scholarly journals Comparison of logistic regression with machine learning methods for the prediction of fetal growth abnormalities: a retrospective cohort study

2018 ◽  
Vol 18 (1) ◽  
Author(s):  
Stefan Kuhle ◽  
Bryan Maguire ◽  
Hongqun Zhang ◽  
David Hamilton ◽  
Alexander C. Allen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Cohort Study ◽  
Fetal Growth ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Growth Abnormalities

scholarly journals Accuracy of Prenatal Ultrasound in Detecting Growth Abnormalities in Triplets: A Retrospective Cohort Study

2017 ◽  
Vol 20 (1) ◽  
pp. 84-89 ◽  
Author(s):  
Cameron Sklar ◽  
Maryna Yaskina ◽  
Sue Ross ◽  
Kentia Naud
Keyword(s):  
Cohort Study ◽  
Fetal Growth ◽  
Retrospective Cohort Study ◽  
Predictive Value ◽  
Retrospective Cohort ◽  
Prenatal Ultrasound ◽  
Growth Restriction ◽  
Fetal Weight ◽  
Growth Abnormalities ◽  
Estimated Fetal Weight

Significant management decisions in triplet pregnancies are made based mainly on ultrasound measurements of fetal growth, although there is a paucity of data examining the accuracy of fetal weight measurements in these gestations. To evaluate accuracy of prenatal ultrasound to diagnose growth abnormalities (intrauterine growth restriction, severe growth discordance) in triplet pregnancies, a retrospective cohort study of 78 triplet pregnancies (234 fetuses) delivered at a single tertiary hospital from January 2004 to May 2015 was performed. Growth percentiles from the last ultrasound were derived from estimated fetal weight using Hadlock's formula for each triplet. Growth discordance was calculated for each triplet set using the formula {(estimated fetal weight largest triplet - estimated fetal weight smallest)/estimated fetal weight largest}. These estimations were compared to birth weights. Sensitivity of ultrasound to predict ≥1 growth restricted fetus in a triplet set was 55.6% [95% CI 35.3, 74.5]; specificity was 100% [95% CI 93.0, 100]; positive predictive value (PPV) 100% [95% CI 74.7, 100]; negative predictive value (NPV) 81.0% [95% CI 73.2, 85.7%]. Sensitivity of ultrasound to detect fetal growth discordance >25% in a triplet set was 80.0% [95% CI 44.4, 97.5], specificity 94.1% [95% CI 85.6, 98.4]; PPV 66.7% [95% CI 42.4, 84.5]; NPV 97.0% [95% CI 90.2, 99.1]. Prenatal ultrasound currently remains the most reliable tool to screen for growth anomalies in triplet pregnancies; however, it appears to have less than ideal sensitivity, missing a number of cases of intra-uterine growth restriction and significant growth discordance.

Prediction of sperm extraction in non-obstructive azoospermia patients: a machine-learning perspective

2020 ◽  
Vol 35 (7) ◽  
pp. 1505-1514 ◽  
Author(s):  
A Zeadna ◽  
N Khateeb ◽  
L Rokach ◽  
Y Lior ◽  
I Har-Vardi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Cohort Study ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Obstructive Azoospermia ◽  
Learning Models ◽  
Testicular Sperm ◽  
Sperm Retrieval ◽  
Machine Learning Models

Abstract STUDY QUESTION Can a machine-learning-based model trained in clinical and biological variables support the prediction of the presence or absence of sperm in testicular biopsy in non-obstructive azoospermia (NOA) patients? SUMMARY ANSWER Our machine-learning model was able to accurately predict (AUC of 0.8) the presence or absence of spermatozoa in patients with NOA. WHAT IS KNOWN ALREADY Patients with NOA can conceive with their own biological gametes using ICSI in combination with successful testicular sperm extraction (TESE). Testicular sperm retrieval is successful in up to 50% of men with NOA. However, to the best of our knowledge, there is no existing model that can accurately predict the success of sperm retrieval in TESE. Moreover, machine-learning has never been used for this purpose. STUDY DESIGN, SIZE, DURATION A retrospective cohort study of 119 patients who underwent TESE in a single IVF unit between 1995 and 2017 was conducted. All patients with NOA who underwent TESE during their fertility treatments were included. The development of gradient-boosted trees (GBTs) aimed to predict the presence or absence of spermatozoa in patients with NOA. The accuracy of these GBTs was then compared to a similar multivariate logistic regression model (MvLRM). PARTICIPANTS/MATERIALS, SETTING, METHODS We employed univariate and multivariate binary logistic regression models to predict the probability of successful TESE using a dataset from a retrospective cohort. In addition, we examined various ensemble machine-learning models (GBT and random forest) and evaluated their predictive performance using the leave-one-out cross-validation procedure. A cutoff value for successful/unsuccessful TESE was calculated with receiver operating characteristic (ROC) curve analysis. MAIN RESULTS AND THE ROLE OF CHANCE ROC analysis resulted in an AUC of 0.807 ± 0.032 (95% CI 0.743–0.871) for the proposed GBTs and 0.75 ± 0.052 (95% CI 0.65–0.85) for the MvLRM for the prediction of presence or absence of spermatozoa in patients with NOA. The GBT approach and the MvLRM yielded a sensitivity of 91% vs. 97%, respectively, but the GBT approach has a specificity of 51% compared with 25% for the MvLRM. A total of 78 (65.3%) men with NOA experienced successful TESE. FSH, LH, testosterone, semen volume, age, BMI, ethnicity and testicular size on clinical evaluation were included in these models. LIMITATIONS, REASONS FOR CAUTION This study is a retrospective cohort study, with all the associated inherent biases of such studies. This model was used only for TESE, since micro-TESE is not performed at our center. WIDER IMPLICATIONS OF THE FINDINGS Machine-learning models may lay the foundation for a decision support system for clinicians together with their NOA patients concerning TESE. The findings of this study should be confirmed with further larger and prospective studies. STUDY FUNDING/COMPETING INTEREST(S) The study was funded by the Division of Obstetrics and Gynecology, Soroka University Medical Center, there are no potential conflicts of interest for all authors.

scholarly journals 387. Markers for Mortality in COVID-19 Patients with Atrial Fibrillation or Flutter

2020 ◽  
Vol 7 (Supplement_1) ◽  
pp. S262-S262
Author(s):  
Kok Hoe Chan ◽  
Bhavik Patel ◽  
Iyad Farouji ◽  
Addi Suleiman ◽  
Jihad Slim
Keyword(s):  
Atrial Fibrillation ◽  
Logistic Regression ◽  
Cohort Study ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Prognostic Markers ◽  
Univariate Analysis ◽  
Laboratory Data ◽  
Significant Difference ◽  
New Onset

Abstract Background Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection can lead to many different cardiovascular complications, we were interested in studying prognostic markers in patients with atrial fibrillation/flutter (A. Fib/Flutter). Methods A retrospective cohort study of patients with confirmed COVID-19 and either with existing or new onset A. Fib/Flutter who were admitted to our hospital between March 15 and May 20, 2020. Demographic, outcome and laboratory data were extracted from the electronic medical record and compared between survivors and non-survivors. Univariate and multivariate logistic regression were employed to identify the prognostic markers associated with mortality in patients with A. Fib/Flutter Results The total number of confirmed COVID-19 patients during the study period was 350; 37 of them had existing or new onset A. Fib/Flutter. Twenty one (57%) expired, and 16 (43%) were discharged alive. The median age was 72 years old, ranged from 19 to 100 years old. Comorbidities were present in 33 (89%) patients, with hypertension (82%) being the most common, followed by diabetes (46%) and coronary artery disease (30%). New onset of atrial fibrillation was identified in 23 patients (70%), of whom 13 (57%) expired; 29 patients (78%) presented with atrial fibrillation with rapid ventricular response, and 2 patients (5%) with atrial flutter. Mechanical ventilation was required for 8 patients, of whom 6 expired. In univariate analysis, we found a significant difference in baseline ferritin (p=0.04), LDH (p=0.02), neutrophil-lymphocyte ratio (NLR) (p=0.05), neutrophil-monocyte ratio (NMR) (p=0.03) and platelet (p=0.015) between survivors and non-survivors. With multivariable logistic regression analysis, the only value that had an odds of survival was a low NLR (odds ratio 0.74; 95% confidence interval 0.53–0.93). Conclusion This retrospective cohort study of hospitalized patients with COVID-19 demonstrated an association of increase NLR as risk factors for death in COVID-19 patients with A. Fib/Flutter. A high NLR has been associated with increased incidence, severity and risk for stroke in atrial fibrillation patients but to our knowledge, we are first to demonstrate the utilization in mortality predictions in COVID-19 patients with A. Fib/Flutter. Disclosures Jihad Slim, MD, Abbvie (Speaker’s Bureau)Gilead (Speaker’s Bureau)Jansen (Speaker’s Bureau)Merck (Speaker’s Bureau)ViiV (Speaker’s Bureau)

scholarly journals Lasting s-ketamine block of spreading depolarizations in subarachnoid hemorrhage: a retrospective cohort study

Critical Care ◽  
2019 ◽  
Vol 23 (1) ◽  
Author(s):  
Edgar Santos ◽  
Arturo Olivares-Rivera ◽  
Sebastian Major ◽  
Renán Sánchez-Porras ◽  
Lorenz Uhlmann ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Cohort Study ◽  
Subarachnoid Hemorrhage ◽  
Regression Model ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Logistic Regression Model ◽  
Poisson Model ◽  
High Dose ◽  
First Line

Abstract Objective Spreading depolarizations (SD) are characterized by breakdown of transmembrane ion gradients and excitotoxicity. Experimentally, N-methyl-d-aspartate receptor (NMDAR) antagonists block a majority of SDs. In many hospitals, the NMDAR antagonist s-ketamine and the GABAA agonist midazolam represent the current second-line combination treatment to sedate patients with devastating cerebral injuries. A pressing clinical question is whether this option should become first-line in sedation-requiring individuals in whom SDs are detected, yet the s-ketamine dose necessary to adequately inhibit SDs is unknown. Moreover, use-dependent tolerance could be a problem for SD inhibition in the clinic. Methods We performed a retrospective cohort study of 66 patients with aneurysmal subarachnoid hemorrhage (aSAH) from a prospectively collected database. Thirty-three of 66 patients received s-ketamine during electrocorticographic neuromonitoring of SDs in neurointensive care. The decision to give s-ketamine was dependent on the need for stronger sedation, so it was expected that patients receiving s-ketamine would have a worse clinical outcome. Results S-ketamine application started 4.2 ± 3.5 days after aSAH. The mean dose was 2.8 ± 1.4 mg/kg body weight (BW)/h and thus higher than the dose recommended for sedation. First, patients were divided according to whether they received s-ketamine at any time or not. No significant difference in SD counts was found between groups (negative binomial model using the SD count per patient as outcome variable, p = 0.288). This most likely resulted from the fact that 368 SDs had already occurred in the s-ketamine group before s-ketamine was given. However, in patients receiving s-ketamine, we found a significant decrease in SD incidence when s-ketamine was started (Poisson model with a random intercept for patient, coefficient − 1.83 (95% confidence intervals − 2.17; − 1.50), p < 0.001; logistic regression model, odds ratio (OR) 0.13 (0.08; 0.19), p < 0.001). Thereafter, data was further divided into low-dose (0.1–2.0 mg/kg BW/h) and high-dose (2.1–7.0 mg/kg/h) segments. High-dose s-ketamine resulted in further significant decrease in SD incidence (Poisson model, − 1.10 (− 1.71; − 0.49), p < 0.001; logistic regression model, OR 0.33 (0.17; 0.63), p < 0.001). There was little evidence of SD tolerance to long-term s-ketamine sedation through 5 days. Conclusions These results provide a foundation for a multicenter, neuromonitoring-guided, proof-of-concept trial of ketamine and midazolam as a first-line sedative regime.

scholarly journals Pre-Existing Lymphopenia Increases the Risk of Hospitalization and Death after SARS-CoV-2 Infection

2022 ◽  
Vol 14 (1) ◽  
pp. 20-25
Author(s):  
Riccardo Garbo ◽  
Francesca Valent ◽  
Gian Luigi Gigli ◽  
Mariarosaria Valente
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Cohort Study ◽  
General Population ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Logistic Regression Model ◽  
Protective Factor ◽  
Absolute Lymphocyte Count ◽  
Limited Information

There is limited information regarding the severity of COVID-19 in immunocompromized patients. We conducted a retrospective cohort study considering the period from 1 March 2020 to 31 December 2020 to determine whether previously existing lymphopenia increases the risk of hospitalization and death after SARS-CoV-2 infection in the general population. The laboratory and hospital discharge databases of the Azienda Sanitaria Universitaria Friuli Centrale were used, and 5415 subjects infected with SARS-CoV-2 and with at least one recent absolute lymphocyte count determination before SARS-CoV-2 positivity were included. In total, 817 (15.1%) patients had severe COVID-19. Patients developing severe COVID-19 were more frequently males (44.9% of the severe COVID-19 group vs. 41.5% in the non-severe COVID-19 group; p < 0.0001) and were older (73.2 ± 13.8 vs. 58.4 ± 20.3 years; p < 0.0001). Furthermore, 29.9% of the lymphopenic patients developed severe COVID-19 vs. 14.5% of the non-lymphopenic patients (p < 0.0001). In a logistic regression model, female sex remained a protective factor (OR = 0.514, 95%CI 0.438–0.602, p < 0.0001), while age and lymphopenia remained risk factors for severe COVID-19 (OR = 1.047, 95%CI 1.042–1.053, p < 0.0001 for each additional year of age; OR = 1.715, 95%CI 1.239–2.347, p = 0.0011 for lymphopenia). This provides further information to stratify the risk of COVID-19 severity, which may be an important element in the management of immunosuppressive therapies.

scholarly journals “INTERGROWTH21st vs customized fetal growth curves in the assessment of the neonatal nutritional status: a retrospective cohort study of gestational diabetes”

2019 ◽  
Author(s):  
Juan Jesus Fernández Alba ◽  
Estefania Soto Pazos ◽  
Rocio Moreno Cortes ◽  
Angel Vilar Sanchez ◽  
Carmen Gonzalez Macias ◽  
...  
Keyword(s):  
Cohort Study ◽  
Gestational Diabetes ◽  
Nutritional Status ◽  
Positive Predictive Value ◽  
Pregnant Women ◽  
Fetal Growth ◽  
Retrospective Cohort Study ◽  
Predictive Value ◽  
Retrospective Cohort ◽  
Growth Curves

Abstract Background Gestational diabetes mellitus is associated with increased incidence of adverse perinatal outcomes including newborns large for gestational age, macrosomia, preeclampsia, polihydramnios, stillbirth, and neonatal morbidity. Thus, fetal growth should be monitored by ultrasound to limit fetal overnutrition, and thereby, its clinical consequence, macrosomia. However, it is not clear which reference curve to use to define the limits of normality. Our aim is to determine which method, INTERGROWTH21st or customized curves, better identifies the nutritional status of newborns of diabetic mothers.Methods This retrospective cohort study compared the risk of malnutrition in SGA newborns and the risk of overnutrition in LGA newborns using INTERGROWTH21st and customized birth weight references in gestational diabetes. Additionally, to determine the ability of both methods in the identification of neonatal malnutrition and overnutrition, we calculate sensitivity, specificity, positive predictive value, negative predictive value and likelihood ratios.Results 231 pregnant women with GDM were included in the study. The rate of SGA indentified by INTERGROWTH21st was 4.7% vs 10.7% identified by the customized curves. The rate of LGA identified by INTERGROWT21st was 25.6% vs 13.2% identified by the customized method. Newborns identified as SGA by the customized method showed a higher risk of malnutrition than those identified as SGA by INTERGROWTH21st.(RR 4.24 vs 2.5). LGA newborns according to the customized method also showed a higher risk of overnutrition than those classified as LGA according to INTERGROWTH21st. (RR 5.26 vs 3.57). In addition, the positive predictive value of the customized method was superior to that of INTERGROWTH21st in the identification of malnutrition (32% vs 27.27%), severe malnutrition (22.73% vs 20%), overnutrition (51.61% vs 32.20%) and severe overnutrition (28.57% vs 14.89%).Conclusions In pregnant women with GDM, the ability of customized fetal growth curves to identify the newborns with alterations in nutritional status exceeds that of INTERGROWTH21st.

Sign in / Sign up

Export Citation Format

Share Document