Development of Multivariable Models to Predict and Benchmark Transfusion in Elective Surgery Supporting Patient Blood Management

Hayn, Dieter; Kreiner, Karl; Ebner, Hubert; Kästner, Peter; Breznik, Nada; Rzepka, Angelika; Hofmann, Axel; Gombotz, Hans; Schreier, Günter

doi:10.4338/aci-2016-11-ra-0195

Cited by 23 publications

(19 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predicting the number of patients transfused during their hospital stay will likely be useful for two different reasons. First of all, it enables reliable management of the supply chain for allogeneic blood, 6,7 but more importantly, it also could help to classify the risk profile of an individual patient to undergo transfusion, 11 pointing out the necessity in this specific patient to implement the measures of PBM as thoroughly as possible. However, at the time point of hospital admission, only a very low number of features is known that could help to predict the necessity for transfusion in the following time course.…”

Section: Discussionmentioning

confidence: 99%

“…Therefore, prediction of transfusion needs might also help to economize the supply chain of blood providers. 7 There are several publications that describe the influencing factors on perioperative transfusion, [8][9][10] but to date only small studies exist [11][12][13] that evaluate a multimodal, machine learning-based prediction model in a large jurisdictional cohort. Therefore, it is the aim of this study to evaluate a machine learning-based prediction model, based on a large cohort, and to test this model by cross validation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning–based prediction of transfusion

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background The ability to predict transfusions arising during hospital admission might enable economized blood supply management and might furthermore increase patient safety by ensuring a sufficient stock of red blood cells (RBCs) for a specific patient. We therefore investigated the precision of four different machine learning–based prediction algorithms to predict transfusion, massive transfusion, and the number of transfusions in patients admitted to a hospital. Study Design and Methods This was a retrospective, observational study in three adult tertiary care hospitals in Western Australia between January 2008 and June 2017. Primary outcome measures for the classification tasks were the area under the curve for the receiver operating characteristics curve, the F1 score, and the average precision of the four machine learning algorithms used: neural networks (NNs), logistic regression (LR), random forests (RFs), and gradient boosting (GB) trees. Results Using our four predictive models, transfusion of at least 1 unit of RBCs could be predicted rather accurately (sensitivity for NN, LR, RF, and GB: 0.898, 0.894, 0.584, and 0.872, respectively; specificity: 0.958, 0.966, 0.964, 0.965). Using the four methods for prediction of massive transfusion was less successful (sensitivity for NN, LR, RF, and GB: 0.780, 0.721, 0.002, and 0.797, respectively; specificity: 0.994, 0.995, 0.993, 0.995). As a consequence, prediction of the total number of packed RBCs transfused was also rather inaccurate. Conclusion This study demonstrates that the necessity for intrahospital transfusion can be forecasted reliably, however the amount of RBC units transfused during a hospital stay is more difficult to predict.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine learning–based prediction of transfusion

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition to the economic aspect, a successful patient blood management system diminishes unnecessary allocations of blood bags, which remain available for the patients that actually need transfusions. Some previous works (Sadana et al 2000, Hayn, 2017 focused their attention on the optimization of blood transfusion. The latter describes how predictive modelling and machine learning tools applied on pre-operative data can be used to predict the amount of red blood cells to be transfused during surgery and to prospectively optimize blood ordering schedules.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Cost-Saving Machine Learning Methods for Patient Blood Management

2020

Proceedings of the 12th International Conference on E-Health (EH2020)

View full text Add to dashboard Cite

Our objective is the development of cost-saving methods for the patient blood management in Galeazzi Orthopedic Institute, a large Italian hospital. The methods have been developed in relation to the known costs of the hospital, both in terms of unused blood bags and drugs. Observational data about 4593 patients have been retrieved, with anagraphical and pre-operational clinical features. Model's performances have been compared to an existing baseline in terms of both accuracy measures (F1, recall, AUC) and saved costs per patient. The proposed methods recorded an enhancement of performances for the adopted measures, demonstrating a possible useful application of machine-learning-based methods for the patient blood management task.

show abstract

“…Intelligent health data analytics is now being employed to generate innovative data-driven healthcare services such as (a) precision medicine, 9 (b) prediction of disease trends and outcomes, 10 (c) lifetime health, 11 (d) point-of-care diagnostic and therapeutic decision support, [12][13][14] (e) ethnographic health surveillance, 15 and (f) health system utilization optimization. 16 Artificial intelligence in medicine/health (better termed as AI in healthcare) is an emerging scientific area that aims to generate healthcare intelligence by analyzing health data. 17 To put in context, AI-based methods have been around since the 1970s and have been applied for medical expert systems, medical image analysis, healthcare knowledge management, and patient education.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Intelligent health data analytics: A convergence of artificial intelligence and big data

Abidi

2019

Healthc Manage Forum

View full text Add to dashboard Cite

Healthcare is a living system that generates a significant volume of heterogeneous data. As healthcare systems are pivoting to value-based systems, intelligent and interactive analysis of health data is gaining significance for health system management, especially for resource optimization whilst improving care quality and health outcomes. Health data analytics is being influenced by new concepts and intelligent methods emanating from artificial intelligence and big data. In this article, we contextualize health data and health data analytics in terms of the emerging trends of artificial intelligence and big data. We examine the nature of health data using the big data criterion to understand “how big” is health data. Next, we explain the working of artificial intelligence–based data analytics methods and discuss “what insights” can be derived from a broad spectrum of health data analytics methods to improve health system management, health outcomes, knowledge discovery, and healthcare innovation.

show abstract

Development of Multivariable Models to Predict and Benchmark Transfusion in Elective Surgery Supporting Patient Blood Management

Abstract: We conclude that predictive modeling can be used to benchmark the importance of different features on the models derived with data from different hospitals. This might help to optimize crucial processes in a specific hospital, even in other scenarios beyond Patient Blood Management.

Cited by 23 publications

References 19 publications

Machine learning–based prediction of transfusion

Machine learning–based prediction of transfusion

Evaluation of Cost-Saving Machine Learning Methods for Patient Blood Management

Intelligent health data analytics: A convergence of artificial intelligence and big data

Contact Info

Product

Resources

About