Machine Learning Applied to Registry Data: Development of a Patient-Specific Prediction Model for Blood Transfusion Requirements During Craniofacial Surgery Using the Pediatric Craniofacial Perioperative Registry Dataset

2020 ◽  
Vol 132 (1) ◽  
pp. 160-171 ◽  
Author(s):  
Ali Jalali ◽  
Hannah Lonsdale ◽  
Lillian V. Zamora ◽  
Luis Ahumada ◽  
Anh Thy H. Nguyen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Blood Transfusion ◽  
Prediction Model ◽  
Craniofacial Surgery ◽  
Registry Data ◽  
Patient Specific ◽  
Transfusion Requirements ◽  
Specific Prediction

Efficacy of aprotinin in children undergoing craniofacial surgery

2003 ◽  
Vol 99 (2) ◽  
pp. 287-290 ◽  
Author(s):  
Celia C. D'Errico ◽  
Hamish M. Munro ◽  
Steven R. Buchman ◽  
Deborah Wagner ◽  
Karin M. Muraszko
Keyword(s):  
Placebo Group ◽  
Blood Transfusion ◽  
Pediatric Patients ◽  
Craniofacial Surgery ◽  
Blood Transfusions ◽  
Double Blind ◽  
Craniofacial Reconstruction ◽  
Content Type ◽  
Transfusion Requirements ◽  
Fine Print

Object. This prospective, randomized, placebo-controlled, double-blind trial was undertaken to assess the efficacy of aprotinin in reducing the need for blood transfusions in 39 children undergoing reconstructive craniofacial surgery. Methods. Two demographically similar groups—a total of 39 patients with a mean age of 1.2 ± 1.2 years—were studied. The efficacy of aprotinin (240 mg/m2 administered intravenously over 20 minutes, followed by infusions of 56 mg/m2/hr) was compared with that of an equal infusion of 0.9% saline (placebo). Patients in the aprotinin group received less blood per kilogram of body weight than patients in the placebo group (32 ± 25 ml/kg compared with 52 ± 34 ml/kg, respectively; p = 0.04). Those patients in whom aprotinin was administered experienced less change in their hematocrit levels during surgery (aprotinin −33 ± 13% compared with placebo −44 ± 9%, p = 0.01). Each patient underwent a transfusion as per study protocol, and there was no significant change in hematocrit levels from the beginning to the end of surgery. The surgical faculty judged blood loss in patients in the aprotinin group to be significantly less than usual (p = 0.03). The use of aprotinin was also associated with reduced blood transfusion requirements during the first 3 postoperative days (p = 0.03). There was no adverse event reported in either the aprotinin or placebo group. Conclusions. Aprotinin decreased blood transfusion requirements in pediatric patients undergoing craniofacial reconstruction, thereby reducing the risks associated with exposure to banked blood components.

scholarly journals A 3D insulin sensitivity prediction model enables more patient-specific prediction and model-based glycaemic control

2018 ◽  
Vol 46 ◽  
pp. 192-200 ◽  
Author(s):  
Vincent Uyttendaele ◽  
Jennifer L. Knopp ◽  
Kent W. Stewart ◽  
Thomas Desaive ◽  
Balázs Benyó ◽  
...  
Keyword(s):  
Insulin Sensitivity ◽  
Glycaemic Control ◽  
Prediction Model ◽  
Patient Specific ◽  
Model Based ◽  
Specific Prediction

scholarly journals 768. Use of a Machine-Learning-based Prediction Model to Guide Antibiotic De-escalation in the Treatment of Urinary Tract Infections

2019 ◽  
Vol 6 (Supplement_2) ◽  
pp. S342-S342
Author(s):  
Jonathan Huggins ◽  
Keith W Hamilton ◽  
Ian Barnett
Keyword(s):  
Machine Learning ◽  
Prediction Model ◽  
Learning Algorithm ◽  
Area Under The Curve ◽  
High Specificity ◽  
Patient Specific ◽  
Brier Score ◽  
Cross Sectional ◽  
Usual Practice ◽  
Tract Infections

Abstract Background A patient-specific antibiogram (PS-ABG) issues personalized predicted antibiotic susceptibility results by incorporating patient factors into a prediction model. Predictions, reported as percent likelihood of susceptibility, are available to providers in real-time. In this study, we evaluated the performance characteristics of a PS-ABG based on a machine-learning algorithm in predicting susceptibility of Enterobacteriaceae isolated on urine cultures. Methods This cross-sectional study included 2,517 urine cultures with Enterobacteriaceae collected from 2,211 unique patients over a 12-week period from January 1 through April 15, 2019 in a single health system. Receiver operating curves (ROC) were generated for commonly prescribed antibiotics to assess discrimination. Threshold values to determine when an antibiotic could be used were then determined based on ROC curves. Brier scores were generated for all antibiotics collectively and for individual antibiotics to evaluate the accuracy of the predictions compared with that of the usual practice (UP) of traditional antibiograms. Results The ability of the PS-ABG to discriminate susceptible and nonsusceptible isolates varied by antibiotic [area under the curve (AUC) range: 0.71 - 0.95]. When all antibiotics were considered, AUC was 0.88 (95% C.I. 0.88 – 0.89). Brier score ranged from 0.0037 - 0.2087, representing between a 9 - 56% improvement compared with UP. For all antibiotics, the software had a 32% improvement over UP (median Brier score 0.0794 v. 0.1114, P < 0.0001). Overall, a susceptibility threshold of 95% was associated with a specificity of 96%. A threshold of 95% was associated with a ≥90% specificity in all agents except for cefepime (specificity 70%) and meropenem (specificity 73%). For cefepime and meropenem, specificity reached 90% at a threshold of 97%. Conclusion The PS-ABG demonstrated excellent discriminatory power for all antibiotics tested and was more accurate than UP. A cutoff of 95% likelihood of susceptibility affords high specificity for most agents and may be a reasonable threshold for selecting an appropriate antibiotic. A higher susceptibility threshold yields similar specificity for cefepime and meropenem, but this finding is likely a result of the low number of resistant isolates. Disclosures All authors: No reported disclosures.

Machine-learning-based patient-specific prediction models for knee osteoarthritis

2018 ◽  
Vol 15 (1) ◽  
pp. 49-60 ◽  
Author(s):  
Afshin Jamshidi ◽  
Jean-Pierre Pelletier ◽  
Johanne Martel-Pelletier
Keyword(s):  
Machine Learning ◽  
Knee Osteoarthritis ◽  
Prediction Models ◽  
Patient Specific ◽  
Specific Prediction

scholarly journals Explainable Machine Learning Model for Glaucoma Diagnosis and Its Interpretation

Diagnostics ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 510
Author(s):  
Sejong Oh ◽  
Yuli Park ◽  
Kyong Jin Cho ◽  
Seong Jae Kim
Keyword(s):  
Machine Learning ◽  
Prediction Model ◽  
Diagnostic Performance ◽  
Prediction Models ◽  
Disease Diagnosis ◽  
Learning Model ◽  
Fundus Photography ◽  
Support Vector ◽  
Machine Learning Model ◽  
Specific Prediction

The aim is to develop a machine learning prediction model for the diagnosis of glaucoma and an explanation system for a specific prediction. Clinical data of the patients based on a visual field test, a retinal nerve fiber layer optical coherence tomography (RNFL OCT) test, a general examination including an intraocular pressure (IOP) measurement, and fundus photography were provided for the feature selection process. Five selected features (variables) were used to develop a machine learning prediction model. The support vector machine, C5.0, random forest, and XGboost algorithms were tested for the prediction model. The performance of the prediction models was tested with 10-fold cross-validation. Statistical charts, such as gauge, radar, and Shapley Additive Explanations (SHAP), were used to explain the prediction case. All four models achieved similarly high diagnostic performance, with accuracy values ranging from 0.903 to 0.947. The XGboost model is the best model with an accuracy of 0.947, sensitivity of 0.941, specificity of 0.950, and AUC of 0.945. Three statistical charts were established to explain the prediction based on the characteristics of the XGboost model. Higher diagnostic performance was achieved with the XGboost model. These three statistical charts can help us understand why the machine learning model produces a specific prediction result. This may be the first attempt to apply “explainable artificial intelligence” to eye disease diagnosis.

Sign in / Sign up

Export Citation Format

Share Document