Prediction of prognosis in brain metastasis with artificial-intelligence-driven methods for whole brain radiotherapy

Emine Elif Özkan; Tekin Ahmet Serel

Makale detayları

Prediction of prognosis in brain metastasis with artificial-intelligence-driven methods for whole brain radiotherapy

Yazarlar:

Emine Elif Özkan | Tekin Ahmet Serel

Yayıncı:

Cukurova University

Ana Başlıklar:

Klinik Onkoloji

Dergi:

Cukurova Medical Journal Vol.50 Issue 3, pp.661-672

Belge Tipi:

Makale

Yayın Tarihi:

9/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001357839

pISSN:

2602-3032

Anahtar kelimeler:

Özet:

 Purpose: Inferentially, 2445 of cancer patients develop brain metastases in their course. Individual survival estimation for these patients is crucial to identify the subset that may not benefit from whole-brain irradiation WBI due to a short survival time. This study aimed to identify variables and evaluate an artificial intelligence algorithm to determine which patients would benefit from WBI. Materials and Methods: The data of 345 patients with brain metastasis who were treated with 30 Gy in 10 fractions of WBI were retrospectively analyzed. In this cohort, a total of 15 clinical  laboratory factors are evaluated with 15 models of machine learning algorithms using Python 2.3, Pycaret library. Results: The Gradient Boosting Regressor was found to be the most accurate model, with a 0.68 R2 an R² value of 0.68, and a mean absolute error MAE of 12.90.The prediction error for the gradient Boosting Regressor was calculated as R2: 0.841. When the importance of features was investigated, time from diagnosis to metastasis was found to be the most important predictive variable for survival. Conclusion: The results of this study enable us to identify patients who may have an early death and provide a consequential decision guide in terms of whole-brain radiotherapy or additional labor-intensive techniques.

 Purpose: Inferentially, 2445 of cancer patients develop brain metastases in their course. Individual survival estimation for these patients is crucial to identify the subset that may not benefit from whole-brain irradiation WBI due to a short survival time. This study aimed to identify variables and evaluate an artificial intelligence algorithm to determine which patients would benefit from WBI. Materials and Methods: The data of 345 patients with brain metastasis who were treated with 30 Gy in 10 fractions of WBI were retrospectively analyzed. In this cohort, a total of 15 clinical  laboratory factors are evaluated with 15 models of machine learning algorithms using Python 2.3, Pycaret library. Results: The Gradient Boosting Regressor was found to be the most accurate model, with a 0.68 R2 an R² value of 0.68, and a mean absolute error MAE of 12.90.The prediction error for the gradient Boosting Regressor was calculated as R2: 0.841. When the importance of features was investigated, time from diagnosis to metastasis was found to be the most important predictive variable for survival. Conclusion: The results of this study enable us to identify patients who may have an early death and provide a consequential decision guide in terms of whole-brain radiotherapy or additional labor-intensive techniques.

 Purpose: Inferentially, 2445 of cancer patients develop brain metastases in their course. Individual survival estimation for these patients is crucial to identify the subset that may not benefit from whole-brain irradiation WBI due to a short survival time. This study aimed to identify variables and evaluate an artificial intelligence algorithm to determine which patients would benefit from WBI. Materials and Methods: The data of 345 patients with brain metastasis who were treated with 30 Gy in 10 fractions of WBI were retrospectively analyzed. In this cohort, a total of 15 clinical  laboratory factors are evaluated with 15 models of machine learning algorithms using Python 2.3, Pycaret library. Results: The Gradient Boosting Regressor was found to be the most accurate model, with a 0.68 R2 an R² value of 0.68, and a mean absolute error MAE of 12.90.The prediction error for the gradient Boosting Regressor was calculated as R2: 0.841. When the importance of features was investigated, time from diagnosis to metastasis was found to be the most important predictive variable for survival. Conclusion: The results of this study enable us to identify patients who may have an early death and provide a consequential decision guide in terms of whole-brain radiotherapy or additional labor-intensive techniques.

 Amaç: Çıkarımsal olarak kanser hastalarının 24-45i, seyirleri sırasında beyin metastazları geliştirir. Bu hastalar için bireysel sağkalım tahmini, kısa sağkalım süresi nedeniyle tüm beyin ışınlamasından WBI fayda görmeyebilecek hasta alt grubunu ayırt etmek için önemlidir. Bu çalışma, değişkenler üzerinde arama yapmayı ve WBIdan fayda görecek hasta alt grubunu belirlemek için bir yapay zeka algoritmasını değerlendirmeyi amaçlamaktadır. Gereç ve Yöntem: 10 fraksiyonda 30 Gy WBI ile tedavi edilen beyin metastazı olan 345 hastanın verileri retrospektif olarak analiz edildi. Bu kohortta toplam 15 kliniklaboratuvar faktörü, Python 2.3, Pycaret kütüphanesi kullanılarak 15 makine öğrenme algoritması modeli ile değerlendirildi. Bulgular: Gradient Boosting Regressorun 0,68 R2 değeri ve 12,90 ortalama mutlak değer MAE ile doğru modelleme olduğu bulundu. Gradient Boosting Regressor için tahmin hatası R2: 0,841 olarak hesaplandı. Özelliklerin önemi incelendiğinde, tanıdan metastaza kadar geçen sürenin sağ kalım için en önemli öngörücü değişken olduğu bulundu. Sonuç: Bu çalışmanın sonuçları erken ölüm riski olan hastaları belirlemeyi mümkün kılıyor ve tüm beyin radyoterapisi veya ek emek yoğun teknikler açısından sonuç odaklı bir karar kılavuzu sağlıyor.

Makale detayları

Prediction of prognosis in brain metastasis with artificial-intelligence-driven methods for whole brain radiotherapy

Yazarlar:

Emine Elif Özkan | Tekin Ahmet Serel

Yayıncı:

Cukurova University

Ana Başlıklar:

Klinik Onkoloji

Dergi:

Cukurova Medical Journal Vol.50 Issue 3, pp.661-672

Belge Tipi:

Makale

Yayın Tarihi:

9/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001357839

pISSN:

2602-3032

brain metastases

machine learning

prognosis

radiotherapybeyin metastazı

makina öğrenmesi

prognoz

radyoterapi

Sayı

Makale detayları

Yazarlar: Emine Elif Özkan | Tekin Ahmet Serel

Yayıncı: Cukurova University

Ana Başlıklar: Klinik Onkoloji

Dergi: Cukurova Medical Journal Vol.50 Issue 3, pp.661-672

Belge Tipi: Makale

Yayın Tarihi: 9/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001357839

pISSN: 2602-3032

Sayı

Yazarlar:

Emine Elif Özkan | Tekin Ahmet Serel

Yayıncı:

Cukurova University

Ana Başlıklar:

Klinik Onkoloji

Dergi:

Cukurova Medical Journal Vol.50 Issue 3, pp.661-672

Belge Tipi:

Makale

Yayın Tarihi:

9/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001357839

pISSN:

2602-3032