Using Interpretable Artificial Intelligence Algorithms in the Management of Blunt Splenic Trauma: Applications of Optimal Policy Trees as a Treatment Prescription Aid to Improve Patient Mortality

Background: The identification of the optimal management for blunt splenic trauma—angioembolization (AE), splenectomy, or observation—remains a challenge. This study applies Optimal Policy Trees (OPT), an artificial intelligence (AI) model, to prescribe appropriate management and improve in-hospital...

Full description

Saved in:
Bibliographic Details
Main Authors: Vahe S. Panossian, Yu Ma, Bolin Song, Jefferson A. Proaño-Zamudio, Veerle P. C. van Zon, Ikemsinachi C. Nzenwa, Azadeh Tabari, George C. Velmahos, Haytham M. A. Kaafarani, Dimitris Bertsimas, Dania Daye
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/12/4/336
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144165208260608
author Vahe S. Panossian
Yu Ma
Bolin Song
Jefferson A. Proaño-Zamudio
Veerle P. C. van Zon
Ikemsinachi C. Nzenwa
Azadeh Tabari
George C. Velmahos
Haytham M. A. Kaafarani
Dimitris Bertsimas
Dania Daye
author_facet Vahe S. Panossian
Yu Ma
Bolin Song
Jefferson A. Proaño-Zamudio
Veerle P. C. van Zon
Ikemsinachi C. Nzenwa
Azadeh Tabari
George C. Velmahos
Haytham M. A. Kaafarani
Dimitris Bertsimas
Dania Daye
author_sort Vahe S. Panossian
collection DOAJ
description Background: The identification of the optimal management for blunt splenic trauma—angioembolization (AE), splenectomy, or observation—remains a challenge. This study applies Optimal Policy Trees (OPT), an artificial intelligence (AI) model, to prescribe appropriate management and improve in-hospital mortality. Methods: OPTs were trained on patients with blunt splenic injuries in the ACS-TQIP 2013–2019 to prescribe one of the three interventions: splenectomy, angioembolization (AE), or observation. Prescriptive trees were derived in two separate patient cohorts: those who presented with a systolic blood pressure (SBP) < 70 mmHg and those with an SBP ≥ 70 mmHg. Splenic injury severity was graded using the American Association of Surgical Trauma (AAST) grading scale. Counterfactual estimation was used to predict the effects of interventions on overall in-hospital mortality. Results: Among 54,345 patients, 3.1% underwent splenic AE, 13.1% splenectomy, and 83.8% were managed with observation. In patients with SBP < 70 mmHg, AE was recommended for shock index (SI) < 1.5 or without transfusion, while splenectomy was indicated for SI ≥ 1.5 with transfusion. For patients with SBP ≥ 70 mmHg, AE was recommended for AAST grades 4–5, or grades 1–3 with SI ≥ 1.2; observation was recommended for grades 1–3 with SI < 1.2. Predicted mortality using OPT-prescribed treatments was 18.4% for SBP < 70 mmHg and 4.97% for SBP ≥ 70 mmHg, compared to observed rates of 36.46% and 7.60%, respectively. Conclusions: Interpretable AI models may serve as a decision aid to improve mortality in patients presenting with a blunt splenic injury. Our data-driven prescriptive OPT models may aid in prescribing the appropriate management in this patient cohort based on their characteristics.
format Article
id doaj-art-b10ddec65adf4745a1e5a04f401d3c75
institution OA Journals
issn 2306-5354
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-b10ddec65adf4745a1e5a04f401d3c752025-08-20T02:28:27ZengMDPI AGBioengineering2306-53542025-03-0112433610.3390/bioengineering12040336Using Interpretable Artificial Intelligence Algorithms in the Management of Blunt Splenic Trauma: Applications of Optimal Policy Trees as a Treatment Prescription Aid to Improve Patient MortalityVahe S. Panossian0Yu Ma1Bolin Song2Jefferson A. Proaño-Zamudio3Veerle P. C. van Zon4Ikemsinachi C. Nzenwa5Azadeh Tabari6George C. Velmahos7Haytham M. A. Kaafarani8Dimitris Bertsimas9Dania Daye10Division of Trauma, Emergency Surgery, Surgical Critical Care, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USAOperations Research Center, Massachusetts Institute of Technology, Cambridge, MA 02139, USAOperations Research Center, Massachusetts Institute of Technology, Cambridge, MA 02139, USADivision of Trauma, Emergency Surgery, Surgical Critical Care, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USADivision of Trauma, Emergency Surgery, Surgical Critical Care, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USADivision of Trauma, Emergency Surgery, Surgical Critical Care, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USADepartment of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USADivision of Trauma, Emergency Surgery, Surgical Critical Care, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USADivision of Trauma, Emergency Surgery, Surgical Critical Care, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USAOperations Research Center, Massachusetts Institute of Technology, Cambridge, MA 02139, USADepartment of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USABackground: The identification of the optimal management for blunt splenic trauma—angioembolization (AE), splenectomy, or observation—remains a challenge. This study applies Optimal Policy Trees (OPT), an artificial intelligence (AI) model, to prescribe appropriate management and improve in-hospital mortality. Methods: OPTs were trained on patients with blunt splenic injuries in the ACS-TQIP 2013–2019 to prescribe one of the three interventions: splenectomy, angioembolization (AE), or observation. Prescriptive trees were derived in two separate patient cohorts: those who presented with a systolic blood pressure (SBP) < 70 mmHg and those with an SBP ≥ 70 mmHg. Splenic injury severity was graded using the American Association of Surgical Trauma (AAST) grading scale. Counterfactual estimation was used to predict the effects of interventions on overall in-hospital mortality. Results: Among 54,345 patients, 3.1% underwent splenic AE, 13.1% splenectomy, and 83.8% were managed with observation. In patients with SBP < 70 mmHg, AE was recommended for shock index (SI) < 1.5 or without transfusion, while splenectomy was indicated for SI ≥ 1.5 with transfusion. For patients with SBP ≥ 70 mmHg, AE was recommended for AAST grades 4–5, or grades 1–3 with SI ≥ 1.2; observation was recommended for grades 1–3 with SI < 1.2. Predicted mortality using OPT-prescribed treatments was 18.4% for SBP < 70 mmHg and 4.97% for SBP ≥ 70 mmHg, compared to observed rates of 36.46% and 7.60%, respectively. Conclusions: Interpretable AI models may serve as a decision aid to improve mortality in patients presenting with a blunt splenic injury. Our data-driven prescriptive OPT models may aid in prescribing the appropriate management in this patient cohort based on their characteristics.https://www.mdpi.com/2306-5354/12/4/336traumaartificial intelligencespleendata-driven decision makingpersonalized medicine
spellingShingle Vahe S. Panossian
Yu Ma
Bolin Song
Jefferson A. Proaño-Zamudio
Veerle P. C. van Zon
Ikemsinachi C. Nzenwa
Azadeh Tabari
George C. Velmahos
Haytham M. A. Kaafarani
Dimitris Bertsimas
Dania Daye
Using Interpretable Artificial Intelligence Algorithms in the Management of Blunt Splenic Trauma: Applications of Optimal Policy Trees as a Treatment Prescription Aid to Improve Patient Mortality
Bioengineering
trauma
artificial intelligence
spleen
data-driven decision making
personalized medicine
title Using Interpretable Artificial Intelligence Algorithms in the Management of Blunt Splenic Trauma: Applications of Optimal Policy Trees as a Treatment Prescription Aid to Improve Patient Mortality
title_full Using Interpretable Artificial Intelligence Algorithms in the Management of Blunt Splenic Trauma: Applications of Optimal Policy Trees as a Treatment Prescription Aid to Improve Patient Mortality
title_fullStr Using Interpretable Artificial Intelligence Algorithms in the Management of Blunt Splenic Trauma: Applications of Optimal Policy Trees as a Treatment Prescription Aid to Improve Patient Mortality
title_full_unstemmed Using Interpretable Artificial Intelligence Algorithms in the Management of Blunt Splenic Trauma: Applications of Optimal Policy Trees as a Treatment Prescription Aid to Improve Patient Mortality
title_short Using Interpretable Artificial Intelligence Algorithms in the Management of Blunt Splenic Trauma: Applications of Optimal Policy Trees as a Treatment Prescription Aid to Improve Patient Mortality
title_sort using interpretable artificial intelligence algorithms in the management of blunt splenic trauma applications of optimal policy trees as a treatment prescription aid to improve patient mortality
topic trauma
artificial intelligence
spleen
data-driven decision making
personalized medicine
url https://www.mdpi.com/2306-5354/12/4/336
work_keys_str_mv AT vahespanossian usinginterpretableartificialintelligencealgorithmsinthemanagementofbluntsplenictraumaapplicationsofoptimalpolicytreesasatreatmentprescriptionaidtoimprovepatientmortality
AT yuma usinginterpretableartificialintelligencealgorithmsinthemanagementofbluntsplenictraumaapplicationsofoptimalpolicytreesasatreatmentprescriptionaidtoimprovepatientmortality
AT bolinsong usinginterpretableartificialintelligencealgorithmsinthemanagementofbluntsplenictraumaapplicationsofoptimalpolicytreesasatreatmentprescriptionaidtoimprovepatientmortality
AT jeffersonaproanozamudio usinginterpretableartificialintelligencealgorithmsinthemanagementofbluntsplenictraumaapplicationsofoptimalpolicytreesasatreatmentprescriptionaidtoimprovepatientmortality
AT veerlepcvanzon usinginterpretableartificialintelligencealgorithmsinthemanagementofbluntsplenictraumaapplicationsofoptimalpolicytreesasatreatmentprescriptionaidtoimprovepatientmortality
AT ikemsinachicnzenwa usinginterpretableartificialintelligencealgorithmsinthemanagementofbluntsplenictraumaapplicationsofoptimalpolicytreesasatreatmentprescriptionaidtoimprovepatientmortality
AT azadehtabari usinginterpretableartificialintelligencealgorithmsinthemanagementofbluntsplenictraumaapplicationsofoptimalpolicytreesasatreatmentprescriptionaidtoimprovepatientmortality
AT georgecvelmahos usinginterpretableartificialintelligencealgorithmsinthemanagementofbluntsplenictraumaapplicationsofoptimalpolicytreesasatreatmentprescriptionaidtoimprovepatientmortality
AT haythammakaafarani usinginterpretableartificialintelligencealgorithmsinthemanagementofbluntsplenictraumaapplicationsofoptimalpolicytreesasatreatmentprescriptionaidtoimprovepatientmortality
AT dimitrisbertsimas usinginterpretableartificialintelligencealgorithmsinthemanagementofbluntsplenictraumaapplicationsofoptimalpolicytreesasatreatmentprescriptionaidtoimprovepatientmortality
AT daniadaye usinginterpretableartificialintelligencealgorithmsinthemanagementofbluntsplenictraumaapplicationsofoptimalpolicytreesasatreatmentprescriptionaidtoimprovepatientmortality