scholarly journals Development of an infant mortality risk score in Uruguay

2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
M Alegretti ◽  
I Leon ◽  
A Aleman ◽  
F Cavallieri ◽  
W Callero
Keyword(s):  
High Risk ◽  
Infant Mortality ◽  
Live Birth ◽  
Risk Score ◽  
Mortality Risk ◽  
Home Visit ◽  
Birth Certificate ◽  
Area Under The Curve ◽  
Binary Logistic Regression Model ◽  
Roc Curve Analysis

Abstract Background The Ministry of Public Health of Uruguay incorporated a comprehensive home visit before 7 days of discharge to monitor children at risk of infant mortality. In this context, a precise risk stratification of newborns is needed to optimize the implementation of the home visit. Objective Implement a validated infant mortality risk score for Uruguay using the national electronic live birth certificate. Methods Electronic records of newborns from 2014 to 2017 were used to develop the score. The variables of the electronic live birth certificate were considered for the model and data of Infant mortality was obtained from the national mortality registry. A multivariate binary logistic regression model was estimated with a random sample of 80% of the cohort, the remaining 20% was the validation set. ROC curve analysis was performed. R software was used. Results The 2014-2017 birth cohort contains 187,388 records. 1307 children under one year died (IMR 6.97 per 1,000 births). The variables included in the final model were birth weight, APGAR score at 5 minutes, number of prenatal visits, maternal educational level and father living at home. The area under the curve (AUC) was 89%, CI 95% [87% - 91%]. Two cut-off points were defined: 0.4% and 2%. Less than 0.4% was considered low risk (IMR 1.4 per 1,000 births), between 0.4 and 2% was considered intermediate risk (IMR 7.1 per 1,000 births) and more than 2% was considered high risk (IMR 99.2 per 1,000 births). Conclusions The score identifies high-risk newborns at the time of entering the data in the electronic live birth certificate. This information could be used to plan and implement the home visit and other actions, according to the level of risk identified. Key messages In Uruguay, high-risk newborns can be identified using data collected routinely. The procedure could be applied in other countries with electronic birth certificate.

Estimating infant mortality risk in Uruguay using artificial neural networks

2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
M Alegretti ◽  
A Aleman ◽  
I Leon ◽  
F Cavallieri ◽  
W Callero
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
High Risk ◽  
Infant Mortality ◽  
Live Birth ◽  
Birth Certificate ◽  
The Neural Network ◽  
Artificial Neural ◽  
Prediction Problems

Abstract Background Uruguay has a national electronic live birth certificate that includes variables of risk factors for infant mortality. Accurate risk stratification of newborns is needed to optimize the use of resources for homes visits. Artificial neural networks are computational tools that have been used successfully in many types of prediction problems. Objective To develop a neural network able to estimate the risk of infant mortality using information available in the electronic live birth and mortality certificate in Uruguay. Methods A historical cohort of records of newborns in Uruguay from 2014 to 2017 was used. The variables of the electronic live birth certificate were considered for the model. Infant mortality was obtained from the national mortality registry. A multilayer perceptron was trained with a random sample of 70% of the cohort; the remaining 30% was the validation set. The variables included were birth weight, Apgar score at 5 minutes, number of prenatal consultations, maternal educational level, multiple pregnancy and cohabiting father. ROC curve analysis was performed. Results The 2014-2017 birth cohort contains 187,388 records. 1,307 children under one year died (IMR 6.97 per 1,000 births). The area under the curve (AUC) was 88.7%, 95% CI [87.6% - 89.8%]. The optimal cut-off point of pseudoprobability of infant mortality was 0.008 (78.9% of sensibility and 82.4% of specificity). The IMR in high-risk newborns identified by the neural network was 32.8 per 1,000 births. Conclusions The neural network identifies high-risk newborns at the time of entering the data in the electronic live birth certificate as other models have done. This information could be used to plan and implement preventive actions. Key messages In Uruguay, high-risk newborns can be identified by applying artificial intelligence to data collected routinely. The procedure can be applied in other countries with electronic birth certificate.

scholarly journals A diabetes risk score for Qatar utilizing a novel mathematical modeling approach to identify individuals at high risk for diabetes

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Susanne F. Awad ◽  
Soha R. Dargham ◽  
Amine A. Toumi ◽  
Elsy M. Dumit ◽  
Katie G. El-Nahas ◽  
...  
Keyword(s):  
High Risk ◽  
Sensitivity And Specificity ◽  
Risk Score ◽  
Area Under The Curve ◽  
Diabetes Risk ◽  
Predictive Values ◽  
Predictive Variables ◽  
Comparable Performance ◽  
Representative Random Sample ◽  
Diabetes Risk Score

AbstractWe developed a diabetes risk score using a novel analytical approach and tested its diagnostic performance to detect individuals at high risk of diabetes, by applying it to the Qatari population. A representative random sample of 5,000 Qataris selected at different time points was simulated using a diabetes mathematical model. Logistic regression was used to derive the score using age, sex, obesity, smoking, and physical inactivity as predictive variables. Performance diagnostics, validity, and potential yields of a diabetes testing program were evaluated. In 2020, the area under the curve (AUC) was 0.79 and sensitivity and specificity were 79.0% and 66.8%, respectively. Positive and negative predictive values (PPV and NPV) were 36.1% and 93.0%, with 42.0% of Qataris being at high diabetes risk. In 2030, projected AUC was 0.78 and sensitivity and specificity were 77.5% and 65.8%. PPV and NPV were 36.8% and 92.0%, with 43.0% of Qataris being at high diabetes risk. In 2050, AUC was 0.76 and sensitivity and specificity were 74.4% and 64.5%. PPV and NPV were 40.4% and 88.7%, with 45.0% of Qataris being at high diabetes risk. This model-based score demonstrated comparable performance to a data-derived score. The derived self-complete risk score provides an effective tool for initial diabetes screening, and for targeted lifestyle counselling and prevention programs.

scholarly journals Validation of the Zwolle score for selection of very low-risk STEMI patients treated with primary angioplasty

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
A Cordero ◽  
B Cid ◽  
P Monteiro ◽  
J.M Garcia-Acuna ◽  
M Rodriguez-Manero ◽  
...  
Keyword(s):  
Hospital Mortality ◽  
Risk Score ◽  
Mortality Risk ◽  
Area Under The Curve ◽  
Coronary Intervention ◽  
Low Risk ◽  
Individual Risk ◽  
Care Organization ◽  
Grace Score ◽  
Selection Of

Abstract Background The Zwolle risk score was designed to stratify the actual in-hospital mortality risk of ST-elevation myocardial infarction (STEMI) patients treated with primary percutaneous coronary intervention (p-PCI) but, also, for decision-making related to patients location in an intensive care unit or not. Since the GRACE score continues being the gold-standard for individual risk assessment in STEMI in most institutions we assessed the specificity of both scores for in-hospital mortality. Methods We assessed the accuracy of Zwolle risk score for in-hospital mortality estimation as compared to the GRACE score in all patients admitted for STEMI in 3 tertitary hospitals. Patients with Zwolle risk score <3 would qualify as “low risk”, 3–5 as “intermediate risk” and ≥6 as “high risk”. Patients with GRACE score <140 were classified as low-risk. Specificity, sensitivity and classification were assessed by ROC curves and the area under the curve (AUC). Results We included 4,446 patients, mean age 64.7 (13.6) years, 24% women and 39% with diabetes. Mean GRACE score was 157.3 (4.9) and Zwolle was 2.8 (3.3). In-hospital mortality was 10.6% (471 patients). Patients who died had higher GRACE score (218.4±4.9 vs. 149.6±37.5; p<0.001) and Zwolle score (7.6±4.3 vs. 2.3±2.18; p<0.001); a statistically significant increase of in-hospital mortality risk, adjusted adjusted by age, gender and revascularization, was observed with both scores (figure). A total of 1,629 patients (40.0%) were classified as low risk by the GRACE score and 2,962 (66.6%) by the Zwolle score; in-hospital mortality was 1.6% and 2.7%, respectively. Moreover, the was a significant increase of in-hospital mortality rate according to Zwolle categories (2.7%; 13.0%; 41.6%)The AUC of both score was the same (p=0.49) but the specificity of GRACE score <140 was 43.1% as compared to 72.6% obtained by Zwolle score <3; patients accurately classified was also lower with the GRACE score threshold (48.8% vs. 73.7%). Conclusions Selection of low-risk STEMI patients treated with p-PCI based on the Zwolle risk score has higher specificity than the GRACE score and might be useful for the care organization in clinical practice. Funding Acknowledgement Type of funding source: None

A novel risk score for prediction of hypersensitivity reactions in cancer patients receiving carboplatin: Retrospective observational analysis.

2016 ◽  
Vol 34 (3_suppl) ◽  
pp. e282-e282
Author(s):  
Orawan Suppramote ◽  
Prapatsara Pongpunpisand ◽  
Kanlaya Ladkam ◽  
Somkiat Rujirawat
Keyword(s):  
High Risk ◽  
Cancer Patients ◽  
Risk Score ◽  
Scoring System ◽  
Predictive Accuracy ◽  
Area Under The Curve ◽  
Cancer Type ◽  
Hypersensitivity Reactions ◽  
Risk Patients ◽  
Carboplatin Hypersensitivity

e282 Background: Hypersentitivity reactions (HSRs) from carboplatin are high incidence and most severity in Chulabhorn hospital. These reactions are associated with several causes including patient factors and experience in drug used. A reliable and valid tool for evaluated risk of HSRs before started carboplatin infusion should lead to prevent or decrease severity of the reactions. We innovated risk score to screen patient at high risk of HSRs. Methods: From October 2013 to September 2014, all cancer patients who received carboplatin in Chulabhorn hospital were included. A retrospective study design to developed risk scoring system for prediction of patients at high risk of carboplatin hypersensitivity called “Hypersensitivity risk score”. The hypersensitivity risk score was calculated for all patients receiving carboplatin and data for carboplatin hypersensitivity were obtained from medical records. Expected and observed HSRs were analyzed by using receiver operating characteristic (ROC) curve. Results: Seventy-three cancer patients received carboplatin and five (7%) patients had HSRs. Our scoring algorithm based on cancer type, number of carboplatin retreatment, duration between each retreatment, and number of carboplatin infusions prior to first reaction. All significant predictors were weighted into points and categorized to risk group which ranged from 0 to 8 . The ROC analysis for hypersensitivity risk score indicated good predictive accuracy with an area under the curve of 0.96 (95 %CI: 0.91-1.00). Data showed high sensitivity (80%) and specificity (94.85%) for a risk score cut-off of 4. The hypersensitivity risk score clearly differentiated the low (0-1), intermediate (2-3) and intermediate-high (4-5) and high (6-8) risk patients. Conclusions: The hypersensitivity risk score is a simple scoring system with high predictive value and differentiates low versus high risk patients. This score should be used for screen high risk of hypersensitivity reactions in patients receiving carboplatin.

scholarly journals The risk-treatment paradox in acute coronary syndrome patients: insights from the FORCE-ACS registry

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
J Azzahhafi ◽  
N M R Van Der Sangen ◽  
D R P P Chan Pin Yin ◽  
J P Simao Henriques ◽  
W J Kikkert ◽  
...  
Keyword(s):  
High Risk ◽  
Risk Score ◽  
Mortality Risk ◽  
Recommended Care ◽  
High Risk Patients ◽  
Grace Risk Score ◽  
Risk Patients ◽  
Risk Treatment ◽  
One Year ◽  
Risk Categories

Abstract Background Acute coronary syndrome (ACS) patients at high risk might benefit most from guideline-recommended interventions. However, it is well recognized that the delivery of guideline-directed care is inversely related to the estimated mortality risk, the so called risk-treatment paradox. Purpose To assess the existence of the risk-treatment paradox in a contemporary cohort of ACS patients and its possible association with one-year mortality. Methods The study population consisted patients enrolled in the FORCE-ACS registry who survived their initial admission. All ACS patients were stratified into low, intermediate or high mortality risk based on the Global Registry of Acute Coronary Events (GRACE) risk score. Optimal guideline-recommended care was defined as undergoing coronary angiography during initial hospital admission and receiving all outpatient medications with a class I guideline recommendation (i.e. aspirin, P2Y12-inhibitor, beta-blocker, angiotensin-converting enzyme inhibitor or angiotensin receptor blocker and cholesterol-lowering drug). Aspirin and/or a P2Y12-inhibitor on top of an oral anticoagulant was also considered as optimal guideline-recommended care. The cumulative incidence of one-year mortality between optimal and suboptimal managed patients, within each GRACE risk score stratum, was estimated. Results In total, 2,524 patients who were enrolled between January 2015 and June 2018 were included. Based on the GRACE risk score, 46.9% of patients were classified as low-risk, 37.6% as intermediate-risk and 15.5% as high-risk. Overall, 49.8% of patients received optimal guideline-recommended care. Among the different risk strata, 54.9% of the low-risk, 49.1% of the intermediate-risk and 36.1% of the high-risk patients received optimal guideline-recommended care (Table 1). DAPT or DAT treatment (95.3% overall) did not differ between the risk categories. Beta-blockers were prescribed less frequently (69.6% overall), butprescription rates did not differ between the risk categories. ACE-inhibitors/ARBs were prescribed in 74.1% of all patients, but less often in high risk patients. Cholesterol lowering-drugs were prescribed in almost all patients (94.9% overall), but less frequently in high risk patients. Overall, 93.9% of patients underwent coronary angiography (CAG), high-risk patients had a statistically significant lower likelihood of undergoing CAG. In all risk categories, optimal guideline-recommended care was associated with a lower one-year mortality as compared to sub-optimal treatment (5.7% vs. 15.6% in high-risk) (Fig. 1). Conclusion Patients at higher estimated mortality risk, based on the GRACE-risk score, are less likely to receive guideline-recommended care. Although, the absolute benefit from guideline-recommended care appears to be greater in high-risk patients. Receiving guideline-recommended care was associated with a statistically significant better prognosis in intermediate- and high-risk patients. FUNDunding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): ZonMW Netherlands TopZorgSt. Antonius Research funds Figure 1. All-cause mortality

scholarly journals Increased plasma concentration of cell-free DNA precedes disease recurrence in children with high-risk neuroblastoma

2020 ◽  
Author(s):  
Yan Su ◽  
Lijun Wang ◽  
Chiyi Jiang ◽  
Zhixia Yue ◽  
Hongjun Fan ◽  
...  
Keyword(s):  
High Risk ◽  
Maintenance Treatment ◽  
Multidisciplinary Treatment ◽  
Area Under The Curve ◽  
Predictive Biomarkers ◽  
Disease Recurrence ◽  
High Rate ◽  
Roc Curve Analysis ◽  
Cell Free Dna ◽  
Free Dna

Abstract Background: Neuroblastoma is the most common extracranial solid tumor of childhood. The high rate of recurrence is associated with a low survival rate for patients with high-risk neuroblastoma. There is thus an urgent need to identify effective predictive biomarkers of disease recurrence. Methods: A total of 116 patients with high-risk neuroblastoma were recruited at Beijing Children’s Hospital between February 2015 and December 2017. All patients received multidisciplinary treatment, were evaluated for the therapeutic response, and then initiated on maintenance treatment. Blood samples were collected at the beginning of maintenance treatment, every 3 months thereafter, and at the time of disease recurrence. Plasma levels of cell-free DNA (cfDNA) were quantified by qPCR. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the ability of plasma cfDNA concentration to predict recurrence. Results: Of the 116 patients, 36 (31.0%) developed recurrence during maintenance treatment. The median time to recurrence was 19.00, 9.00, and 8.00 months for patients who had achieved complete response (n = 6), partial response (n = 25), and stable disease (n = 5), respectively, after multidisciplinary treatment. The median plasma cfDNA concentration at the time of recurrence was significantly higher than the concentration in recurrence-free patients throughout maintenance treatment (29.34 ng/mL vs 10.32 ng/mL). Patients recorded a plasma cfDNA level ≥29 ng/mL an average of 0.55 months before diagnosis of disease recurrence. ROC analysis of the power of plasma cfDNA to distinguish between patients with or without recurrence yielded an area under the curve of 0.825, with optimal sensitivity and specificity of 80.6% and 71.3%, respectively, at a cfDNA level of 12.93 ng/mL. Conclusions: High plasma cfDNA concentration is a potential molecular marker to signal disease recurrence in patients with high-risk neuroblastoma.

scholarly journals Increased plasma concentration of cell-free DNA precedes disease recurrence in children with high-risk neuroblastoma

2020 ◽  
Author(s):  
Yan Su ◽  
Lijun Wang ◽  
Chiyi Jiang ◽  
Zhixia Yue ◽  
Hongjun Fan ◽  
...  
Keyword(s):  
High Risk ◽  
Maintenance Treatment ◽  
Multidisciplinary Treatment ◽  
Area Under The Curve ◽  
Predictive Biomarkers ◽  
Disease Recurrence ◽  
High Rate ◽  
Roc Curve Analysis ◽  
Cell Free Dna ◽  
Free Dna

Abstract Background: Neuroblastoma is the most common extracranial solid tumor of childhood. The high rate of recurrence is associated with a low survival rate for patients with high-risk neuroblastoma. There is thus an urgent need to identify effective predictive biomarkers of disease recurrence. Methods: A total of 116 patients with high-risk neuroblastoma were recruited at Beijing Children’s Hospital between February 2015 and December 2017. All patients received multidisciplinary treatment, were evaluated for the therapeutic response, and then initiated on maintenance treatment. Blood samples were collected at the beginning of maintenance treatment, every 3 months thereafter, and at the time of disease recurrence. Plasma levels of cell-free DNA (cfDNA) were quantified by qPCR. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the ability of plasma cfDNA concentration to predict recurrence. Results: Of the 116 patients, 36 (31.0%) developed recurrence during maintenance treatment. The median time to recurrence was 19.00, 9.00, and 8.00 months for patients who had achieved complete response (n = 6), partial response (n = 25), and stable disease (n = 5), respectively, after multidisciplinary treatment. The median plasma cfDNA concentration at the time of recurrence was significantly higher than the concentration in recurrence-free patients throughout maintenance treatment (29.34 ng/mL vs 10.32 ng/mL). Patients recorded a plasma cfDNA level ≥29 ng/mL an average of 0.55 months before diagnosis of disease recurrence. ROC analysis of the power of plasma cfDNA to distinguish between patients with or without recurrence yielded an area under the curve of 0.825, with optimal sensitivity and specificity of 80.6% and 71.3%, respectively, at a cfDNA level of 12.93 ng/mL. Conclusions: High plasma cfDNA concentration is a potential molecular marker to signal disease recurrence in patients with high-risk neuroblastoma.

354 Pre-operative Risk Score Predicts 30-day Mortality Following Subdural Hematoma Evacuation

Neurosurgery ◽  
2017 ◽  
Vol 64 (CN_suppl_1) ◽  
pp. 281-281
Author(s):  
Samuel Tomlinson ◽  
Joseph Van Galen ◽  
Alexis E Zavez ◽  
Keaton Piper ◽  
Kristopher T Kimmell ◽  
...  
Keyword(s):  
High Risk ◽  
Risk Score ◽  
Subdural Hematoma ◽  
Area Under The Curve ◽  
High Sensitivity ◽  
International Classification Of Diseases ◽  
Improvement Program ◽  
Emergency Case ◽  
Classification Of Diseases ◽  
Wbc Count

Abstract INTRODUCTION Subdural hematoma (SDH) evacuation is a common neurosurgical procedure with high risk for morbidity and mortality. The purpose of this study was to develop a risk score for 30-day mortality following SDH evacuation on the basis of readily available pre-operative information. METHODS Data recorded in the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database between 2006 and 2014 were selected on the basis of ICD-9 (International Classification of Diseases, Ninth ed.) and CPT (Current Procedural Terminology) coding. Sequential univariate and multivariate analyses were used to identify significant independent predictors of 30-day mortality among 32 pre- operative factors. Multivariate regression coefficients were used to develop a weighted risk score capable of separating outcome groups with high sensitivity and specificity. RESULTS >Following list-wise exclusion of patients with incomplete datasets, 1271 patients (35.6% F; median age 73.0 years, IQR 44.1-89.0 years) were examined. Sequential univariate and multivariate analysis identified seven independent predictors of 30-day mortality (OR = adjusted odds ratio): emergency case (OR 2.27), age >= 65 years (OR 2.42), ventilator dependent status (OR 4.95), dialysis (OR 5.16), bleeding disorder (OR 2.37), WBC count >= 10,000 mu;L-1 (OR 1.79), and platelets <150,000 μL-1 (OR 2.18). Receiver operating characteristic (ROC) analysis demonstrated impressive outcome discrimination (area under the curve = 0.82, CI 5–95% = 0.78 0.86). Optimal score threshold was used to identify high-risk (mortality 35.0%) and low-risk (mortality 6.33%) patient groups. CONCLUSION We demonstrate a novel risk score capable of classifying patients based on 30-day postsurgical mortality. Application will provide an improved means of predicting outcomes for patients undergoing craniotomy or craniectomy for SDH evacuation.

scholarly journals Improving CHA2DS2-VASc stratification of non-fatal stroke and mortality risk using the Intermountain Mortality Risk Score among patients with atrial fibrillation

Open Heart ◽  
2018 ◽  
Vol 5 (2) ◽  
pp. e000907 ◽  
Author(s):  
Kevin G Graves ◽  
Heidi T May ◽  
Kirk U Knowlton ◽  
Joseph B Muhlestein ◽  
Victoria Jacobs ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
High Risk ◽  
Risk Score ◽  
Mortality Risk ◽  
Cox Regression ◽  
Complete Blood Count ◽  
Predictive Ability ◽  
Stroke Mortality ◽  
Fatal Stroke ◽  
Systemic Nature

BackgroundOral anticoagulation (OAC) therapy guidelines recommend using CHA2DS2-VASc to determine OAC need in atrial fibrillation (AF). A usable tool, CHA2DS2-VASc is challenged by its predictive ability. Applying components of the complete blood count and basic metabolic profile, the Intermountain Mortality Risk Score (IMRS) has been extensively validated. This study evaluated whether use of IMRS with CHA2DS2-VASc in patients with AF improves prediction.MethodsPatients with AF undergoing cardiac catheterisation (N=10 077) were followed for non-fatal stroke and mortality (mean 5.8±4.1 years, maximum 19 years). CHA2DS2-VASc and IMRS were calculated at baseline. IMRS categories were defined based on previously defined criteria. Cox regression was adjusted for demographic, clinical and treatment variables not included in IMRS or CHA2DS2-VASc.ResultsIn women (n=4122, mean age 71±12 years), the composite of non-fatal stroke/mortality was stratified (all p-trend <0.001) by CHA2DS2-VASc (1: 12.6%, 2: 22.8%, >2: 48.1%) and IMRS (low: 17.8%, moderate: 40.9%, high risk: 64.5%), as it was for men (n=5955, mean age 68±12 years) by CHA2DS2-VASc (<2: 15.7%, 2: 30.3%, >2: 51.8%) and IMRS (low: 19.0%, moderate: 42.0%, high risk: 65.9%). IMRS stratified stroke/mortality (all p-trend <0.001) in each CHA2DS2-VASc category.ConclusionsUsing IMRS jointly with CHA2DS2-VASc in patients with AF improved the prediction of stroke and mortality. For example, in patients at the OAC treatment threshold (CHA2DS2 -VASc = 2), IMRS provided ≈4-fold separation between low and high risk. IMRS provides an enhancing marker for risk in patients with AF that reflects the underlying systemic nature of this disease that may be considered in combination with the CHA2DS2-VASc score.

Sign in / Sign up

Export Citation Format

Share Document