Explainable Machine Learning Solution for Observing Optimal Surgery Timings in Thoracic Cancer Diagnosis
In this paper, we introduce an AI-based procedure to estimate and assist in choosing the optimal surgery timing, in the case of a thoracic cancer diagnostic, based on an explainable machine learning model trained on a knowledge base. This decision is usually taken by the surgeon after examining a se...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/13/6506 |
| _version_ | 1797480987244888064 |
|---|---|
| author | Gabriel V. Cozma Darian Onchis Codruta Istin Ioan Adrian Petrache |
| author_facet | Gabriel V. Cozma Darian Onchis Codruta Istin Ioan Adrian Petrache |
| author_sort | Gabriel V. Cozma |
| collection | DOAJ |
| description | In this paper, we introduce an AI-based procedure to estimate and assist in choosing the optimal surgery timing, in the case of a thoracic cancer diagnostic, based on an explainable machine learning model trained on a knowledge base. This decision is usually taken by the surgeon after examining a set of clinical parameters and their evolution in time. Therefore, it is sometimes subjective, it depends heavily on the previous experience of the surgeon, and it might not be confirmed by the histopathological exam. Therefore, we propose a pipeline of automatic processing steps with the purpose of inferring the prospective result of the histopathologic exam, generating an explanation of why this inference holds, and finally, evaluating it against the conclusive opinion of an experienced surgeon. To obtain an accurate practical result, the training dataset is labeled manually by the thoracic surgeon, creating a training knowledge base that is not biased towards clinical practice. The resulting intelligent system benefits from both the precision of a classical expert system and the flexibility of deep neural networks, and it is supposed to avoid, at maximum, any possible human misinterpretations and provide a factual estimate for the proper timing for surgical intervention. Overall, the experiments showed a 7% improvement on the test set compared with the medical opinion alone. To enable the reproducibility of the AI system, complete handling of a case study is presented from both the medical and technical aspects. |
| first_indexed | 2024-03-09T22:08:00Z |
| format | Article |
| id | doaj.art-f37130a82777472db4961ac4500b8ab6 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:08:00Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f37130a82777472db4961ac4500b8ab62023-11-23T19:37:52ZengMDPI AGApplied Sciences2076-34172022-06-011213650610.3390/app12136506Explainable Machine Learning Solution for Observing Optimal Surgery Timings in Thoracic Cancer DiagnosisGabriel V. Cozma0Darian Onchis1Codruta Istin2Ioan Adrian Petrache3Department of Surgical Semiology I and Thoracic Surgery, “Victor Babes” University of Medicine and Pharmacy of Timisoara, 300041 Timisoara, RomaniaDepartment of Computer Science, West University of Timisoara, 300223 Timisoara, RomaniaComputer and Information Technology Department, Politehnica University of Timisoara, 300006 Timisoara, RomaniaDepartment of Surgical Semiology I and Thoracic Surgery, “Victor Babes” University of Medicine and Pharmacy of Timisoara, 300041 Timisoara, RomaniaIn this paper, we introduce an AI-based procedure to estimate and assist in choosing the optimal surgery timing, in the case of a thoracic cancer diagnostic, based on an explainable machine learning model trained on a knowledge base. This decision is usually taken by the surgeon after examining a set of clinical parameters and their evolution in time. Therefore, it is sometimes subjective, it depends heavily on the previous experience of the surgeon, and it might not be confirmed by the histopathological exam. Therefore, we propose a pipeline of automatic processing steps with the purpose of inferring the prospective result of the histopathologic exam, generating an explanation of why this inference holds, and finally, evaluating it against the conclusive opinion of an experienced surgeon. To obtain an accurate practical result, the training dataset is labeled manually by the thoracic surgeon, creating a training knowledge base that is not biased towards clinical practice. The resulting intelligent system benefits from both the precision of a classical expert system and the flexibility of deep neural networks, and it is supposed to avoid, at maximum, any possible human misinterpretations and provide a factual estimate for the proper timing for surgical intervention. Overall, the experiments showed a 7% improvement on the test set compared with the medical opinion alone. To enable the reproducibility of the AI system, complete handling of a case study is presented from both the medical and technical aspects.https://www.mdpi.com/2076-3417/12/13/6506thoracic cancer diagnosisexplainable intelligent systemstabilized LIME |
| spellingShingle | Gabriel V. Cozma Darian Onchis Codruta Istin Ioan Adrian Petrache Explainable Machine Learning Solution for Observing Optimal Surgery Timings in Thoracic Cancer Diagnosis Applied Sciences thoracic cancer diagnosis explainable intelligent system stabilized LIME |
| title | Explainable Machine Learning Solution for Observing Optimal Surgery Timings in Thoracic Cancer Diagnosis |
| title_full | Explainable Machine Learning Solution for Observing Optimal Surgery Timings in Thoracic Cancer Diagnosis |
| title_fullStr | Explainable Machine Learning Solution for Observing Optimal Surgery Timings in Thoracic Cancer Diagnosis |
| title_full_unstemmed | Explainable Machine Learning Solution for Observing Optimal Surgery Timings in Thoracic Cancer Diagnosis |
| title_short | Explainable Machine Learning Solution for Observing Optimal Surgery Timings in Thoracic Cancer Diagnosis |
| title_sort | explainable machine learning solution for observing optimal surgery timings in thoracic cancer diagnosis |
| topic | thoracic cancer diagnosis explainable intelligent system stabilized LIME |
| url | https://www.mdpi.com/2076-3417/12/13/6506 |
| work_keys_str_mv | AT gabrielvcozma explainablemachinelearningsolutionforobservingoptimalsurgerytimingsinthoraciccancerdiagnosis AT darianonchis explainablemachinelearningsolutionforobservingoptimalsurgerytimingsinthoraciccancerdiagnosis AT codrutaistin explainablemachinelearningsolutionforobservingoptimalsurgerytimingsinthoraciccancerdiagnosis AT ioanadrianpetrache explainablemachinelearningsolutionforobservingoptimalsurgerytimingsinthoraciccancerdiagnosis |