Cascade-Based Input-Doubling Classifier for Predicting Survival in Allogeneic Bone Marrow Transplants: Small Data Case

In the field of transplantology, where medical decisions are heavily dependent on complex data analysis, the challenge of small data has become increasingly prominent. Transplantology, which focuses on the transplantation of organs and tissues, requires exceptional accuracy and precision in predicti...

Full description

Saved in:
Bibliographic Details
Main Authors: Ivan Izonin, Roman Tkachenko, Nazarii Hovdysh, Oleh Berezsky, Kyrylo Yemets, Ivan Tsmots
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Computation
Subjects:
Online Access:https://www.mdpi.com/2079-3197/13/4/80
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714344641691648
author Ivan Izonin
Roman Tkachenko
Nazarii Hovdysh
Oleh Berezsky
Kyrylo Yemets
Ivan Tsmots
author_facet Ivan Izonin
Roman Tkachenko
Nazarii Hovdysh
Oleh Berezsky
Kyrylo Yemets
Ivan Tsmots
author_sort Ivan Izonin
collection DOAJ
description In the field of transplantology, where medical decisions are heavily dependent on complex data analysis, the challenge of small data has become increasingly prominent. Transplantology, which focuses on the transplantation of organs and tissues, requires exceptional accuracy and precision in predicting outcomes, assessing risks, and tailoring treatment plans. However, the inherent limitations of small datasets present significant obstacles. This paper introduces an advanced input-doubling classifier designed to improve survival predictions for allogeneic bone marrow transplants. The approach utilizes two artificial intelligence tools: the first Probabilistic Neural Network generates output signals that expand the independent attributes of an augmented dataset, while the second machine learning algorithm performs the final classification. This method, based on the cascading principle, facilitates the development of novel algorithms for preparing and applying the enhanced input-doubling technique to classification tasks. The proposed method was tested on a small dataset within transplantology, focusing on binary classification. Optimal parameters for the method were identified using the Dual Annealing algorithm. Comparative analysis of the improved method against several existing approaches revealed a substantial improvement in accuracy across various performance metrics, underscoring its practical benefits
format Article
id doaj-art-04fe350e9afb4cb58f0ecc62ebbd83bc
institution DOAJ
issn 2079-3197
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Computation
spelling doaj-art-04fe350e9afb4cb58f0ecc62ebbd83bc2025-08-20T03:13:44ZengMDPI AGComputation2079-31972025-03-011348010.3390/computation13040080Cascade-Based Input-Doubling Classifier for Predicting Survival in Allogeneic Bone Marrow Transplants: Small Data CaseIvan Izonin0Roman Tkachenko1Nazarii Hovdysh2Oleh Berezsky3Kyrylo Yemets4Ivan Tsmots5Department of Artificial Intelligence, Lviv Polytechnic National University, 79013 Lviv, UkraineDepartment of Publishing Information Technologies, Lviv Polytechnic National University, 79013 Lviv, UkraineDepartment of Artificial Intelligence, Lviv Polytechnic National University, 79013 Lviv, UkraineDepartment of Computer Engineering, West Ukrainian National University, Lvivska, 11, 46003 Ternopil, UkraineDepartment of Artificial Intelligence, Lviv Polytechnic National University, 79013 Lviv, UkraineDepartment of Automated Control Systems, Lviv Polytechnic National University, 79013 Lviv, UkraineIn the field of transplantology, where medical decisions are heavily dependent on complex data analysis, the challenge of small data has become increasingly prominent. Transplantology, which focuses on the transplantation of organs and tissues, requires exceptional accuracy and precision in predicting outcomes, assessing risks, and tailoring treatment plans. However, the inherent limitations of small datasets present significant obstacles. This paper introduces an advanced input-doubling classifier designed to improve survival predictions for allogeneic bone marrow transplants. The approach utilizes two artificial intelligence tools: the first Probabilistic Neural Network generates output signals that expand the independent attributes of an augmented dataset, while the second machine learning algorithm performs the final classification. This method, based on the cascading principle, facilitates the development of novel algorithms for preparing and applying the enhanced input-doubling technique to classification tasks. The proposed method was tested on a small dataset within transplantology, focusing on binary classification. Optimal parameters for the method were identified using the Dual Annealing algorithm. Comparative analysis of the improved method against several existing approaches revealed a substantial improvement in accuracy across various performance metrics, underscoring its practical benefitshttps://www.mdpi.com/2079-3197/13/4/80small data approachinput-doubling methodclassification taskimbalanced datasettransplantation medicinemachine learning
spellingShingle Ivan Izonin
Roman Tkachenko
Nazarii Hovdysh
Oleh Berezsky
Kyrylo Yemets
Ivan Tsmots
Cascade-Based Input-Doubling Classifier for Predicting Survival in Allogeneic Bone Marrow Transplants: Small Data Case
Computation
small data approach
input-doubling method
classification task
imbalanced dataset
transplantation medicine
machine learning
title Cascade-Based Input-Doubling Classifier for Predicting Survival in Allogeneic Bone Marrow Transplants: Small Data Case
title_full Cascade-Based Input-Doubling Classifier for Predicting Survival in Allogeneic Bone Marrow Transplants: Small Data Case
title_fullStr Cascade-Based Input-Doubling Classifier for Predicting Survival in Allogeneic Bone Marrow Transplants: Small Data Case
title_full_unstemmed Cascade-Based Input-Doubling Classifier for Predicting Survival in Allogeneic Bone Marrow Transplants: Small Data Case
title_short Cascade-Based Input-Doubling Classifier for Predicting Survival in Allogeneic Bone Marrow Transplants: Small Data Case
title_sort cascade based input doubling classifier for predicting survival in allogeneic bone marrow transplants small data case
topic small data approach
input-doubling method
classification task
imbalanced dataset
transplantation medicine
machine learning
url https://www.mdpi.com/2079-3197/13/4/80
work_keys_str_mv AT ivanizonin cascadebasedinputdoublingclassifierforpredictingsurvivalinallogeneicbonemarrowtransplantssmalldatacase
AT romantkachenko cascadebasedinputdoublingclassifierforpredictingsurvivalinallogeneicbonemarrowtransplantssmalldatacase
AT nazariihovdysh cascadebasedinputdoublingclassifierforpredictingsurvivalinallogeneicbonemarrowtransplantssmalldatacase
AT olehberezsky cascadebasedinputdoublingclassifierforpredictingsurvivalinallogeneicbonemarrowtransplantssmalldatacase
AT kyryloyemets cascadebasedinputdoublingclassifierforpredictingsurvivalinallogeneicbonemarrowtransplantssmalldatacase
AT ivantsmots cascadebasedinputdoublingclassifierforpredictingsurvivalinallogeneicbonemarrowtransplantssmalldatacase