclusion One year after COVID-19-associated pneumonia, a decrease in LV GLS was observed in 27.6% of patients without IHD, AF, history of PE, and peripheral thrombosis and was associated with male gender, increased BMI and LVESVI, and shortened RVOT acceleration time as measured 3 months after discharge from the hospital. The decrease in LV GLS one year after discharge was not associated with the severity of the disease, length of stay in the hospital, or biological and hormonal therapy.

Application of Data Fusion in Traditional Chinese Medicine: A Review.

Traditional Chinese medicine is characterized by numerous chemical constituents, complex components, and unpredictable interactions among constituents. Therefore, a single analytical technique is usually unable to obtain comprehensive chemical information. Data fusion is an information processing technology that can improve the accuracy of test results by fusing data from multiple devices, which has a broad application prospect by utilizing chemometrics methods, adopting low-level, mid-level, and high-level data fusion techniques, and establishing final classification or prediction models. This paper summarizes the current status of the application of data fusion strategies based on spectroscopy, mass spectrometry, chromatography, and sensor technologies in traditional Chinese medicine (TCM) in light of the latest research progress of data fusion technology at home and abroad. It also gives an outlook on the development of data fusion technology in TCM analysis to provide references for the research and development of TCM.

A nomogram model for predicting 5-year risk of prediabetes in Chinese adults

Early identification is crucial to effectively intervene in individuals at high risk of developing pre-diabetes. This study aimed to create a personalized nomogram to determine the 5-year risk of pre-diabetes among Chinese adults. This retrospective cohort study included 184,188 participants without prediabetes at baseline. Training cohorts (92,177) and validation cohorts (92,011) were randomly assigned (92,011). We compared five prediction models on the training cohorts: full cox proportional hazards model, stepwise cox proportional hazards model, multivariable fractional polynomials (MFP), machine learning, and least absolute shrinkage and selection operator (LASSO) models. At the same time, we validated the above five models on the validation set. And we chose the LASSO model as the final risk prediction model for prediabetes. We presented the model with a nomogram. The model's performance was evaluated in terms of its discriminative ability, clinical utility, and calibration using the area under the receiver operating characteristic (ROC) curve, decision curve analysis, and calibration analysis on the training cohorts. Simultaneously, we also evaluated the above nomogram on the validation set. The 5-year incidence of prediabetes was 10.70% and 10.69% in the training and validation cohort, respectively. We developed a simple nomogram that predicted the risk of prediabetes by using the parameters of age, body mass index (BMI), fasting plasma glucose (FBG), triglycerides (TG), systolic blood pressure (SBP), and serum creatinine (Scr). The nomogram's area under the receiver operating characteristic curve (AUC) was 0.7341 (95% CI 0.7290–0.7392) for the training cohort and 0.7336 (95% CI 0.7285–0.7387) for the validation cohort, indicating good discriminative ability. The calibration curve showed a perfect fit between the predicted prediabetes risk and the observed prediabetes risk. An analysis of the decision curve presented the clinical application of the nomogram, with alternative threshold probability spectrums being presented as well. A personalized prediabetes prediction nomogram was developed and validated among Chinese adults, identifying high-risk individuals. Doctors and others can easily and efficiently use our prediabetes prediction model when assessing prediabetes risk.

Development and internal validation of a clinical prediction model for spontaneous abortion risk in early pregnancy

ObjectiveThis study aimed to develop and internally validate a prediction model for estimating the risk of spontaneous abortion in early pregnancy. MethodsThis prospective cohort study included 9,895 pregnant women who received prenatal care at a maternal health facility in China from January 2021 to December 2022. Data on demographics, medical history, lifestyle factors, and mental health were collected. A multivariable logistic regression analysis was performed to develop the prediction model with spontaneous abortion as the outcome. The model was internally validated using bootstrapping techniques, and its discrimination and calibration were assessed. ResultsThe spontaneous abortion rate was 5.95% (589/9,895) 1. The final prediction model included nine variables: maternal age, history of embryonic arrest, thyroid dysfunction, polycystic ovary syndrome, assisted reproduction, exposure to pollution, recent home renovation, depression score, and stress score 1. The model showed good discrimination with a C-statistic of 0.88 (95% CI 0.87‒0.90) 1, and its calibration was adequate based on the Hosmer-Lemeshow test (p = 0.27). ConclusionsThe prediction model demonstrated good performance in estimating spontaneous abortion risk in early pregnancy based on demographic, clinical, and psychosocial factors. Further external validation is recommended before clinical application.

Development and Validation of a Prediction Model for Failure of the Transfemoral Approach of Endovascular Treatment for Large Vessel Occlusion Acute Ischemic Stroke

Introduction: Extracranial vascular characteristics determine the accessibility of the large vessel intracranial occlusion for endovascular treatment (EVT) in acute ischemic stroke. We developed and validated a prediction model for failure of the transfemoral approach to aid clinical decision-making regarding EVT. Methods: A prediction model was developed from data of patients included in the Dutch multicenter MR CLEAN Registry (March 18, 2014, until June 15, 2016) with penalized logistic regression. Predictor variables were available prior to the EVT procedure and included age, hypertension, and extracranial vascular characteristics assessed on baseline CTA. The prediction model was internally validated, temporally validated within a second MR CLEAN Registry cohort (June 15, 2016, until November 1, 2017), and updated by re-estimating the coefficients using the combined cohort. Results: Failure of the transfemoral approach occurred in 7% of patients, in both cohorts (derivation cohort: n = 887, median age 71 years, interquartile range [IQR] 60–80, 52% men; validation cohort: n = 1,111, median age 73 years, IQR: 62–81, 51% men). The prediction model had a c-statistic of 0.81 (95% CI: 0.76–0.86) in the derivation cohort, 0.69 (95% CI: 0.62–0.75) at temporal validation, and 0.75 (95% CI: 0.71–0.79) in the final prediction model, with the following penalized β-coefficients for predictor age (per decade): 0.26, hypertension: −0.16, severe aortic arch elongation: 1.45, bovine aortic arch: 0.44, elongation of the supra-aortic arteries: 0.72, cervical ICA elongation: 0.44, and high-grade stenosis of the cervical ICA: 0.78. Conclusion: Our prediction model showed good performance for prediction of failure to reach the intracranial occlusion by the transfemoral approach.

A robust ensemble surrogate model and its application in the in situ data modelling and analysis of a combine harvester

In this article, a robust ensemble model is proposed based on extended adaptive hybrid functions and fuzzy clustering. In the outlier detection stage, each sample is assigned memberships to judge whether it is an outlier or not, where the memberships are determined based on the responses of the ensemble surrogate model of each cluster. Then, the detected outliers are removed from the initial training samples, and the final prediction model is constructed based on the remaining normal samples. The results of numerical problems and the in-situ dataset from a combine harvester show that the proposed model can provide accurate detection results for outliers and accurate prediction results for new points. The sensitivity analysis based on the proposed robust ensemble model indicates that the angle of guide plate, the open rate of cleaning fan, and the height of header have a greater effect on the cleaning loss of combine harvester.

Predicting long-term survival after de novo cardioverter-defibrillator implantation for primary prevention: A population based study

BackgroundImplantable cardioverter-defibrillators (ICDs) reduce the risk of sudden cardiac death in patients with left ventricular dysfunction. While short-term mortality benefit of ICD insertion has been established in landmark randomized controlled trials, little is known about the long-term outcomes of patients with ICDs in clinical practice. In this paper, we describe the long-term survival of patients following de novo ICD implantation for primary prevention in clinical practice and determine the factors which help predict survival after ICD implant. MethodsRetrospective population-based study of all patients receiving a de novo ICD for primary prevention in Ontario, Canada from 2007 to 2011 using the Ontario ICD Database housed within ICES. Simple random selection was used to split the population into a derivation and internal validation cohort in a ratio of 2:1. Cox proportional hazards regression was used to determine predictors of interest and predict 10-year survival, model performance was assessed using calibration and validation. ResultsIn the derivation cohort (n = 3399), mean age was 65.3 years (standard deviation [SD] = 11.0), 664 patients were female (19.5 %) and 2344 patients (69.0 %) had ischemic cardiomyopathy. Ten year survival was 45.7 % (95 % confidence interval [CI] 44.0 %–47.4 %). The final prediction model included age, sex, disease factors (ischemic vs nonischemic cardiomyopathy, left ventricular ejection fraction) and patient factors (symptoms, comorbidities), and biomarkers at the time of ICD assessment. This model had good discrimination and calibration in derivation (0.79, 95 % CI 0.77, 0.81) and validation samples (0.78, 95 % CI 0.76, 0.79). ConclusionsA combination of demographic and clinical factors determined at baseline can be used to predict 10-year survival in patients with implantable cardioverter-defibrillators with good accuracy. Our findings help to identify individuals at risk of long-term mortality and may be useful in targeting future prevention strategies to enhance longevity in this high-risk population.

Predictors of clinical worsening during a discontinuation trial of serotonin reuptake inhibitors for obsessive compulsive disorder

ObjectiveTo explore predictors and moderators of clinical worsening during a double-blind trial in which patients with obsessive-compulsive disorder (OCD) were randomized to either continue or discontinue their Serotonin Reuptake Inhibitor (SRI) medication after achieving wellness from the addition of exposure and response prevention (EX/RP) therapy. MethodThe data came from a double-blind discontinuation trial that included N = 101 participants, 35 of whom were removed from the study due to clinical worsening. We first used LASSO logistic regression to identify which of the 34 potential baseline variables of interest (including demographics, diagnoses, other relevant clinical constructs, and specific genotypes), might moderate or predict this clinical worsening. Then logistic regression was used to examine which of these identified variables were significantly related to later clinical worsening. We verified the validity of our final prediction model using k-fold cross-validation. ResultsThere was one significant predictor of clinical worsening: In both groups, those with more past diagnoses had a greater likelihood of clinical worsening (p = .015). There were several moderators. Rates of clinical worsening were higher in the Discontinuation group compared to the Continuation group for participants who were taking a shorter half-life SRI (p = .044), were female (p = .022), had higher baseline levels of maladaptive metacognitions (p < .001), had fewer sleep problems at baseline (p = .001), and/or had more years of education (p < .001). ConclusionsOur results identified several factors that may predict the development of clinical worsening in OCD patients discontinuing SRI medication following successful EX/RP treatment.

Development and validation of a risk prediction model for pulmonary tuberculosis among presumptive tuberculosis cases in Ethiopia

BackgroundEarly diagnosis and treatment of tuberculosis (TB) is one of the key strategies to achieve the WHO End TB targets. This study aimed to develop and validate a simple, convenient...

A field-validated ensemble species distribution model of Eriogonum pelinophilum, an endangered subshrub in Colorado, USA.

Understanding the suitable habitat of endangered species is crucial for agencies such as the Bureau of Land Management to plan management and conservation. However, few species distribution models are directly validated, potentially limiting their application in management. In preparation for a Species Status Assessment of clay-loving wild buckwheat (Eriogonum pelinophilum), an endangered subshrub found in southwest Colorado, we ran a series of species distribution models to estimate the species' potential occupied habitat and validated these models in the field. A 1-meter resolution digital elevation model derived from LiDAR and a high-resolution geology mapping helped identify biologically relevant characteristics of the species' habitat. We employed a weighted ensemble model based on two Random Forest and one Boosted Regression Tree model, and discrimination performance of the ensemble model was high (AUC-PR = 0.793). We then conducted a systematic field survey of model habitat suitability predictions, during which we discovered 55 new subpopulations of the species and demonstrated that new species observations were strongly associated with model predictions (p < .0001, Cliff's delta = 0.575). We further refined our original models by incorporating the additional species occurrences collected in the field survey, a new explanatory variable, and a more diverse set of models. These iterative changes marginally improved performance of the ensemble model (AUC-PR = 0.825). Direct validation of species distribution models is extremely rare, and our field survey provides strong validation of our model results. This helps increase confidence to utilize predictions in planning. The final model predictions greatly improve the Bureau of Land Management's understanding of the species' habitat and increase our ability to consider potential habitat in planning land use activities such as road development and travel management.

Prediction of disease recurrence or residual disease after primary endoscopic resection of pT1 colorectal cancer—results from a large nationwide Danish study

PurposeRisk assessment of disease recurrence in pT1 colorectal cancer is crucial in order to select the appropriate treatment strategy. The study aimed to develop a prediction model, based on histopathological data, for the probability of disease recurrence and residual disease in patients with pT1 colorectal cancer.MethodsThe model dataset consisted of 558 patients with pT1 CRC who had undergone endoscopic resection only (n = 339) or endoscopic resection followed by subsequent bowel resection (n = 219). Tissue blocks and slides were retrieved from Pathology Departments from all regions in Denmark. All original slides were evaluated by one experienced gastrointestinal pathologist (TPK). New sections were cut and stained for haematoxylin and eosin (HE) and immunohistochemical markers. Missing values were multiple imputed. A logistic regression model with backward elimination was used to construct the prediction model.ResultsThe final prediction model for disease recurrence demonstrated good performance with AUC of 0.75 [95% CI 0.72–0.78], HL chi-squared test of 0.59 and scaled Brier score of 10%. The final prediction model for residual disease demonstrated medium performance with an AUC of 0.68 [0.63–0.72].ConclusionWe developed a prediction model for the probability of disease recurrence in pT1 CRC with good performance and calibration based on histopathological data. Together with lymphatic and venous invasion, an involved resection margin (0 mm) as opposed to a margin of ≤ 1 mm was an independent risk factor for both disease recurrence and residual disease.

Day 4 and day 0 neutrophil-to-lymphocyte ratios as predictors of treatment failure with single-dose methotrexate for ectopic pregnancies.

To evaluate changes in the neutrophil-to-lymphocyte ratio (NLR) between day 4 and day 0 in ectopic pregnancy (EP) patients treated with single-dose methotrexate (MTX) and investigate its predictive value for treatment outcome. A total of 406 EP patients receiving single-dose MTX therapy at Shanghai First Maternity and Infant Hospital from January 10, 2013 to September 30, 2019 were studied. A multivariate model was constructed to predict treatment outcome. Among the 406 patients, 281 were treated successfully. Treatment success declined significantly when NLR decreased by less than 23% (74.8% vs 58.5%, P = 0.004). Multivariate regression analysis identified NLR reduction of less than 23% on day 4 (odds ratio [OR] 2.09, 95% confidence interval [CI] 1.27-3.44), a human chorionic gonadotropin (hCG) decrease of 15% or less (OR 3.17, 95% CI 1.62-6.34), and an hCG increase of more than 15% on day 4 (OR 5.47, 95% CI 3.05-10.22) as independent risk factors for single-dose MTX treatment failure. The final predictive model had a sensitivity of 0.768 and a specificity of 0.569, using a cut-off value of 3. The area under the receiver operating characteristic curve was 0.712. Patients with a predictive score of ≥3 were more likely to fail single-dose MTX therapy. The present study concluded that an NLR decrease of less than 23% on day 4, a plateau or increase in serum hCG on day 4, and an hCG value greater than 1000 mIU/mL on day 0 were predictors of single-dose MTX treatment failure in EP patients.

Risk Stratification of Patients with RUNX1-mutated Acute Myeloid Leukemia

Mutations in RUNX1 ( RUNX1mut) occur in ~15% of intensively treated AML cases. RUNX1mut have no specific hotspot and various types of alteration are observed. The European LeukemiaNet (ELN) risk stratification assigns adverse prognosis to RUNX1mut if they do not co-occur with favorable-risk genotypes. Considering the biological complexity of RUNX1 it seems implausible that all alterations have similar consequences. Using clinical and genetic variables, we developed a prognostic risk stratification model for ELN adverse-risk RUNX1mut AML patients. We combined data from five groups, totaling 609 patients with intensively treated RUNX1mut AML, to develop the model. Our training set included 448 patients treated on trials of the AML Cooperative Group (AMLCG; Herold et al, Leukemia, 2020; (n=178)), AML Study Group (Gerstung et al, NEJM, 2016; (n=116)) and Study Alliance Leukemia (n=154). Patients from the Munich Leukemia Laboratory (MLL; (n=107)) and of the Alliance group (trials NCT00048958, NCT00899223, NCT00900224; Support: U10CA180821, U10CA180882, U24CA196171; https://acknowledgments.alliancefound.org; (n=54)) served as independent validation cohorts. Additionally, 955 patients without RUNX1mut treated on AMLCG trials served as controls. Patients with t(15;17), prior treatment, or RUNX1mut with co-occurring favorable-risk genotypes according to ELN 2017 were excluded. Differences between RUNX1mut patients and controls were investigated using univariate logistic regression. Testing was performed using likelihood ratio tests and adjusted for study group. Univariate analyses were adjusted for multiple testing using the Benjamini-Hochberg procedure. We obtained risk prediction models using multivariate Cox regression. Missing values were imputed using the missForest approach. Model selection was performed using forward selection based on the Bayesian information criterion. Cut-offs were based on the 25 th- 50 th- and 75 th-percentile score values obtained in the training data. Performance was evaluated using Kaplan-Meier curves. For internal validation Harrell's C index was estimated using cross-study validation. For external validation, the final risk prediction models were separately applied to the external datasets. RUNX1mut were more common in older, male patients and sAML (table). White blood cells, lactate dehydrogenase and bone marrow blasts were lower in RUNX1mut patients. Mutations in several myelodysplasia-related genes were enriched in RUNX1mut patients ( ASXL1, BCOR, BCORL1, EZH2, KMT2A, PHF6, and STAG2, SF3B1, SRSF2, and U2AF1), whereas DNMT3A, NPM1 and FLT3 were more frequently altered in controls. A strong association with mutations of the splicing factor complex was identified (49% vs. 13%, p&amp;lt;0.0001). Contradicting previous reports, we found no association with IDH mutations. The risk prediction score we obtained for OS is as follows: 0.03054 x age (y) + 0.74996 x adverse MRC + 0.43779 x FLT3-ITD + 0.00317 x WBC count (10^9/L) - 0.00158 x platelet count (10^9/L) + 0.37401 x NRAS-mutation, where the obtained cut-off values are: &amp;lt;1.592 (low risk); 1.592 to 2.303 (moderate risk) &amp;gt;2.303 (high risk). Binary variables are coded as 0 or 1. Harrell's C index estimated using internal validation was 0.6. Kaplan-Meier curves estimated using the training set suggest strong differences in survival between the risk categories. Median overall survival (OS) was 2.5, 1.0 and 0.6 years for low-, intermediate-, and high-risk. External validation using the Alliance cohort shows similar results (Figure). Results obtained for the MLL cohort show smaller differences. However, we still observe clear separation of risk groups with a significant difference between low- and high-risk groups (adjusted p-value: 0.0266). Scores for relapse-free survival (RFS) as well as for OS and RFS censored for allogeneic transplant show similar results. We analyzed a large collection of intensively treated RUNX1mut AML patients and observed heterogenous outcomes that could be predicted by applying few variables (age, MRC-score, FLT3/NRAS mutation-status, and WBC/platelet count). The OS of RUNX1mut high-risk patients is discouraging, highlighting the unmet need of these patients. In addition, our work demonstrates that ELN risk groups can be further stratified and that integrated approaches using routinely available variables can further advance risk prediction.