Max Hahn-Klimroth1, Philipp Loick1, Soo-Zin Kim-Wanner2, Erhard Seifried2,3, Halvard Bonig4,5,6. 1. Goethe University Mathematics Institute, Frankfurt, Germany. 2. German Red Cross Blood Service BaWüHe, Institute Frankfurt, Sandhofstraße 1, 60528, Frankfurt, Germany. 3. Institute for Transfusion Medicine and Immunohematology, Goethe University, Frankfurt, Germany. 4. German Red Cross Blood Service BaWüHe, Institute Frankfurt, Sandhofstraße 1, 60528, Frankfurt, Germany. h.boenig@blutspende.de. 5. Institute for Transfusion Medicine and Immunohematology, Goethe University, Frankfurt, Germany. h.boenig@blutspende.de. 6. Department of Medicine/Hematology, University of Washington, Seattle, WA, USA. h.boenig@blutspende.de.
Abstract
BACKGROUND: The ability to approximate intra-operative hemoglobin loss with reasonable precision and linearity is prerequisite for determination of a relevant surgical outcome parameter: This information enables comparison of surgical procedures between different techniques, surgeons or hospitals, and supports anticipation of transfusion needs. Different formulas have been proposed, but none of them were validated for accuracy, precision and linearity against a cohort with precisely measured hemoglobin loss and, possibly for that reason, neither has established itself as gold standard. We sought to identify the minimal dataset needed to generate reasonably precise and accurate hemoglobin loss prediction tools and to derive and validate an estimation formula. METHODS: Routinely available clinical and laboratory data from a cohort of 401 healthy individuals with controlled hemoglobin loss between 29 and 233 g were extracted from medical charts. Supervised learning algorithms were applied to identify a minimal data set and to generate and validate a formula for calculation of hemoglobin loss. RESULTS: Of the classical supervised learning algorithms applied, the linear and Ridge regression models performed at least as well as the more complex models. Most straightforward to analyze and check for robustness, we proceeded with linear regression. Weight, height, sex and hemoglobin concentration before and on the morning after the intervention were sufficient to generate a formula for estimation of hemoglobin loss. The resulting model yields an outstanding R2 of 53.2% with similar precision throughout the entire range of volumes or donor sizes, thereby meaningfully outperforming previously proposed medical models. CONCLUSIONS: The resulting formula will allow objective benchmarking of surgical blood loss, enabling informed decision making as to the need for pre-operative type-and-cross only vs. reservation of packed red cell units, depending on a patient's anemia tolerance, and thus contributing to resource management.
BACKGROUND: The ability to approximate intra-operative hemoglobin loss with reasonable precision and linearity is prerequisite for determination of a relevant surgical outcome parameter: This information enables comparison of surgical procedures between different techniques, surgeons or hospitals, and supports anticipation of transfusion needs. Different formulas have been proposed, but none of them were validated for accuracy, precision and linearity against a cohort with precisely measured hemoglobin loss and, possibly for that reason, neither has established itself as gold standard. We sought to identify the minimal dataset needed to generate reasonably precise and accurate hemoglobin loss prediction tools and to derive and validate an estimation formula. METHODS: Routinely available clinical and laboratory data from a cohort of 401 healthy individuals with controlled hemoglobin loss between 29 and 233 g were extracted from medical charts. Supervised learning algorithms were applied to identify a minimal data set and to generate and validate a formula for calculation of hemoglobin loss. RESULTS: Of the classical supervised learning algorithms applied, the linear and Ridge regression models performed at least as well as the more complex models. Most straightforward to analyze and check for robustness, we proceeded with linear regression. Weight, height, sex and hemoglobin concentration before and on the morning after the intervention were sufficient to generate a formula for estimation of hemoglobin loss. The resulting model yields an outstanding R2 of 53.2% with similar precision throughout the entire range of volumes or donor sizes, thereby meaningfully outperforming previously proposed medical models. CONCLUSIONS: The resulting formula will allow objective benchmarking of surgical blood loss, enabling informed decision making as to the need for pre-operative type-and-cross only vs. reservation of packed red cell units, depending on a patient's anemia tolerance, and thus contributing to resource management.
Entities:
Keywords:
Anemia management; Blood loss calculator; Blood loss formula; Blood management; Machine learning; Surgical blood loss
Authors: Michal Radomski; Mazen Zenati; Stephanie Novak; Vernissia Tam; Jennifer Steve; David L Bartlett; Amer H Zureikat; Herbert J Zeh; Melissa E Hogg Journal: Am J Surg Date: 2017-09-18 Impact factor: 2.565
Authors: Pamela T Soliman; Michael Frumovitz; Charlotte C Sun; Ricardo Dos Reis; Kathleen M Schmeler; Alpa M Nick; Shannon N Westin; Jubilee Brown; Charles F Levenback; Pedro T Ramirez Journal: Gynecol Oncol Date: 2011-08-27 Impact factor: 5.482