Real-world performance analysis of a universal computational reasoning model for precision oncology in lung cancer

Abstract Tumors harbor multiple genetic alterations, yet treatment decisions are commonly based on single biomarkers, leading to underutilization of genomic information by comprehensive molecular tests, uncertainty in clinical practice, and frequent treatment failures. Although molecular tumor board...

Full description

Saved in:
Bibliographic Details
Main Authors: Anna Dirner, Dóra Kormos, Dóra Lakatos, Márton Bolyácz, Mária Kocsis-Steinbach, Gábor György Kalmár, Dóra Tihanyi, Ákos Takács, Ákos Boldizsár, Viktor Kardos, Réka Szalkai-Dénes, Barbara Vodicska, Edit Várkondi, Júlia Déri, Gábor Pajkos, Dóra Mathiász, István Vályi-Nagy, Richárd Schwáb, Maud Kamal, Christian Rolfo, Arkadiusz Z. Dudek, Christophe Le Tourneau, Róbert Dóczi, László Urbán, István Peták
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:npj Precision Oncology
Online Access:https://doi.org/10.1038/s41698-025-00943-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849705130469883904
author Anna Dirner
Dóra Kormos
Dóra Lakatos
Márton Bolyácz
Mária Kocsis-Steinbach
Gábor György Kalmár
Dóra Tihanyi
Ákos Takács
Ákos Boldizsár
Viktor Kardos
Réka Szalkai-Dénes
Barbara Vodicska
Edit Várkondi
Júlia Déri
Gábor Pajkos
Dóra Mathiász
István Vályi-Nagy
Richárd Schwáb
Maud Kamal
Christian Rolfo
Arkadiusz Z. Dudek
Christophe Le Tourneau
Róbert Dóczi
László Urbán
István Peták
author_facet Anna Dirner
Dóra Kormos
Dóra Lakatos
Márton Bolyácz
Mária Kocsis-Steinbach
Gábor György Kalmár
Dóra Tihanyi
Ákos Takács
Ákos Boldizsár
Viktor Kardos
Réka Szalkai-Dénes
Barbara Vodicska
Edit Várkondi
Júlia Déri
Gábor Pajkos
Dóra Mathiász
István Vályi-Nagy
Richárd Schwáb
Maud Kamal
Christian Rolfo
Arkadiusz Z. Dudek
Christophe Le Tourneau
Róbert Dóczi
László Urbán
István Peták
author_sort Anna Dirner
collection DOAJ
description Abstract Tumors harbor multiple genetic alterations, yet treatment decisions are commonly based on single biomarkers, leading to underutilization of genomic information by comprehensive molecular tests, uncertainty in clinical practice, and frequent treatment failures. Although molecular tumor boards can assist personalized treatments, this process is not scalable or standardized, resulting in highly discordant recommendations. Validated digital solutions for personalized decision support are highly needed. The Digital Drug Assignment (DDA) system is a computational reasoning model that scores treatment options based on the full tumor genomic data. We retrospectively analyzed data of 111 lung cancer patients and found that high-score MTAs (1000≦DDA score) provided significant clinical benefit over other treatments, in terms of ORR, PFS, and OS. These results demonstrate that the DDA system is predictive of relative benefit of the various agents used in lung cancer care. Digital drug assignment can potentially address challenges with complex molecular profiles in routine clinical settings.
format Article
id doaj-art-c799fd8cf4e44a478aef754e169db4ff
institution DOAJ
issn 2397-768X
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series npj Precision Oncology
spelling doaj-art-c799fd8cf4e44a478aef754e169db4ff2025-08-20T03:16:33ZengNature Portfolionpj Precision Oncology2397-768X2025-05-019111010.1038/s41698-025-00943-4Real-world performance analysis of a universal computational reasoning model for precision oncology in lung cancerAnna Dirner0Dóra Kormos1Dóra Lakatos2Márton Bolyácz3Mária Kocsis-Steinbach4Gábor György Kalmár5Dóra Tihanyi6Ákos Takács7Ákos Boldizsár8Viktor Kardos9Réka Szalkai-Dénes10Barbara Vodicska11Edit Várkondi12Júlia Déri13Gábor Pajkos14Dóra Mathiász15István Vályi-Nagy16Richárd Schwáb17Maud Kamal18Christian Rolfo19Arkadiusz Z. Dudek20Christophe Le Tourneau21Róbert Dóczi22László Urbán23István Peták24Genomate Health IncDepartment of Pulmonology, Mátraháza University and Teaching HospitalGenomate Health IncGenomate Health IncGenomate Health IncGenomate Health IncGenomate Health IncGenomate Health IncOncompass Medicine Hungary LtdDepartment of Pulmonology, Mátraháza University and Teaching HospitalGenomate Health IncGenomate Health IncOncompass Medicine Hungary LtdOncompass Medicine Hungary LtdOncompass Medicine Hungary LtdGenomate Health IncNational Hematology and Infectology Institute, Centrum Hospital of Southern PestMIND ClinicDepartment of Drug Development and Innovation (D3i), Institute CurieDivision of Medical Oncology, The James Comprehensive Cancer Center, Ohio State University, School of Medicine, ColumbusDivision of Oncology, Mayo ClinicDepartment of Drug Development and Innovation (D3i), Institute CurieGenomate Health IncDepartment of Pulmonology, Mátraháza University and Teaching HospitalGenomate Health IncAbstract Tumors harbor multiple genetic alterations, yet treatment decisions are commonly based on single biomarkers, leading to underutilization of genomic information by comprehensive molecular tests, uncertainty in clinical practice, and frequent treatment failures. Although molecular tumor boards can assist personalized treatments, this process is not scalable or standardized, resulting in highly discordant recommendations. Validated digital solutions for personalized decision support are highly needed. The Digital Drug Assignment (DDA) system is a computational reasoning model that scores treatment options based on the full tumor genomic data. We retrospectively analyzed data of 111 lung cancer patients and found that high-score MTAs (1000≦DDA score) provided significant clinical benefit over other treatments, in terms of ORR, PFS, and OS. These results demonstrate that the DDA system is predictive of relative benefit of the various agents used in lung cancer care. Digital drug assignment can potentially address challenges with complex molecular profiles in routine clinical settings.https://doi.org/10.1038/s41698-025-00943-4
spellingShingle Anna Dirner
Dóra Kormos
Dóra Lakatos
Márton Bolyácz
Mária Kocsis-Steinbach
Gábor György Kalmár
Dóra Tihanyi
Ákos Takács
Ákos Boldizsár
Viktor Kardos
Réka Szalkai-Dénes
Barbara Vodicska
Edit Várkondi
Júlia Déri
Gábor Pajkos
Dóra Mathiász
István Vályi-Nagy
Richárd Schwáb
Maud Kamal
Christian Rolfo
Arkadiusz Z. Dudek
Christophe Le Tourneau
Róbert Dóczi
László Urbán
István Peták
Real-world performance analysis of a universal computational reasoning model for precision oncology in lung cancer
npj Precision Oncology
title Real-world performance analysis of a universal computational reasoning model for precision oncology in lung cancer
title_full Real-world performance analysis of a universal computational reasoning model for precision oncology in lung cancer
title_fullStr Real-world performance analysis of a universal computational reasoning model for precision oncology in lung cancer
title_full_unstemmed Real-world performance analysis of a universal computational reasoning model for precision oncology in lung cancer
title_short Real-world performance analysis of a universal computational reasoning model for precision oncology in lung cancer
title_sort real world performance analysis of a universal computational reasoning model for precision oncology in lung cancer
url https://doi.org/10.1038/s41698-025-00943-4
work_keys_str_mv AT annadirner realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT dorakormos realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT doralakatos realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT martonbolyacz realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT mariakocsissteinbach realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT gaborgyorgykalmar realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT doratihanyi realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT akostakacs realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT akosboldizsar realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT viktorkardos realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT rekaszalkaidenes realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT barbaravodicska realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT editvarkondi realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT juliaderi realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT gaborpajkos realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT doramathiasz realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT istvanvalyinagy realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT richardschwab realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT maudkamal realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT christianrolfo realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT arkadiuszzdudek realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT christopheletourneau realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT robertdoczi realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT laszlourban realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer
AT istvanpetak realworldperformanceanalysisofauniversalcomputationalreasoningmodelforprecisiononcologyinlungcancer