A machine-learning expert-supporting system for diagnosis prediction of lymphoid neoplasms using a probabilistic
Yosep Chong1,2, Ji Young Lee1, Yejin Kim3,4
1Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul, Korea.
Insights
A new machine-learning system aids in diagnosing lymphoid neoplasms using immunohistochemistry (IHC) data. This expert-supporting tool achieved high accuracy in both training and validation datasets for lymphoma diagnosis.
Area of Science:
- Hematopathology
- Computational Pathology
- Machine Learning in Medicine
Background:
- Immunohistochemistry (IHC) is crucial for diagnosing hematolymphoid neoplasms but presents interpretation challenges.
- Increasing IHC data volume complicates diagnostic tasks.
- A machine-learning expert-supporting system was developed to aid lymphoid neoplasm diagnosis.
Purpose of the Study:
- To develop and validate a machine-learning system for improving the accuracy of lymphoid neoplasm diagnosis.
- To assess the system's performance using real-world IHC data.
Main Methods:
- A probabilistic decision-tree algorithm based on Bayesian theorem was implemented in mobile application software.
- The system was trained on 602 cases and validated on 392 cases of lymphoid neoplasms.
- Precision hit rates were compared between training and validation datasets.
Main Results:
- The system analyzed IHC expression data for 150 lymphoid neoplasms and 584 antibodies.
- Lymphoma diagnosis achieved high precision hit rates: 94.7% in training and 95.7% in validation data, with no statistically significant difference.
- Excellent performance was observed in most B-cell lymphomas and equivalent performance in T-cell lymphomas.
Conclusions:
- The machine-learning algorithm demonstrated acceptable diagnostic precision for lymphoid neoplasms in both training and validation sets.
- Clinical and histological context is essential for optimal use, especially when disease-specific markers are lacking or profiles overlap.
- The system serves as a valuable expert-supporting tool in pathologic decision-making.
Background:
Immunohistochemistry (IHC) has played an essential role in the diagnosis of hematolymphoid neoplasms. However, IHC interpretations can be challenging in daily practice, and exponentially expanding volumes of IHC data are making the task increasingly difficult. We therefore developed a machine-learning expert-supporting system for diagnosing lymphoid neoplasms.
Methods:
A probabilistic decision-tree algorithm based on the Bayesian theorem was used to develop mobile application software for iOS and Android platforms. We tested the software with real data from 602 training and 392 validation cases of lymphoid neoplasms and compared the precision hit rates between the training and validation datasets.
Results:
IHC expression data for 150 lymphoid neoplasms and 584 antibodies was gathered. The precision hit rates of 94.7% in the training data and 95.7% in the validation data for lymphomas were not statistically significant. Results in most B-cell lymphomas were excellent, and generally equivalent performance was seen in T-cell lymphomas. The primary reasons for lack of precision were atypical IHC profiles for certain cases (e.g., CD15-negative Hodgkin lymphoma), a lack of disease-specific markers, and overlapping IHC profiles of similar diseases.
Conclusions:
Application of the machine-learning algorithm to diagnosis precision produced acceptable hit rates in training and validation datasets. Because of the lack of origin- or disease-specific markers in differential diagnosis, contextual information such as clinical and histological features should be taken into account to make proper use of this system in the pathologic decision-making process.
