This preprint is under consideration at Diagnostic Pathology. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research
Diagnosis Prediction of Tumours of Unknown Origin Using ImmunoGenius, A Machine Learning-based Expert System for Immunohistochemistry Profile Interpretation
Yosep Chong
College of Medicine, The Catholic University of Korea
Corresponding Author
ORCiD: https://orcid.org/0000-0001-8615-3064
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Background
Immunohistochemistry (IHC) remains the gold standard for the diagnosis of pathological diseases. This technique has been supporting pathologists in making precise decisions regarding differential diagnosis and subtyping, and in creating personalized treatment plans. However, the interpretation of IHC results presents challenges in complicated cases. Furthermore, rapidly increasing amounts of IHC data are making it even harder for pathologists to reach to definitive conclusions.
Methods
We developed ImmunoGenius, a machine-learning-based expert system for the pathologist, to support the diagnosis of tumors of unknown origin. Based on Bayesian theorem, the most probable diagnoses can be drawn by calculating the probabilities of the IHC results in each disease. We prepared IHC profile data of 584 antibodies in 2009 neoplasms based on the relevant textbooks. We developed the reactive native mobile application for iOS and Android platform that can provide 10 most possible differential diagnoses based on the IHC input.
Results
We trained the software using 562 real case data, validated it with 382 case data, tested it with 164 case data and compared the precision hit rate. Precision hit rate was 78.5%, 78.0% and 89.0% in training, validation and test dataset respectively. which showed no significant difference. The main reason for discordant precision was lack of disease-specific IHC markers and overlapping IHC profiles observed in similar diseases.
Conclusion
The results of this study showed a potential that the machine-learning algorithm based expert system can support the pathologic diagnosis by providing second opinion on IHC interpretation based on IHC database. Incorporation with contextual data including the clinical and histological findings might be required to elaborate the system in the future.
Keywords
Database, Expert system, Machine learning, Immunohistochemistry, Probabilistic decision tree
Figure 1
Figure 2
Figure 3
Figure 4
This is a list of supplementary files associated with this preprint. Click to download.
- SupplFig1.jpeg
Fig S1: The example of the IHC database
- SupplFig2.jpeg
Fig S2: The example of the patients IHC profile dataset for training and validation of the diagnosis presumption algorithm.
- Supplementarydata.docx
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Review
Version 2
Posted 15 Jan, 2021
No community comments so far
Review #4 received
Received 22 Jan, 2021
Editorial decision: Major Revision
On 22 Jan, 2021
Reviewer #4 agreed
On 16 Jan, 2021
Review #1 received
Received 12 Jan, 2021
Reviewer #3 agreed
On 09 Jan, 2021
Review #3 received
Received 09 Jan, 2021
Reviewer #2 agreed
On 09 Jan, 2021
Review #2 received
Received 09 Jan, 2021
Reviewer #1 agreed
On 06 Jan, 2021
Reviewers invited
Invitations sent on 05 Jan, 2021
Editor assigned
On 04 Jan, 2021
Submission checks complete
On 04 Jan, 2021
Editor invited
On 04 Jan, 2021
No comments provided
Editorial decision: Major Revision
On 04 Nov, 2020
Review #5 received
Received 02 Nov, 2020
Review #4 received
Received 02 Nov, 2020
Review #3 received
Received 30 Oct, 2020
Review #2 received
Received 28 Oct, 2020
Review #1 received
Received 26 Oct, 2020
Reviewer #5 agreed
On 24 Oct, 2020
Reviewer #2 agreed
On 19 Oct, 2020
Reviewer #3 agreed
On 19 Oct, 2020
Reviewer #4 agreed
On 19 Oct, 2020
Reviewer #1 agreed
On 14 Oct, 2020
Reviewers invited
Invitations sent on 12 Oct, 2020
Submission checks complete
On 12 Aug, 2020
Editor assigned
On 12 Aug, 2020
First submitted
On 11 Aug, 2020
Editor invited
On 11 Aug, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Pathology
Learn more about our company.
This preprint is under consideration at Diagnostic Pathology. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research
Diagnosis Prediction of Tumours of Unknown Origin Using ImmunoGenius, A Machine Learning-based Expert System for Immunohistochemistry Profile Interpretation
Yosep Chong
College of Medicine, The Catholic University of Korea
Corresponding Author
ORCiD: https://orcid.org/0000-0001-8615-3064
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Review
Version 2
Posted 15 Jan, 2021
No community comments so far
Review #4 received
Received 22 Jan, 2021
Editorial decision: Major Revision
On 22 Jan, 2021
Reviewer #4 agreed
On 16 Jan, 2021
Review #1 received
Received 12 Jan, 2021
Reviewer #3 agreed
On 09 Jan, 2021
Review #3 received
Received 09 Jan, 2021
Reviewer #2 agreed
On 09 Jan, 2021
Review #2 received
Received 09 Jan, 2021
Reviewer #1 agreed
On 06 Jan, 2021
Reviewers invited
Invitations sent on 05 Jan, 2021
Editor assigned
On 04 Jan, 2021
Submission checks complete
On 04 Jan, 2021
Editor invited
On 04 Jan, 2021
No comments provided
Editorial decision: Major Revision
On 04 Nov, 2020
Review #5 received
Received 02 Nov, 2020
Review #4 received
Received 02 Nov, 2020
Review #3 received
Received 30 Oct, 2020
Review #2 received
Received 28 Oct, 2020
Review #1 received
Received 26 Oct, 2020
Reviewer #5 agreed
On 24 Oct, 2020
Reviewer #2 agreed
On 19 Oct, 2020
Reviewer #3 agreed
On 19 Oct, 2020
Reviewer #4 agreed
On 19 Oct, 2020
Reviewer #1 agreed
On 14 Oct, 2020
Reviewers invited
Invitations sent on 12 Oct, 2020
Submission checks complete
On 12 Aug, 2020
Editor assigned
On 12 Aug, 2020
First submitted
On 11 Aug, 2020
Editor invited
On 11 Aug, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Pathology
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Background
Immunohistochemistry (IHC) remains the gold standard for the diagnosis of pathological diseases. This technique has been supporting pathologists in making precise decisions regarding differential diagnosis and subtyping, and in creating personalized treatment plans. However, the interpretation of IHC results presents challenges in complicated cases. Furthermore, rapidly increasing amounts of IHC data are making it even harder for pathologists to reach to definitive conclusions.
Methods
We developed ImmunoGenius, a machine-learning-based expert system for the pathologist, to support the diagnosis of tumors of unknown origin. Based on Bayesian theorem, the most probable diagnoses can be drawn by calculating the probabilities of the IHC results in each disease. We prepared IHC profile data of 584 antibodies in 2009 neoplasms based on the relevant textbooks. We developed the reactive native mobile application for iOS and Android platform that can provide 10 most possible differential diagnoses based on the IHC input.
Results
We trained the software using 562 real case data, validated it with 382 case data, tested it with 164 case data and compared the precision hit rate. Precision hit rate was 78.5%, 78.0% and 89.0% in training, validation and test dataset respectively. which showed no significant difference. The main reason for discordant precision was lack of disease-specific IHC markers and overlapping IHC profiles observed in similar diseases.
Conclusion
The results of this study showed a potential that the machine-learning algorithm based expert system can support the pathologic diagnosis by providing second opinion on IHC interpretation based on IHC database. Incorporation with contextual data including the clinical and histological findings might be required to elaborate the system in the future.
Figure 1
Figure 2
Figure 3
Figure 4