東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Improving the Efficiency and Effecti...

Medow, Joshua.

FindBook

Google Book

Amazon

博客來

Improving the Efficiency and Effectiveness of Chronic Blood Transfusions in the Hematology Clinic Using an Adaptive Algorithm Designed to Optimize Red Cell Use in Patients with Different Specific Transfusion Needs.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Improving the Efficiency and Effectiveness of Chronic Blood Transfusions in the Hematology Clinic Using an Adaptive Algorithm Designed to Optimize Red Cell Use in Patients with Different Specific Transfusion Needs./
作者:	Medow, Joshua.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2019,
面頁冊數:	140 p.
附註:	Source: Dissertations Abstracts International, Volume: 80-10, Section: B.
Contained By:	Dissertations Abstracts International80-10B.
標題:	Information Technology. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13810486
ISBN:	9781392019924

Improving the Efficiency and Effectiveness of Chronic Blood Transfusions in the Hematology Clinic Using an Adaptive Algorithm Designed to Optimize Red Cell Use in Patients with Different Specific Transfusion Needs.
Medow, Joshua.

Improving the Efficiency and Effectiveness of Chronic Blood Transfusions in the Hematology Clinic Using an Adaptive Algorithm Designed to Optimize Red Cell Use in Patients with Different Specific Transfusion Needs. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 140 p.

Source: Dissertations Abstracts International, Volume: 80-10, Section: B.

Thesis (Ph.D.)--The University of Wisconsin - Madison, 2019.

This item must not be sold to any third party vendors.

Background: Patients with myelodysplastic disorders who require chronic transfusions are often given packed red blood cells (PRBCs) based on a care plan that is copied over from previous visits. This has resulted in transfusions when the patient likely did not require one. A better approach would be to set a target hemoglobin level upon return to clinic. However, there is significant variability in response to PRBC transfusions due to disease progression and marrow suppressive chemotherapy. This can make both the dosing and the timing of transfusion difficult to predict, underscoring the need for an individualized model to guide PRBC transfusions. Based on this a computer algorithm for decision support that individualizes transfusion recommendations for myelodysplastic patients. Methods: The Digital Intern (iVMD) algorithm for transfusion prediction was implemented to predict the response to the transfusion being ordered. The calculator pulls information from the electronic medical record (EMR) (Epic Systems) to calculate transfusion half-lives for up to 6 prior transfusions. These half-lives are used predict the response to transfusion given the patients current hemoglobin and weight. These options are then presented to the ordering provider for the transfusion dose, in PRBC units, and the follow-up time over which the patient is expected to stay at or above the selected target Hgb. We performed a prospective trial over a 12-month period evaluating the proximity of the model to the return hemoglobin level and return date with the primary outcome being the percentage of patients that return with a hemoglobin at or above the selected target (within 0.5g/dL) in an intent to treat fashion. We also compared the number of 1 vs multi-unit PRBC transfusions and total number of PRBC units transfused using the predictive algorithm vs those not using the predictive algorithm during the same time period. Results: Over 12 months, PRBC transfusions were ordered using the predictive algorithm of which 117 had complete data for analysis. A target hemoglobin of 8 was selected in 80% of cases. PRBC transfusions were 45% for single unit and 55% were two units which represents a significant increase in single unit transfusions from non-algorithm patients treated at the same time meaning that multi-unit PRBC transfusions were significantly reduced for the short-term follow-up that these patients often receive. The total number of units transfused also was reduced compared to historical and simultaneous controls. The mean predicted time to return after transfusion was 10.5 days and 75% of patients had follow-up within 3 days of the predictive algorithm selected return time. Overall 90.6% of patients returned with a hemoglobin at or above target. Conclusion: The predictive algorithm reduces the number of PRBC transfusions and the number of multi-unit transfusions prospectively. Simultaneously, over 90% of patients remained at or above the target hemoglobin selected by the ordering provider. Further studies to expand the role of this and other adaptive algorithm technologies should be done because they have the potential to reduce costs and improve outcomes. If applied correctly, artificial intelligence may significantly impact the future of quality medical care provided worldwide.

ISBN: 9781392019924Subjects--Topical Terms:

1030799
Information Technology.

Improving the Efficiency and Effectiveness of Chronic Blood Transfusions in the Hematology Clinic Using an Adaptive Algorithm Designed to Optimize Red Cell Use in Patients with Different Specific Transfusion Needs.
LDR:04569nmm a2200337 4500 001 2208031
005 20190929184032.5
008 201008s2019 ||||||||||||||||| ||eng d
020 $a 9781392019924
035 $a (MiAaPQ)AAI13810486
035 $a (MiAaPQ)wisc:16053
035 $a AAI13810486
040 $a MiAaPQ $c MiAaPQ
100 1 $a Medow, Joshua. $3 3435040
245 1 0 $a Improving the Efficiency and Effectiveness of Chronic Blood Transfusions in the Hematology Clinic Using an Adaptive Algorithm Designed to Optimize Red Cell Use in Patients with Different Specific Transfusion Needs.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 140 p.
500 $a Source: Dissertations Abstracts International, Volume: 80-10, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Mendonca, Eneida.
502 $a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2019.
506 $a This item must not be sold to any third party vendors.
520 $a Background: Patients with myelodysplastic disorders who require chronic transfusions are often given packed red blood cells (PRBCs) based on a care plan that is copied over from previous visits. This has resulted in transfusions when the patient likely did not require one. A better approach would be to set a target hemoglobin level upon return to clinic. However, there is significant variability in response to PRBC transfusions due to disease progression and marrow suppressive chemotherapy. This can make both the dosing and the timing of transfusion difficult to predict, underscoring the need for an individualized model to guide PRBC transfusions. Based on this a computer algorithm for decision support that individualizes transfusion recommendations for myelodysplastic patients. Methods: The Digital Intern (iVMD) algorithm for transfusion prediction was implemented to predict the response to the transfusion being ordered. The calculator pulls information from the electronic medical record (EMR) (Epic Systems) to calculate transfusion half-lives for up to 6 prior transfusions. These half-lives are used predict the response to transfusion given the patients current hemoglobin and weight. These options are then presented to the ordering provider for the transfusion dose, in PRBC units, and the follow-up time over which the patient is expected to stay at or above the selected target Hgb. We performed a prospective trial over a 12-month period evaluating the proximity of the model to the return hemoglobin level and return date with the primary outcome being the percentage of patients that return with a hemoglobin at or above the selected target (within 0.5g/dL) in an intent to treat fashion. We also compared the number of 1 vs multi-unit PRBC transfusions and total number of PRBC units transfused using the predictive algorithm vs those not using the predictive algorithm during the same time period. Results: Over 12 months, PRBC transfusions were ordered using the predictive algorithm of which 117 had complete data for analysis. A target hemoglobin of 8 was selected in 80% of cases. PRBC transfusions were 45% for single unit and 55% were two units which represents a significant increase in single unit transfusions from non-algorithm patients treated at the same time meaning that multi-unit PRBC transfusions were significantly reduced for the short-term follow-up that these patients often receive. The total number of units transfused also was reduced compared to historical and simultaneous controls. The mean predicted time to return after transfusion was 10.5 days and 75% of patients had follow-up within 3 days of the predictive algorithm selected return time. Overall 90.6% of patients returned with a hemoglobin at or above target. Conclusion: The predictive algorithm reduces the number of PRBC transfusions and the number of multi-unit transfusions prospectively. Simultaneously, over 90% of patients remained at or above the target hemoglobin selected by the ordering provider. Further studies to expand the role of this and other adaptive algorithm technologies should be done because they have the potential to reduce costs and improve outcomes. If applied correctly, artificial intelligence may significantly impact the future of quality medical care provided worldwide.
590 $a School code: 0262.
650 4 $a Information Technology. $3 1030799
650 4 $a Medicine. $3 641104
650 4 $a Bioinformatics. $3 553671
690 $a 0489
690 $a 0564
690 $a 0715
710 2 $a The University of Wisconsin - Madison. $b Clinical Investigation. $3 2103709
773 0 $t Dissertations Abstracts International $g 80-10B.
790 $a 0262
791 $a Ph.D.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13810486