A prediction model for chemotherapy-associated thrombocytopenia in cancer patients

2006 ◽  
Vol 24 (18_suppl) ◽  
pp. 8616-8616 ◽  
Author(s):  
N. M. Kuderer ◽  
C. W. Francis ◽  
J. Crawford ◽  
D. C. Dale ◽  
D. A. Wolff ◽  
...  
Keyword(s):  
Risk Factors ◽  
Prediction Model ◽  
Likelihood Ratio ◽  
Test Performance ◽  
Dose Intensity ◽  
High Specificity ◽  
Performance Characteristics ◽  
Multivariate Logistic Regression Model ◽  
Model Based ◽  
The Impact

8616 Background: Thrombocytopenia (TP) can lead to serious complications, however, little is known about the incidence and risk factors for chemotherapy-associated TP. A prospective, nationwide cohort study was undertaken to better define the impact of TP in cancer treatment. Methods: 2,842 patients with cancer of the breast, lung, colon, ovary or lymphoma initiating a new chemotherapy regimen have been prospectively enrolled at 115 randomly selected US community oncology practices between 2002 and 2005. Risk factors for chemotherapy-associated TP were identified, a multivariate logistic regression model based on pretreatment characteristics was developed, and test performance characteristics were estimated. Results: Over a median of 3 cycles of chemotherapy, minimum recorded platelet counts were: ≥150K in 53% of patients; 100–150K in 26%; 75–100K in 8%; 50–75K in 6% and <50K in 7%. Significant independent predictive factors for platelets <75K include type of cancer (P<.0001), type of chemotherapy including gemcitabine-based (P<.0001), anthracycline-based (P<.0001) and platinum-based (P<.0001) regimens, prior chemotherapy (P<.0001) or surgery (P=.005), age (P=.015), Caucasian ethnicity (P=.022), body surface area (P=.0001), planned relative dose intensity ≥85% (P=.082), diabetes (P=.018), pulmonary disease (P=.011), abnormal baseline platelets (P<.0001), hematocrit (P=0.030), alkaline phosphatase (P=.072) or albumin (P=.017). Model fit was good (Chi-square, P<.0001), R2 = 0.735 and c-statistic = 0.816 [95% CI: 0.792–0.840, P<.0001]. Model test performance characteristics [95% CI] at a ≥20% risk of TP include: sensitivity 56% [51–61]; specificity 88% [87–89]; likelihood ratio positive 4.63 [4.02–5.33]; likelihood ratio negative 0.50 [0.45–0.57]; and diagnostic odds ratio 9.22 [7.23–11.75]. Validation of the model is underway. Conclusions: This prediction model based on pretreatment factors identifies with high specificity patients at risk for clinically important chemotherapy-associated thrombocytopenia early in the treatment course. It may provide a valuable tool for guiding chemotherapy and new supportive care measures. [Table: see text]

scholarly journals Risk factors for pegylated liposomal doxorubicin-induced moderate to severe hand-foot syndrome in breast cancer patients: assessment of baseline clinical parameters

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Guohua Liang ◽  
Wenjie Ma ◽  
Yanfang Zhao ◽  
Eryu Liu ◽  
Xiaoyu Shan ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Risk Factors ◽  
Prediction Model ◽  
Cancer Patients ◽  
Blood Circulation ◽  
Pegylated Liposomal Doxorubicin ◽  
Dose Intensity ◽  
Breast Cancer Patients ◽  
Hand Foot Syndrome ◽  
Peripheral Blood Circulation

Abstract Background Hand-foot syndrome (HFS) is a side effect of skin related to pegylated liposomal doxorubicin (PLD) application. Moderate to severe hand-foot syndrome (MSHFS) might have a serious impact on patients’ quality of life and treatment. However, information on risk factors for the development of MSHFS is still limited. To analyze the risk factors for PLD-induced MSHFS in breast cancer patients and constructed a logistic regression prediction model. Methods We conducted a retrospective analysis of breast cancer patients who were treated with a PLD regimen in the Tumor Hospital of Harbin Medical University from January 2017 to August 2019. A total of 26 factors were collected from electronic medical records. Patients were divided into MSHFS (HFS > grade 1) and NMHFS (HFS ≤ grade 1) groups according to the NCI classification. Statistical analysis of these factors and the construction of a logistic regression prediction model based on risk factors. Results A total of 44.7% (206/461) of patients developed MSHFS. The BMI, dose intensity, and baseline Alanine aminotransferase (ALT) and Aspartate aminotransferase (AST) levels in the MSHFS group, as well as good peripheral blood circulation, excessive sweat excretion, history of gallstones, and tumour- and HER2-positive percentages, were all higher than those in the NMHFS group (P < 0.05). The model for predicting the occurrence of MSHFS was P = 1/1 + exp. (11.138–0.110*BMI-0.234*dose intensity-0.018*baseline ALT+ 0.025*baseline AST-1.225*gallstone history-0.681* peripheral blood circulation-1.073*sweat excretion-0.364*with or without tumor-0.680*HER-2). The accuracy of the model was 72.5%, AUC = 0.791, and Hosmer-Lemeshow fit test P = 0.114 > 0.05. Conclusions Nearly half of the patients developed MSHFS. The constructed prediction model may be valuable for predicting the occurrence of MSHFS in patients.

scholarly journals Quantitative Thresholds Enable Accurate Identification ofClostridium difficileInfection by the Luminex xTAG Gastrointestinal Pathogen Panel

2018 ◽  
Vol 56 (6) ◽  
Author(s):  
Sixto M. Leal ◽  
Elena B. Popowitch ◽  
Kara J. Levinson ◽  
Teny M. John ◽  
Bethany Lehman ◽  
...  
Keyword(s):  
Test Performance ◽  
Predictive Value ◽  
High Specificity ◽  
Clinical Suspicion ◽  
Performance Characteristics ◽  
Accurate Identification ◽  
Data Set ◽  
Content Type ◽  
Molecular Assays ◽  
Stool Samples

ABSTRACTClostridium difficilecolonizes the gastrointestinal (GI) tract, resulting in either asymptomatic carriage or a spectrum of diarrheal illness. If clinical suspicion forC. difficileis low, stool samples are often submitted for analysis by multiplex molecular assays capable of detecting multiple GI pathogens, and some institutions do not report this organism due to concerns for high false-positive rates. Since clinical disease correlates with organism burden and molecular assays yield quantitative data, we hypothesized that numerical cutoffs could be utilized to improve the specificity of the Luminex xTAG GI pathogen panel (GPP) forC. difficileinfection. Analysis of cotested liquid stool samples (n= 1,105) identified a GPP median fluorescence intensity (MFI) value cutoff of ≥1,200 to be predictive of two-step algorithm (2-SA; 96.4% concordance) and toxin enzyme immunoassay (EIA) positivity. Application of this cutoff to a second cotested data set (n= 1,428) yielded 96.5% concordance. To determine test performance characteristics, concordant results were deemed positive or negative, and discordant results were adjudicated via chart review. Test performance characteristics for the MFI cutoff of ≥150 (standard), MFI cutoff of ≥1,200, and 2-SA were as follows (respectively): concordance, 95, 96, and 97%; sensitivity, 93, 78, and 90%; specificity, 95, 98, and 98%; positive predictive value, 67, 82, and 81%;, and negative predictive value, 99, 98, and 99%. To capture the high sensitivity for organism detection (MFI of ≥150) and high specificity for active infection (MFI of ≥1,200), we developed and applied a reporting algorithm to interpret GPP data from patients (n= 563) with clinician orders only for syndromic panel testing, thus enabling accurate reporting ofC. difficilefor 95% of samples (514 negative and 5 true positives) irrespective of initial clinical suspicion and without the need for additional testing.

Establishment of Prediction Models for venous thromboembolism in non-oncological urological inpatients--a single center experience

2020 ◽  
Author(s):  
Kaixuan Li ◽  
Haozhen Li ◽  
Quan Zhu ◽  
Ziqiang Wu ◽  
Zhao Wang ◽  
...  
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Venous Thromboembolism ◽  
Prediction Model ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Prediction Models ◽  
Predictive Ability ◽  
Multivariate Logistic Regression Model ◽  
Single Center Experience

Abstract Background To establish prediction models for venous thromboembolism (VTE) in non-oncological urological inpatients. Methods A retrospective analysis of 1453 inpatients was carried out and the risk factors for VTE had been clarified our previous studies. Results Risk factors included the following 5 factors: presence of previous VTE (X1), presence of anticoagulants or anti-platelet agents treatment before admission (X2), D-dimer value (≥ 0.89 µg/ml, X3), presence of lower extremity swelling (X4), presence of chest symptoms (X5). The logistic regression model is Logit (P) = − 5.970 + 2.882 * X1 + 2.588 * X2 + 3.141 * X3 + 1.794 * X4 + 3.553 * X5. When widened the p value to not exceeding 0.1 in multivariate logistic regression model, two addition risk factors were enrolled: Caprini score (≥ 5, X6), presence of complications (X7). The prediction model turns into Logit (P) = − 6.433 + 2.696 * X1 + 2.507 * X2 + 2.817 * X3 + 1.597 * X4 + 3.524 * X5 + 0.886 * X6 + 0.963 * X7. Internal verification results suggest both two models have a good predictive ability, but the prediction accuracy turns to be both only 43.0% when taking the additional 291 inpatients’ data in the two models. Conclusion We built two similar novel prediction models to predict VTE in non-oncological urological inpatients. Trial registration: This trial was retrospectively registered at http://www.chictr.org.cn/index.aspx under the public title“The incidence, risk factors and establishment of prediction model for VTE n urological inpatients” with a code ChiCTR1900027180 on November 3, 2019. (Specific URL to the registration web page: http://www.chictr.org.cn/showproj.aspx?proj=44677).

A Prospective Risk Model for Neutropenic Complications in Patients with Malignant Lymphoma.

Blood ◽  
2005 ◽  
Vol 106 (11) ◽  
pp. 3328-3328
Author(s):  
Gary H. Lyman ◽  
Jeffrey Crawford ◽  
Debra Wolff ◽  
Eva Culakova ◽  
Marek S. Poniewierski ◽  
...  
Keyword(s):  
Febrile Neutropenia ◽  
Malignant Lymphoma ◽  
Likelihood Ratio ◽  
Cancer Chemotherapy ◽  
Test Performance ◽  
Predictive Value ◽  
Risk Model ◽  
Chemotherapy Regimen ◽  
Performance Characteristics ◽  
Increased Risk

Abstract Background: Myelosuppression including severe and febrile neutropenia continues to represent a major cause of dose-limiting toxicity of cancer chemotherapy. Neutropenic complications in cycle 1 have been shown to frequently lead to reduced dose intensity or addition of a myeloid growth factor. A prospective, nationwide study was undertaken to develop and validate risk models for first cycle neutropenic events associated with cancer chemotherapy. Methods: Patients with malignant lymphoma initiating a new chemotherapy regimen have been prospectively registered at 115 randomly selected practice sites. Data on at least one cycle of chemotherapy were available on 357 patients including 56 with Hodgkin’s disease and 301 with non-Hodgkin’s lymphoma. A logistic regression model for first cycle neutropenic events based on pretreatment characteristics was developed and predictive test performance characteristics examined. Results: Severe or febrile neutropenia occurred in 81 (22.7%) of patients in cycle 1. Two-thirds of patients with one or more neutropenic events experienced their initial event in cycle 1. Significant independent pretreatment predictive factors for first cycle neutropenic complications were: history of renal disease (OR=33.15, P=.011) or recent infection (OR=12.41, P=.035), Caucasian (OR=4.13, P=.053), use of an anthracycline-based chemotherapy regimen (OR=6.9, P&lt;.001), baseline absolute neutrophil count (OR=0.95, P&lt;.001) and lymphocyte count (OR=0.95, P&lt;.001), anemia (OR=2.14, P=.043), elevated lactate dehydrogenase (OR=2.0, P=.040) and elevated bilirubin (OR=2.25, P=.051). Model fit was excellent (P&lt;.001), R2= 0.503 and c-statistic = 0.769 [95% CL: .71–.83, P&lt;.0001]. Individual predicted risk of cycle 1 events based on the model ranged from 0 to 96% with mean and median probabilities of 0.23 and 0.21, respectively. Two-thirds of patients were classified as high risk with mean risk scores in high and low risk subjects of 32.0% and 5.6%, respectively. Model test performance characteristics [±95% CL] included: sensitivity: 92% [84–96]; specificity: 40% [34–46]; likelihood ratio positive: 1.53 [1.36–1.73]; likelihood ratio negative: 0.19 [0.09–0.42]; positive predictive value: 32% [26–38]; negative predictive value: 94% [88–97] and diagnostic odds ratio: 7.92 [3.32–18.91]. Discussion: The risk model identified lymphoma patients at increased risk for first cycle neutropenic complications using common clinical parameters. Validation of the model in a separate population of patients is in progress.

A Risk Model for Chemotherapy-Induced Anemia (CIA) in Cancer Patients.

Blood ◽  
2005 ◽  
Vol 106 (11) ◽  
pp. 754-754
Author(s):  
Gary H. Lyman ◽  
Brandon McMahon ◽  
Nicole M. Kuderer ◽  
Jeffrey Crawford ◽  
Debra Wolff ◽  
...  
Keyword(s):  
Cancer Patients ◽  
Likelihood Ratio ◽  
Test Performance ◽  
Predictive Value ◽  
Risk Model ◽  
Performance Status ◽  
Low Risk ◽  
Performance Characteristics ◽  
Hematological Toxicity ◽  
Predictive Test

Abstract Background: Anemia represents the most common hematological toxicity in cancer patients receiving systemic chemotherapy and is associated with considerable morbidity and cost (Lyman‚ Value in Health 2005). Current ASH/ASCO guidelines call for intervention at a hemoglobin (Hgb) &lt;10 gm/dl. Treatment options include transfusion or administration of an erythropoietic-stimulating protein (ESP). A recent meta-analysis demonstrated the clinical value of early versus late intervention with an ESP (Lyman‚ Cancer‚ 2005 in press). An accurate and valid risk model for CIA is needed to select patients for ESP treatment early in the course of chemotherapy when it can be most effective. Methods: More than 3‚000 patients with cancer of the breast‚ lung‚ colon and ovary or malignant lymphoma initiating a new chemotherapy regimen have been prospectively registered at 115 randomly selected U.S. practice sites. Data on at least one cycle of chemotherapy were available on 2‚842 patients. A logistic regression model for Hgb &lt;10 gm/dl based on pretreatment characteristics was developed and predictive test performance characteristics examined. Results: Over a median of three cycles of chemotherapy, Hgb &lt;10 gm/dl was reported one or more times in 817 (28.7%) patients. Significant independent predictive factors for Hgb &lt;10 gm/dl include: history of peptic ulcer (OR=1.90; P=.015), myocardial infarction (OR=1.94; P=.009), or congestive heart failure (OR=2.13; P=.017), increasing age (OR=1.02; P=.002), female gender (OR=2.40; P&lt;.001), ECOG performance status (OR=1.24; P=.002), Charlson Comorbidity Index (OR=1.06, P=.002), body surface area (OR=3.75, P&lt;.001), low baseline hemoglobin (OR=1.95, P&lt;.001), pretreatment hematocrit (OR=.85, P&lt;.001), and glomerular filtration rate (OR=0.99, P=.027), and regimens containing anthracyclines (OR=3.21, P&lt;.001), cisplatinum (OR=3.86, P&lt;.001) or carboplatinum (OR=2.71, P&lt;.001). Model fit was excellent (P&lt;.001), R2=0.455 and c-statistic = 0.775 [95% CL: .76–.79, P&lt;.0001]. Individual predicted risk of Hgb &lt;10 gm/dl based on the model ranged from 0 to 98% with mean and median probabilities of 0.28 and 0.22, respectively. Based on a risk cutpoint of 20%, 1,541 patients (55%) were classified as high risk and 1,282 as low risk. The average risks of Hgb &lt;10 gm/dl during chemotherapy in high and low risk subjects were 43% and 12%, respectively. Model test performance characteristics [±95% CL] included: sensitivity: 81% [78–84]; specificity: 56% [54–58]; likelihood ratio positive: 1.85 [1.74–1.96]; likelihood ratio negative: 0.34 [0.29–0.39]; positive predictive value: 43% [40–45]; negative predictive value: 88% [86–90] and diagnostic odds ratio: 5.47 [4.50–6.66]. Conclusions: This risk model identified cancer patients initiating chemotherapy who are at risk for clinically significant anemia using common clinical parameters. Validation of the model in a separate population of patients is in progress.

scholarly journals Development and External Validation of a Melanoma Risk Prediction Model Based on Self-assessed Risk Factors

2016 ◽  
Vol 152 (8) ◽  
pp. 889 ◽  
Author(s):  
Kylie Vuong ◽  
Bruce K. Armstrong ◽  
Elisabete Weiderpass ◽  
Eiliv Lund ◽  
Hans-Olov Adami ◽  
...  
Keyword(s):  
Risk Factors ◽  
Prediction Model ◽  
Risk Prediction ◽  
External Validation ◽  
Risk Prediction Model ◽  
Melanoma Risk ◽  
Model Based

scholarly journals Risk factors and in-hospital mortality of postoperative hyperlactatemia in patients after acute type A aortic dissection surgery

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Su Wang ◽  
Dashuai Wang ◽  
Xiaofan Huang ◽  
Hongfei Wang ◽  
Sheng Le ◽  
...  
Keyword(s):  
Risk Factors ◽  
Aortic Dissection ◽  
Hospital Mortality ◽  
Prediction Model ◽  
Clinical Utility ◽  
Type A ◽  
Acute Type ◽  
Goodness Of Fit Test ◽  
Lactate Levels ◽  
The Impact

Abstract Background Hyperlactatemia may be caused by increased production due to tissue hypoxia or non-hypoxia. The aim of this study was first to identify risk factors for postoperative hyperlactatemia (POHL) after Stanford type A acute aortic dissection surgery (AADS) and construct a predictive model, and second to evaluate the impact of POHL on prognosis. Methods This retrospective study involved patients undergoing AADS from January 2016 to December 2019 in Wuhan Union Hospital. Multivariate logistic regression analysis was performed to identify independent risk factors for POHL. A nomogram predicting POHL was established based on these factors and was validated in the original dataset. The receiver operating characteristic curve was drawn to assess the ability of postoperative lactate levels to predict the in-hospital mortality. Results A total of 188 patients developed POHL after AADS (38.6%). Male gender, surgery history, red blood cell transfusion and cardiopulmonary bypass time were identified as independent predictors. The C-index of the prediction model for POHL was 0.72, indicating reasonable discrimination. The model was well calibrated by visual inspection and goodness-of-fit test (Hosmer–Lemeshow χ2 = 10.25, P = 0.25). Decision and clinical impact curves of the model showed good clinical utility. The overall in-hospital mortality rate was 10.1%. Postoperative lactate levels showed a moderate predictive power for postoperative in-hospital mortality (C-index: 0.72). Conclusion We developed and validated a prediction model for POHL in patients undergoing AADS, which may have clinical utility in personal risk evaluation and preventive interventions. The POHL could be a good predictor for in-hospital mortality.

scholarly journals Prediction of Repeat Customers on E-Commerce Platform Based on Blockchain

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Huibing Zhang ◽  
Junchao Dong
Keyword(s):  
Prediction Model ◽  
Ensemble Learning ◽  
Information Fusion ◽  
Prediction Accuracy ◽  
Feature Engineering ◽  
Learning Models ◽  
Information Dimension ◽  
Model Based ◽  
Repeat Purchase ◽  
The Impact

In recent years, blockchain has substantially enhanced the credibility of e-commerce platforms for users. The prediction accuracy of the repeat purchase behaviour of e-commerce users directly affects the impact of precision marketing by merchants. The existing ensemble learning models have low prediction accuracy when the purchase behaviour sample is unbalanced and the information dimension of feature engineering is single. To overcome this problem, an ensemble learning prediction model based on multisource information fusion is proposed. Tests on the Tmall dataset showed that the accuracy and AUC values of the model reached 91.28% and 70.53%, respectively.

scholarly journals Reduction of severe intraventricular hemorrhage, a tertiary single-center experience: incidence trends, associated risk factors, and hospital policy

2020 ◽  
Vol 36 (12) ◽  
pp. 2971-2979
Author(s):  
Wafa Sattam M. Alotaibi ◽  
Nada S. Alsaif ◽  
Ibrahim A. Ahmed ◽  
Aly Farouk Mahmoud ◽  
Kamal Ali ◽  
...  
Keyword(s):  
Risk Factors ◽  
Clinical Practice ◽  
Intraventricular Hemorrhage ◽  
Retrospective Chart Review ◽  
Multivariate Logistic Regression Model ◽  
Hospital Policy ◽  
Incidence Trends ◽  
Single Center Experience ◽  
The Impact ◽  
Neonatal Risk Factors

Abstract Objectives To determine the incidence, trends, maternal and neonatal risk factors of severe intraventricular hemorrhage (IVH) among infants born 24–32 weeks and/or < 1500 g, and to evaluate the impact of changing of hospital policies and unit clinical practice on the IVH incidence. Study design Retrospective chart review of preterm infants with a gestational age (GA) of 24–326 weeks and/or weight of < 1500 g born at King Abdulaziz Medical City–Riyadh (KAMC-R), Saudi Arabia, from 2016 to 2018. Multivariate logistic regression model was constructed to determine the probability of developing severe IVH and identify associations with maternal and neonatal risk factors. Results Among 640 infants, the overall incidence of severe IVH was 6.4% (41 infants), and its rate decreased significantly, from 9.4% in 2016 to 4.5% and 5% in 2017 and 2018 (p = 0.044). Multivariate analysis revealed that caesarian section delivery decreased the risk of severe IVH in GA group 24–27 weeks (p = 0.045). Furthermore use of inotropes (p = 0.0004) and surfactant (p = 0.0003) increased the risk of severe IVH. Despite increasing use of inotropes (p = 0.024), surfactant therapy (p = 0.034), and need for delivery room intubation (p = 0.015), there was a significant reduction in the incidence of severe IVH following the change in unit clinical practice and hospital policy (p = 0.007). Conclusion Cesarean section was associated with decreased all grades of IVH and severe IVH, while use of inotropes was associated with increased severe IVH. The changes in hospital and unit policy were correlated with decreased IVH during the study period.

Sign in / Sign up

Export Citation Format

Share Document