Respecting patient privacy with federated artificial intelligence
Multiple research has shown that deep artificial neural networks (ANN) can assist physicians in diagnosing a patient with greater accuracy and sensitivity. Nonetheless, the grand march of success by ANN is only possible by the availability of an open medical dataset. However, at the time of writing,...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IIUM Press
2021
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/92925/7/92925_Respecting%20patient%20privacy%20with%20federated%20artificial%20intelligence.pdf http://irep.iium.edu.my/92925/ https://journals.iium.edu.my/kict/index.php/jisdt/article/download/220/159/1477 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Multiple research has shown that deep artificial neural networks (ANN) can assist physicians in diagnosing a patient with greater accuracy and sensitivity. Nonetheless, the grand march of success by ANN is only possible by the availability of an open medical dataset. However, at the time of writing, there is no open medical dataset from the Malaysian population. The local dataset is crucial to validate the performance of any ANN modal on the local populations. The lack of any local dataset may be due to local medical institution's hesitance to release any medical images and records to respect patient's confidentiality. One way around this is to adopt the Federated Learning system, in which no sharing of patient data is required. Our experiment tested the capability of 25 ANN models to classify chest radiograph images into three classes: normal, bacterial pneumonia, and viral pneumonia. Each ANN model is given a training dataset that is random in size and class ratio. The result obtained from the experiment shows that the federated system obtains the highest score in all measured metrics. It obtained a score of 0.76, 0.72, and 0.72 for average weighted precision, weight sensitivity, and F1, respectively. It also has the lowest standard deviation in all performance metrics compared to other learning systems. The result obtained here further strengthens the notion that if Malaysia wants to adopt a national-level artificial intelligent system for medical purposes, it should utilize the federated learning system at its core. It ensures Malaysia has an artificial intelligence system that respects patient's privacy while maintaining its robustness. |
|---|