scholarly journals Artificial Neural Networks Versus Multiple Logistic Regression to Predict 30-Day Mortality After Operations For Type A Ascending Aortic Dissection§

2009 ◽  
Vol 3 (1) ◽  
pp. 81-95 ◽  
Author(s):  
Francesco Macrina ◽  
Paolo Emilio Puddu ◽  
Alfonso Sciangula ◽  
Fausto Trigilia ◽  
Marco Totaro ◽  
...  
Keyword(s):  
Risk Factors ◽  
Neural Networks ◽  
Logistic Regression ◽  
Aortic Dissection ◽  
Predictive Accuracy ◽  
Area Under The Curve ◽  
Type A ◽  
Multiple Logistic Regression ◽  
Short Term Mortality ◽  
Potential Risk Factors

Background:There are few comparative reports on the overall accuracy of neural networks (NN), assessed only versus multiple logistic regression (LR), to predict events in cardiovascular surgery studies and none has been performed among acute aortic dissection (AAD) Type A patients.Objectives:We aimed at investigating the predictive potential of 30-day mortality by a large series of risk factors in AAD Type A patients comparing the overall performance of NN versus LR.Methods:We investigated 121 plus 87 AAD Type A patients consecutively operated during 7 years in two Centres. Forced and stepwise NN and LR solutions were obtained and compared, using receiver operating characteristic area under the curve (AUC) and their 95% confidence intervals (CI) and Gini’s coefficients. Both NN and LR models were re-applied to data from the second Centre to adhere to a methodological imperative with NN.Results:Forced LR solutions provided AUC 87.9±4.1% (CI: 80.7 to 93.2%) and 85.7±5.2% (CI: 78.5 to 91.1%) in the first and second Centre, respectively. Stepwise NN solution of the first Centre had AUC 90.5±3.7% (CI: 83.8 to 95.1%). The Gini’s coefficients for LR and NN stepwise solutions of the first Centre were 0.712 and 0.816, respectively. When the LR and NN stepwise solutions were re-applied to the second Centre data, Gini’s coefficients were, respectively, 0.761 and 0.850. Few predictors were selected in common by LR and NN models: the presence of pre-operative shock, intubation and neurological symptoms, immediate post-operative presence of dialysis in continuous and the quantity of post-operative bleeding in the first 24 h. The length of extracorporeal circulation, post-operative chronic renal failure and the year of surgery were specifically detected by NN.Conclusions:Different from the International Registry of AAD, operative and immediate post-operative factors were seen as potential predictors of short-term mortality. We report a higher overall predictive accuracy with NN than with LR. However, the list of potential risk factors to predict 30-day mortality after AAD Type A by NN model is not enlarged significantly.

A proof-of-concept study applying machine learning methods to putative risk factors for eating disorders: results from the multi-centre European project on healthy eating

2021 ◽  
pp. 1-10
Author(s):  
I. Krug ◽  
J. Linardon ◽  
C. Greenwood ◽  
G. Youssef ◽  
J. Treasure ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Logistic Regression ◽  
Predictive Accuracy ◽  
Area Under The Curve ◽  
Prediction Rule ◽  
Predictive Performance ◽  
Individual Risk ◽  
European Project ◽  
Wide Range

Abstract Background Despite a wide range of proposed risk factors and theoretical models, prediction of eating disorder (ED) onset remains poor. This study undertook the first comparison of two machine learning (ML) approaches [penalised logistic regression (LASSO), and prediction rule ensembles (PREs)] to conventional logistic regression (LR) models to enhance prediction of ED onset and differential ED diagnoses from a range of putative risk factors. Method Data were part of a European Project and comprised 1402 participants, 642 ED patients [52% with anorexia nervosa (AN) and 40% with bulimia nervosa (BN)] and 760 controls. The Cross-Cultural Risk Factor Questionnaire, which assesses retrospectively a range of sociocultural and psychological ED risk factors occurring before the age of 12 years (46 predictors in total), was used. Results All three statistical approaches had satisfactory model accuracy, with an average area under the curve (AUC) of 86% for predicting ED onset and 70% for predicting AN v. BN. Predictive performance was greatest for the two regression methods (LR and LASSO), although the PRE technique relied on fewer predictors with comparable accuracy. The individual risk factors differed depending on the outcome classification (EDs v. non-EDs and AN v. BN). Conclusions Even though the conventional LR performed comparably to the ML approaches in terms of predictive accuracy, the ML methods produced more parsimonious predictive models. ML approaches offer a viable way to modify screening practices for ED risk that balance accuracy against participant burden.

scholarly journals Nomogram Based on Preoperative Clinical Characteristics to Predict the Risk of Lymph Node Metastasis in Hepatocellular Carcinoma

2020 ◽  
Author(s):  
Rongyu Wei ◽  
Shuqun Li ◽  
Liying Ren ◽  
Junxiong Yu ◽  
Weijia Liao
Keyword(s):  
Risk Factors ◽  
Hepatocellular Carcinoma ◽  
Logistic Regression ◽  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Clinical Characteristics ◽  
Predictive Accuracy ◽  
Hepatitis B Surface Antigen ◽  
Area Under The Curve ◽  
Node Metastasis

Abstract Background: There are limitations in judging the occurrence of lymph node metastasis (LNM) in hepatocellular carcinoma (HCC) before surgery. The purpose of this study was to establish a preoperative nomogram for predicting the risk of LNM in HCC and to explore its clinical utility.Methods: A total of 195 HCC patients undergoing radical hepatectomy were retrospectively analyzed. According to the presence or absence of LNM, the patients were divided into two groups, and the clinical characteristics of the two groups were compared. Risk factors for LNM were assessed based on logistic regression, and a nomogram was established. The receiver operating characteristic (ROC) curve was used to calculate area under the curve (AUC) of the logistic regression model, and the predictive accuracy of the nomogram was evaluated by the concordance index (C-index). The clinical efficacy of the nomogram was detected by decision curve analysis (DCA).Results: Logistic analysis revealed hepatitis B surface antigen (HBsAg) (HR = 3.50, 95% CI, 1.30-9.42, P = 0.013), globulin (HR = 2.46, 95% CI, 1.05-5.75, P = 0.039), neutrophil to lymphocyte ratio (NLR) (HR = 7.64, 95% CI, 3.22-18.11, P < 0.001) and tumor size (HR = 3.86, 95% CI, 1.26-11.88 P = 0.018) were independent risk factors for lymph node metastasis in HCC. The nomogram was established based on the above 4 variables, and the AUC was 0.835 (95% CI, 0.780-0.890). The calibration curve showed that the model has good predictive ability, and DCA indicates good predictive effect.Conclusions: The nomogram established by analyzing the preoperative clinical characteristics is a simple tool that can predict the risk of lymph node metastasis in HCC patients and guide clinicians to make better clinical decisions.

scholarly journals Acute kidney injury in patients operated on for type A acute aortic dissection: incidence, risk factors and short-term outcomes

2020 ◽  
Vol 31 (5) ◽  
pp. 697-703 ◽  
Author(s):  
Zhigang Wang ◽  
Min Ge ◽  
Tao Chen ◽  
Cheng Chen ◽  
Qiuyan Zong ◽  
...  
Keyword(s):  
Risk Factors ◽  
Acute Kidney Injury ◽  
Logistic Regression ◽  
Aortic Dissection ◽  
Cystatin C ◽  
Acute Aortic Dissection ◽  
Kidney Injury ◽  
Type A ◽  
Short Term ◽  
Postoperative Ventilation

Abstract OBJECTIVES Acute kidney injury (AKI) is a relatively common complication after an operation for type A acute aortic dissection and is indicative of a poor prognosis. We examined the risk factors for and the outcomes of developing AKI in patients being operated on for thoracic aortic diseases. METHODS We retrospectively analysed 712 patients with acute type A dissection who had deep hypothermic circulatory operations from January 2014 to December 2018, emphasizing those who developed AKI. Logistic regression models were used to identify predisposing factors for the postoperative development of AKI. RESULTS Among all enrolled patients, 359 (50.4%) had AKI; of these, 133 were diagnosed as stage 1 (18.7%), 126 were stage 2 (17.7%) and 100 were stage 3 (14.0%). Postoperative haemodialysis was required in 111 patients (15.9%). The development of AKI after aortic surgery contributed to the higher mortality rate within 30 days after surgery (P &lt; 0.001), longer stay in the intensive care unit (P = 0.01) and longer hospital stay (P &lt; 0.001). Binary logistic regression analysis showed that preoperative cystatin C levels [odds ratio (OR) 2.615, 95% confidence interval (CI) 1.139–6.002; P = 0.023] and postoperative ventilation time (OR 1.019, 95% CI 1.005–1.034; P = 0.009) were independent risk factors for developing AKI. Multiple ordinal logistic regression analyses showed that the preoperative cystatin C level (OR 2.921, 95% CI 1.542–5.540; P = 0.001) was an independent risk factor associated with the severity of AKI. CONCLUSIONS Our data suggested that the development of AKI after surgery for type A acute aortic dissection was common and associated with an increased short-term mortality rate. The preoperative cystatin C level was identified as an indicator for the occurrence and severity of AKI postoperatively. Furthermore, we discovered that longer postoperative ventilation time was also associated with the development of AKI.

scholarly journals Development of a practical prediction score for acute renal injury after surgery for Stanford type A aortic dissection

2020 ◽  
Vol 30 (5) ◽  
pp. 746-753
Author(s):  
Ning Dong ◽  
Hulin Piao ◽  
Yu Du ◽  
Bo Li ◽  
Jian Xu ◽  
...  
Keyword(s):  
Aortic Dissection ◽  
Risk Score ◽  
Scoring System ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Kidney Injury ◽  
Type A ◽  
Postoperative Management ◽  
Prediction Score ◽  
Improve Patient

Abstract OBJECTIVES Acute kidney injury (AKI) is a common complication of cardiovascular surgery that is associated with increased mortality, especially after surgeries involving the aorta. Early detection and prevention of AKI in patients with aortic dissection may help improve outcomes. The objective of this study was to develop a practical prediction score for AKI after surgery for Stanford type A acute aortic dissection (TAAAD). METHODS This was a retrospective cohort study that included 2 independent hospitals. A larger cohort of 326 patients from The Second Hospital of Jilin University was used to identify the risk factors for AKI and to develop a risk score. The derived risk score was externally validated in a separate cohort of 102 patients from the other hospital. RESULTS The scoring system included the following variables: (i) age &gt;45 years; (ii) body mass index &gt;25 kg/m2; (iii) white blood cell count &gt;13.5 × 109/l; and (iv) lowest perioperative haemoglobin &lt;100 g/l, cardiopulmonary bypass duration &gt;150 min and renal malperfusion. On receiver operating characteristic curve analysis, the score predicted AKI with fair accuracy in both the derivation [area under the curve 0.778, 95% confidence interval (CI) 0.726–0.83] and the validation (area under the curve 0.747, 95% CI 0.657–0.838) cohorts. CONCLUSIONS We developed a convenient scoring system to identify patients at high risk of developing AKI after surgery for TAAAD. This scoring system may help identify patients who require more intensive postoperative management and facilitate appropriate interventions to prevent AKI and improve patient outcomes.

Risk factors and outcomes of postoperative emergency response team activation: a matched case-control study

2020 ◽  
Vol 22 (1) ◽  
pp. 6-14
Author(s):  
Matthew I Hardman ◽  
◽  
S Chandralekha Kruthiventi ◽  
Michelle R Schmugge ◽  
Alexandre N Cavalcante ◽  
...  
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Postoperative Complications ◽  
Emergency Response ◽  
Case Control Study ◽  
Case Control ◽  
Multiple Logistic Regression ◽  
Increased Risk ◽  
Response Team ◽  
Control Study

OBJECTIVE: To determine patient and perioperative characteristics associated with unexpected postoperative clinical deterioration as determined for the need of a postoperative emergency response team (ERT) activation. DESIGN: Retrospective case–control study. SETTING: Tertiary academic hospital. PARTICIPANTS: Patients who underwent general anaesthesia discharged to regular wards between 1 January 2013 and 31 December 2015 and required ERT activation within 48 postoperative hours. Controls were matched based on age, sex and procedure. MAIN OUTCOME MEASURES: Baseline patient and perioperative characteristics were abstracted to develop a multiple logistic regression model to assess for potential associations for increased risk for postoperative ERT. RESULTS: Among 105 345 patients, 797 had ERT calls, with a rate of 7.6 (95% CI, 7.1–8.1) calls per 1000 anaesthetics (0.76%). Multiple logistic regression analysis showed the following risk factors for postoperative ERT: cardiovascular disease (odds ratio [OR], 1.61; 95% CI, 1.18–2.18), neurological disease (OR, 1.57; 95% CI, 1.11–2.22), preoperative gabapentin (OR, 1.60; 95% CI, 1.17–2.20), longer surgical duration (OR, 1.06; 95% CI, 1.02–1.11, per 30 min), emergency procedure (OR, 1.54; 95% CI, 1.09–2.18), and intraoperative use of colloids (OR, 1.50; 95% CI, 1.17–1.92). Compared with control participants, ERT patients had a longer hospital stay, a higher rate of admissions to critical care (55.5%), increased postoperative complications, and a higher 30-day mortality rate (OR, 3.36; 95% CI, 1.73–6.54). CONCLUSION: We identified several patient and procedural characteristics associated with increased likelihood of postoperative ERT activation. ERT intervention is a marker for increased rates of postoperative complications and death.

Abstract P249: Incident Sleep-Disordered Breathing is Associated with Obesity: Penn State Child Cohort

Circulation ◽  
2013 ◽  
Vol 127 (suppl_12) ◽  
Author(s):  
Edward O Bixler ◽  
Alexandros N Vgontzas ◽  
Duanping Liao ◽  
Susan Calhoun ◽  
Julio Fernandez-Mendoza ◽  
...  
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Sleep Disordered Breathing ◽  
Population Sample ◽  
Population Based ◽  
Penn State ◽  
Potential Risk Factors ◽  
State Child ◽  
Disordered Breathing

Objectives: To study the epidemiology of sleep-disordered breathing (SDB) in adolescents, which has received little attention. Methods: The Penn State Child Cohort (PSCC) is a representative general population sample of 700 children aged 5-12 years. Our preliminary results are based on an average 8 year follow up of the initial 300 prospective subjects (~43%) from this ongoing cohort study. A logistic regression was used to assess the association between potential risk factors and incident SDB. Results: The mean age at the 8-year follow up examination was 17.2 ± 0.1 years, with an average BMI percentile of 66.6 ± 1.6 and 56.5% boys. At baseline 1.5% of this subsample had SDB, defined by Apnea Hypopnia Index (AHI > 5 /hour). Surprisingly, there was no persistence of SDB. Eight-year incident SDB was 10.5%. The average AHI in those with incident SDB was 12.7 with a maximum of 92.4. Incident SDB was similar for girls (7.8%) and boys (12.7%). Those with SDB were older than those without (18.7 vs 17.0 years, P<0.001) and girls with SDB were older than boys with SDB (20.0 vs 18.0 years, P=0.002). Those with incident SDB tended to have a greater change in BMI percentile (8.2 vs 1.8, P = 0.143) during the follow up and slightly higher minority representation (25.8% vs 21.9%, P=0.655). A logistic regression model identified three variables that were associated with incident SDB, controlling for baseline AHI: age (OR = 1.5 (1.3, 1.9) P<0.001), male (OR= 2.5 (1.11,10.00) P=0.021), and [[Unable to Display Character: &#8710;]]BMIPCT (OR=1.2(1.02, 1.5) P=0.032). Conclusion: In this population based sample of adolescents, the 8-year incidence of SDB was high (10.5%), whereas childhood SDB did not persist into adolescence. Further, the results indicate that risk factors for incident SDB in adolescents are age, male and the development of obesity.

scholarly journals Risk factors for hypoxemia following surgical repair of acute type A aortic dissection

2016 ◽  
pp. ivw272
Author(s):  
Nan Liu ◽  
Wei Zhang ◽  
Weiguo Ma ◽  
Wei Shang ◽  
Jun Zheng ◽  
...  
Keyword(s):  
Risk Factors ◽  
Aortic Dissection ◽  
Surgical Repair ◽  
Type A ◽  
Acute Type ◽  
Type A Aortic Dissection
Sign in / Sign up

Export Citation Format

Share Document