Establishment of a Knowledge‐and‐Data‐Driven Artificial Intelligence System with Robustness and Interpretability in Laboratory Medicine
Laboratory medicine plays an important role in clinical diagnosis. However, no laboratory‐based artificial intelligence (AI) diagnostic system has been applied in current clinical practice due to the lack of robustness and interpretability. Although many attempts have been made, it is still difficul...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-05-01
|
| Series: | Advanced Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/aisy.202100204 |
| _version_ | 1818211561083240448 |
|---|---|
| author | Beilei Wang Jie Jing Xiaochun Huang Cheng Hua Qin Qin Yin Jia Zhiyong Wang Lei Jiang Bai Gao Lele Wu Xianfei Zeng Fubo Wang Chuanbin Mao Shanrong Liu |
| author_facet | Beilei Wang Jie Jing Xiaochun Huang Cheng Hua Qin Qin Yin Jia Zhiyong Wang Lei Jiang Bai Gao Lele Wu Xianfei Zeng Fubo Wang Chuanbin Mao Shanrong Liu |
| author_sort | Beilei Wang |
| collection | DOAJ |
| description | Laboratory medicine plays an important role in clinical diagnosis. However, no laboratory‐based artificial intelligence (AI) diagnostic system has been applied in current clinical practice due to the lack of robustness and interpretability. Although many attempts have been made, it is still difficult for doctors to adopt the existing machine learning (ML) patterns in interpreting laboratory (lab) big data. Here, a knowledge‐and‐data‐driven laboratory diagnostic system is developed, termed AI‐based Lab tEst tO diagNosis (AI LEON), by integrating an innovative knowledge graph analysis framework and “mixed XGboost and Genetic Algorithm (MiXG)” technique to simulate the doctor's laboratory‐based diagnosis. To establish AI LEON, we included 89 116 949 laboratory data and 10 423 581 diagnosis data points from 730 113 participants. Among them, 686 626 participants were recruited for training and validating purposes with the remaining for testing purposes. AI LEON automatically identified and analyzed 2071 lab indexes, resulting in multiple disease recommendations that involved 441 common diseases in ten organ systems. AI LEON exhibited outstanding transparency and interpretability in three universal clinical application scenarios and outperformed human physicians in interpreting lab reports. AI LEON is an advanced intelligent system that enables a comprehensive interpretation of lab big data, which substantially improves the clinical diagnosis. |
| first_indexed | 2024-12-12T05:34:27Z |
| format | Article |
| id | doaj.art-9cba12ad35ac489b8fcaf44227d3ad7e |
| institution | Directory Open Access Journal |
| issn | 2640-4567 |
| language | English |
| last_indexed | 2024-12-12T05:34:27Z |
| publishDate | 2022-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Intelligent Systems |
| spelling | doaj.art-9cba12ad35ac489b8fcaf44227d3ad7e2022-12-22T00:36:12ZengWileyAdvanced Intelligent Systems2640-45672022-05-0145n/an/a10.1002/aisy.202100204Establishment of a Knowledge‐and‐Data‐Driven Artificial Intelligence System with Robustness and Interpretability in Laboratory MedicineBeilei Wang0Jie Jing1Xiaochun Huang2Cheng Hua3Qin Qin4Yin Jia5Zhiyong Wang6Lei Jiang7Bai Gao8Lele Wu9Xianfei Zeng10Fubo Wang11Chuanbin Mao12Shanrong Liu13Department of Laboratory Diagnostics Changhai Hospital Navy Military Medical University 168 Changhai Road Shanghai 200433 ChinaDepartment of Laboratory Diagnostics Changhai Hospital Navy Military Medical University 168 Changhai Road Shanghai 200433 ChinaDepartment of Laboratory Diagnostics Changhai Hospital Navy Military Medical University 168 Changhai Road Shanghai 200433 ChinaAntai College of Economics and Management Shanghai Jiao Tong University 1954 Huashan Road Shanghai 200031 ChinaDepartment of Laboratory Diagnostics Changhai Hospital Navy Military Medical University 168 Changhai Road Shanghai 200433 ChinaDepartment of Laboratory Diagnostics Changhai Hospital Navy Military Medical University 168 Changhai Road Shanghai 200433 ChinaDepartment of Information Changhai Hospital Navy Military Medical University 168 Changhai Road Shanghai 200433 ChinaDepartment of Rheumatology and Immunology Shanghai Changzheng Hospital Navy Military Medical University 415 Fengyang Road Shanghai 200003 ChinaDepartment of Information Changhai Hospital Navy Military Medical University 168 Changhai Road Shanghai 200433 ChinaDepartment of Information Changhai Hospital Navy Military Medical University 168 Changhai Road Shanghai 200433 ChinaSchool of Medicine Xi'an Area Medical Laboratory Center Northwest University 15 Gaoxin Road Xi'an 710000 ChinaCenter for Genomic and Personalized Medicine Guangxi Medical University 22 Shuangyong Road Nanning 530021 ChinaDepartment of Chemistry and Biochemistry Stephenson Life Sciences Research Center University of Oklahoma 101 Stephenson Parkway Norman Oklahoma 73019-5300 USADepartment of Laboratory Diagnostics Changhai Hospital Navy Military Medical University 168 Changhai Road Shanghai 200433 ChinaLaboratory medicine plays an important role in clinical diagnosis. However, no laboratory‐based artificial intelligence (AI) diagnostic system has been applied in current clinical practice due to the lack of robustness and interpretability. Although many attempts have been made, it is still difficult for doctors to adopt the existing machine learning (ML) patterns in interpreting laboratory (lab) big data. Here, a knowledge‐and‐data‐driven laboratory diagnostic system is developed, termed AI‐based Lab tEst tO diagNosis (AI LEON), by integrating an innovative knowledge graph analysis framework and “mixed XGboost and Genetic Algorithm (MiXG)” technique to simulate the doctor's laboratory‐based diagnosis. To establish AI LEON, we included 89 116 949 laboratory data and 10 423 581 diagnosis data points from 730 113 participants. Among them, 686 626 participants were recruited for training and validating purposes with the remaining for testing purposes. AI LEON automatically identified and analyzed 2071 lab indexes, resulting in multiple disease recommendations that involved 441 common diseases in ten organ systems. AI LEON exhibited outstanding transparency and interpretability in three universal clinical application scenarios and outperformed human physicians in interpreting lab reports. AI LEON is an advanced intelligent system that enables a comprehensive interpretation of lab big data, which substantially improves the clinical diagnosis.https://doi.org/10.1002/aisy.202100204artificial intelligencediagnosisknowledge and data drivenlaboratory medicinemachine learning |
| spellingShingle | Beilei Wang Jie Jing Xiaochun Huang Cheng Hua Qin Qin Yin Jia Zhiyong Wang Lei Jiang Bai Gao Lele Wu Xianfei Zeng Fubo Wang Chuanbin Mao Shanrong Liu Establishment of a Knowledge‐and‐Data‐Driven Artificial Intelligence System with Robustness and Interpretability in Laboratory Medicine Advanced Intelligent Systems artificial intelligence diagnosis knowledge and data driven laboratory medicine machine learning |
| title | Establishment of a Knowledge‐and‐Data‐Driven Artificial Intelligence System with Robustness and Interpretability in Laboratory Medicine |
| title_full | Establishment of a Knowledge‐and‐Data‐Driven Artificial Intelligence System with Robustness and Interpretability in Laboratory Medicine |
| title_fullStr | Establishment of a Knowledge‐and‐Data‐Driven Artificial Intelligence System with Robustness and Interpretability in Laboratory Medicine |
| title_full_unstemmed | Establishment of a Knowledge‐and‐Data‐Driven Artificial Intelligence System with Robustness and Interpretability in Laboratory Medicine |
| title_short | Establishment of a Knowledge‐and‐Data‐Driven Artificial Intelligence System with Robustness and Interpretability in Laboratory Medicine |
| title_sort | establishment of a knowledge and data driven artificial intelligence system with robustness and interpretability in laboratory medicine |
| topic | artificial intelligence diagnosis knowledge and data driven laboratory medicine machine learning |
| url | https://doi.org/10.1002/aisy.202100204 |
| work_keys_str_mv | AT beileiwang establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT jiejing establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT xiaochunhuang establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT chenghua establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT qinqin establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT yinjia establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT zhiyongwang establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT leijiang establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT baigao establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT lelewu establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT xianfeizeng establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT fubowang establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT chuanbinmao establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine AT shanrongliu establishmentofaknowledgeanddatadrivenartificialintelligencesystemwithrobustnessandinterpretabilityinlaboratorymedicine |