1
|
Liu Z, Cao Q, Du N, Shu H, Zhong E, Jiang N, Chen Q, Shen Y, Chen K. FIT-graph: A multi-grained evolutionary graph based framework for disease diagnosis. Artif Intell Med 2024; 147:102735. [PMID: 38184359 DOI: 10.1016/j.artmed.2023.102735] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2022] [Revised: 10/04/2023] [Accepted: 11/28/2023] [Indexed: 01/08/2024]
Abstract
Early assessment, with the help of machine learning methods, can aid clinicians in optimizing the diagnosis and treatment process, allowing patients to receive critical treatment time. Due to the advantages of effective information organization and interpretable reasoning, knowledge graph-based methods have become one of the most widely used machine learning algorithms for this task. However, due to a lack of effective organization and use of multi-granularity and temporal information, current knowledge graph-based approaches are hard to fully and comprehensively exploit the information contained in medical records, restricting their capacity to make superior quality diagnoses. To address these challenges, we examine and study disease diagnosis applications in-depth, and propose a novel disease diagnosis framework named FIT-Graph. With novel medical multi-grained evolutionary graphs, FIT-Graph efficiently organizes the extracted information from various granularities and time stages, maximizing the retention of valuable information for disease inference and ensuring the comprehensiveness and validity of the final disease inference. We compare FIT-Graph with two real-world clinical datasets from cardiology and respiratory departments with the baseline. The experimental results show that its effect is better than the baseline model, and the baseline performance of the task is improved by about 5% in multiple indices.
Collapse
Affiliation(s)
- Zizhu Liu
- Department of Cardiovascular Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
| | - Qing Cao
- Department of Cardiovascular Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
| | - Nan Du
- School of Intelligent Systems Engineering, Sun Yat-Sen University, China.
| | | | | | | | | | - Ying Shen
- School of Intelligent Systems Engineering, Sun Yat-Sen University, China.
| | - Kang Chen
- Department of Cardiovascular Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
| |
Collapse
|
2
|
Zhao G, Gu W, Cai W, Zhao Z, Zhang X, Liu J. MLEE: A method for extracting object-level medical knowledge graph entities from Chinese clinical records. Front Genet 2022; 13:900242. [PMID: 35938002 PMCID: PMC9354090 DOI: 10.3389/fgene.2022.900242] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2022] [Accepted: 06/16/2022] [Indexed: 11/13/2022] Open
Abstract
As a typical knowledge-intensive industry, the medical field uses knowledge graph technology to construct causal inference calculations, such as “symptom-disease”, “laboratory examination/imaging examination-disease”, and “disease-treatment method”. The continuous expansion of large electronic clinical records provides an opportunity to learn medical knowledge by machine learning. In this process, how to extract entities with a medical logic structure and how to make entity extraction more consistent with the logic of the text content in electronic clinical records are two issues that have become key in building a high-quality, medical knowledge graph. In this work, we describe a method for extracting medical entities using real Chinese clinical electronic clinical records. We define a computational architecture named MLEE to extract object-level entities with “object-attribute” dependencies. We conducted experiments based on randomly selected electronic clinical records of 1,000 patients from Shengjing Hospital of China Medical University to verify the effectiveness of the method.
Collapse
Affiliation(s)
- Genghong Zhao
- School of Computer Science and Engineering Northeastern University, Shenyang, China
- Neusoft Research of Intelligent Healthcare Technology, Shenyang, China
- *Correspondence: Genghong Zhao, ; Xia Zhang, ; Jiren Liu,
| | - Wenjian Gu
- School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
| | - Wei Cai
- Neusoft Research of Intelligent Healthcare Technology, Shenyang, China
| | - Zhiying Zhao
- Department of Clinical Epidemiology, Shengjing Hospital of China Medical University, Shenyang, China
| | - Xia Zhang
- School of Computer Science and Engineering Northeastern University, Shenyang, China
- Neusoft Research of Intelligent Healthcare Technology, Shenyang, China
- *Correspondence: Genghong Zhao, ; Xia Zhang, ; Jiren Liu,
| | - Jiren Liu
- School of Computer Science and Engineering Northeastern University, Shenyang, China
- Neusoft Corporation, Shenyang, China
- *Correspondence: Genghong Zhao, ; Xia Zhang, ; Jiren Liu,
| |
Collapse
|
3
|
Jiang J, Yu X, Lin Y, Guan Y. PercolationDF: A percolation-based medical diagnosis framework. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2022; 19:5832-5849. [PMID: 35603381 DOI: 10.3934/mbe.2022273] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Goal: With the continuing shortage and unequal distribution of medical resources, our objective is to develop a general diagnosis framework that utilizes a smaller amount of electronic medical records (EMRs) to alleviate the problem that the data volume requirement of prevailing models is too vast for medical institutions to afford. Methods: The framework proposed contains network construction, network expansion, and disease diagnosis methods. In the first two stages above, the knowledge extracted from EMRs is utilized to build and expense an EMR-based medical knowledge network (EMKN) to model and represent the medical knowledge. Then, percolation theory is modified to diagnose EMKN. Result: Facing the lack of data, our framework outperforms naïve Bayes networks, neural networks and logistic regression, especially in the top-10 recall. Out of 207 test cases, 51.7% achieved 100% in the top-10 recall, 21% better than what was achieved in one of our previous studies. Conclusion: The experimental results show that the proposed framework may be useful for medical knowledge representation and diagnosis. The framework effectively alleviates the lack of data volume by inferring the knowledge modeled in EMKN. Significance: The proposed framework not only has applications for diagnosis but also may be extended to other domains to represent and model the knowledge and inference on the representation.
Collapse
Affiliation(s)
- Jingchi Jiang
- The Artificial Intelligence Institute, Harbin Institute of Technology, Harbin, China
| | - Xuehui Yu
- The Faculty of Computing, Harbin Institute of Technology, Harbin, China
| | - Yi Lin
- The Faculty of Computing, Harbin Institute of Technology, Harbin, China
| | - Yi Guan
- The Faculty of Computing, Harbin Institute of Technology, Harbin, China
| |
Collapse
|
4
|
AIM in Electronic Health Records (EHRs). Artif Intell Med 2022. [DOI: 10.1007/978-3-030-64573-1_47] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
5
|
Sheng X, Chen H, Shao P, Qin R, Zhao H, Xu Y, Bai F. Brain Structural Network Compensation Is Associated With Cognitive Impairment and Alzheimer's Disease Pathology. Front Neurosci 2021; 15:630278. [PMID: 33716654 PMCID: PMC7947929 DOI: 10.3389/fnins.2021.630278] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2020] [Accepted: 01/26/2021] [Indexed: 12/12/2022] Open
Abstract
BACKGROUND Structural network alterations in Alzheimer's disease (AD) are related to worse cognitive impairment. The aim of this study was to quantify the alterations in gray matter associated with impaired cognition and their pathological biomarkers in AD-spectrum patients. METHODS We extracted gray matter networks from 3D-T1 magnetic resonance imaging scans, and a graph theory analysis was used to explore alterations in the network metrics in 34 healthy controls, 70 mild cognitive impairment (MCI) patients, and 40 AD patients. Spearman correlation analysis was computed to investigate the relationships among network properties, neuropsychological performance, and cerebrospinal fluid pathological biomarkers (i.e., Aβ, t-tau, and p-tau) in these subjects. RESULTS AD-spectrum individuals demonstrated higher nodal properties and edge properties associated with impaired memory function, and lower amyloid-β or higher tau levels than the controls. Furthermore, these compensations at the brain regional level in AD-spectrum patients were mainly in the medial temporal lobe; however, the compensation at the whole-brain network level gradually extended from the frontal lobe to become widely distributed throughout the cortex with the progression of AD. CONCLUSION The findings provide insight into the alterations in the gray matter network related to impaired cognition and pathological biomarkers in the progression of AD. The possibility of compensation was detected in the structural networks in AD-spectrum patients; the compensatory patterns at regional and whole-brain levels were different and the clinical significance was highlighted.
Collapse
Affiliation(s)
- Xiaoning Sheng
- Department of Neurology, Affiliated Drum Tower Hospital of Medical School and The State Key Laboratory of Pharmaceutical Biotechnology, Institute of Brain Science, Nanjing University, Nanjing, China
| | - Haifeng Chen
- Department of Neurology, Affiliated Drum Tower Hospital of Medical School and The State Key Laboratory of Pharmaceutical Biotechnology, Institute of Brain Science, Nanjing University, Nanjing, China
- Jiangsu Province Stroke Center for Diagnosis and Therapy, Nanjing, China
- Nanjing Neuropsychiatry Clinic Medical Center, Nanjing, China
| | - Pengfei Shao
- Department of Neurology, Affiliated Drum Tower Hospital of Medical School and The State Key Laboratory of Pharmaceutical Biotechnology, Institute of Brain Science, Nanjing University, Nanjing, China
| | - Ruomeng Qin
- Department of Neurology, Affiliated Drum Tower Hospital of Medical School and The State Key Laboratory of Pharmaceutical Biotechnology, Institute of Brain Science, Nanjing University, Nanjing, China
- Jiangsu Province Stroke Center for Diagnosis and Therapy, Nanjing, China
- Nanjing Neuropsychiatry Clinic Medical Center, Nanjing, China
| | - Hui Zhao
- Department of Neurology, Affiliated Drum Tower Hospital of Medical School and The State Key Laboratory of Pharmaceutical Biotechnology, Institute of Brain Science, Nanjing University, Nanjing, China
- Jiangsu Province Stroke Center for Diagnosis and Therapy, Nanjing, China
- Nanjing Neuropsychiatry Clinic Medical Center, Nanjing, China
| | - Yun Xu
- Department of Neurology, Affiliated Drum Tower Hospital of Medical School and The State Key Laboratory of Pharmaceutical Biotechnology, Institute of Brain Science, Nanjing University, Nanjing, China
- Jiangsu Province Stroke Center for Diagnosis and Therapy, Nanjing, China
- Nanjing Neuropsychiatry Clinic Medical Center, Nanjing, China
| | - Feng Bai
- Department of Neurology, Affiliated Drum Tower Hospital of Medical School and The State Key Laboratory of Pharmaceutical Biotechnology, Institute of Brain Science, Nanjing University, Nanjing, China
- Jiangsu Province Stroke Center for Diagnosis and Therapy, Nanjing, China
- Nanjing Neuropsychiatry Clinic Medical Center, Nanjing, China
| | | |
Collapse
|
6
|
AIM in Electronic Health Records (EHRs). Artif Intell Med 2021. [DOI: 10.1007/978-3-030-58080-3_47-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
7
|
Guan Y, Jiang J. AIM in Electronic Health Records (EHRs). Artif Intell Med 2021. [DOI: 10.1007/978-3-030-58080-3_47-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
8
|
Zhang Y, Sheng M, Zhou R, Wang Y, Han G, Zhang H, Xing C, Dong J. HKGB: An Inclusive, Extensible, Intelligent, Semi-auto-constructed Knowledge Graph Framework for Healthcare with Clinicians’ Expertise Incorporated. Inf Process Manag 2020. [DOI: 10.1016/j.ipm.2020.102324] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022]
|
9
|
Xie J, Jiang J, Wang Y, Guan Y, Guo X. Learning an expandable EMR-based medical knowledge network to enhance clinical diagnosis. Artif Intell Med 2020; 107:101927. [PMID: 32828460 DOI: 10.1016/j.artmed.2020.101927] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2018] [Revised: 10/04/2019] [Accepted: 07/02/2020] [Indexed: 01/10/2023]
Abstract
Electronic medical records (EMRs) contain a wealth of knowledge that can be used to assist doctors in making clinical decisions like disease diagnosis. Constructing a medical knowledge network (MKN) to link medical concepts in EMRs is an effective way to manage this knowledge. The quality of the diagnostic result made by MKN-based clinical decision support system depends on the accuracy of medical knowledge and the completeness of the network. However, collecting knowledge is a long-lasting and cumulative process, which means it's hard to construct a complete MKN with limited data. This study was conducted with the objective of developing an expandable EMR-based MKN to enhance capabilities in making an initial clinical diagnosis. A network of symptom-indicate-disease knowledge in 992 Chinese EMRs (CEMRs) was manually constructed as Original-MKN, and an incremental expansion framework was applied to it to obtain an expandable MKN based on new CEMRs. The framework was composed by: (1) integrating external knowledge extracted from the medical information websites and (2) mining potential knowledge with new EMRs. The framework also adopts a diagnosis-driven learning method to estimate the effectiveness of each knowledge in clinical practice. Experimental results indicate that our expanded MKN achieves a precision of 0.837 for a recall of 0.719 in clinical diagnosis, which outperforms Original-MKN and four classical machine learning methods. Furthermore, both external medical knowledge and potential medical knowledge benefit MKN expansion and disease diagnosis. The proposed incremental expansion framework sustains the MKN learning new knowledge.
Collapse
Affiliation(s)
- Jing Xie
- School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China
| | - Jingchi Jiang
- School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China
| | - Yehan Wang
- Unisound AI Technology Co., Ltd, Beijing 100096, China
| | - Yi Guan
- School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China.
| | - Xitong Guo
- School of Management, Harbin Institute of Technology, Harbin 150001, China
| |
Collapse
|
10
|
Li L, Wang P, Yan J, Wang Y, Li S, Jiang J, Sun Z, Tang B, Chang TH, Wang S, Liu Y. Real-world data medical knowledge graph: construction and applications. Artif Intell Med 2020; 103:101817. [DOI: 10.1016/j.artmed.2020.101817] [Citation(s) in RCA: 21] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2019] [Revised: 12/19/2019] [Accepted: 02/04/2020] [Indexed: 10/25/2022]
|
11
|
Abstract
OBJECTIVES This survey analyses the latest literature contributions to clinical decision support systems (DSSs) on a two-year period (2017-2018), focusing on the approaches that adopt Artificial Intelligence (AI) techniques in a broad sense. The goal is to analyse the distribution of data-driven AI approaches with respect to "classical" knowledge-based ones, and to consider the issues raised and their possible solutions. METHODS We included PubMed and Web of ScienceTM publications, focusing on contributions describing clinical DSSs that adopted one or more AI methodologies. RESULTS We selected 75 papers, 49 of which describe approaches in the data-driven AI area, 20 present purely knowledge-based DSSs, and 6 adopt hybrid approaches relying on both formalized knowledge and data. CONCLUSIONS Recent studies in the clinical DSS area demonstrate a prevalence of data-driven AI, which can be adopted autonomously in purely data-driven systems, or in cooperation with domain knowledge in hybrid systems. Such hybrid approaches, able to conjugate all available knowledge sources through proper knowledge integration steps, represent an interesting example of synergy between the two AI categories. This synergy can lead to the resolution of some existing issues, such as the need for transparency and explainability, nowadays recognized as central themes to be addressed by both AI and medical informatics research.
Collapse
Affiliation(s)
- Stefania Montani
- DISIT, Computer Science Institute, University of Piemonte Orientale, Alessandria, Italy
| | - Manuel Striani
- DISIT, Computer Science Institute, University of Piemonte Orientale, Alessandria, Italy
| |
Collapse
|
12
|
Alizadehsani R, Hosseini MJ, Khosravi A, Khozeimeh F, Roshanzamir M, Sarrafzadegan N, Nahavandi S. Non-invasive detection of coronary artery disease in high-risk patients based on the stenosis prediction of separate coronary arteries. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2018; 162:119-127. [PMID: 29903478 DOI: 10.1016/j.cmpb.2018.05.009] [Citation(s) in RCA: 40] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/18/2017] [Revised: 04/24/2018] [Accepted: 05/03/2018] [Indexed: 05/10/2023]
Abstract
BACKGROUND AND OBJECTIVE Cardiovascular diseases are an extremely widespread sickness and account for 17 million deaths in the world per annum. Coronary artery disease (CAD) is one of such diseases with an annual mortality rate of about 7 million. Thus, early diagnosis of CAD is of vital importance. Angiography is currently the modality of choice for the detection of CAD. However, its complications and costs have prompted researchers to seek alternative methods via machine learning algorithms. METHODS The present study proposes a novel machine learning algorithm. The proposed algorithm uses three classifiers for detection of the stenosis of three coronary arteries, i.e., left anterior descending (LAD), left circumflex (LCX) and right coronary artery (RCA) to get higher accuracy for CAD diagnosis. RESULTS This method was applied on the extension of Z-Alizadeh Sani dataset which contains demographic, examination, ECG, and laboratory and echo data of 500 patients. This method achieves an accuracy, sensitivity and specificity rates of 96.40%, 100% and 88.1%, respectively for the detection of CAD. To our knowledge, such high rates of accuracy and sensitivity have not been attained elsewhere before. CONCLUSION This new algorithm reliably distinguishes those with normal coronary arteries from those with CAD which may obviate the need for angiography in the normal group.
Collapse
Affiliation(s)
- Roohallah Alizadehsani
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Victoria 3217, Australia
| | - Mohammad Javad Hosseini
- Department of Computer Science and Engineering, University of Washington, Seattle, United States
| | - Abbas Khosravi
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Victoria 3217, Australia.
| | - Fahime Khozeimeh
- Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
| | - Mohamad Roshanzamir
- Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran
| | - Nizal Sarrafzadegan
- Isfahan Cardiovascular Research Center, Cardiovascular Research Institute, Isfahan University of Medical Sciences,Isfahan,Iran & Faculty of Medicine, SPPH, University of British Columbia, Vancouver,BC, Canada
| | - Saeid Nahavandi
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Victoria 3217, Australia
| |
Collapse
|
13
|
Zhao C, Jiang J, Guan Y, Guo X, He B. EMR-based medical knowledge representation and inference via Markov random fields and distributed representation learning. Artif Intell Med 2018; 87:49-59. [PMID: 29691122 DOI: 10.1016/j.artmed.2018.03.005] [Citation(s) in RCA: 18] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2017] [Revised: 02/28/2018] [Accepted: 03/29/2018] [Indexed: 01/09/2023]
Abstract
OBJECTIVE Electronic medical records (EMRs) contain medical knowledge that can be used for clinical decision support (CDS). Our objective is to develop a general system that can extract and represent knowledge contained in EMRs to support three CDS tasks-test recommendation, initial diagnosis, and treatment plan recommendation-given the condition of a patient. METHODS We extracted four kinds of medical entities from records and constructed an EMR-based medical knowledge network (EMKN), in which nodes are entities and edges reflect their co-occurrence in a record. Three bipartite subgraphs (bigraphs) were extracted from the EMKN, one to support each task. One part of the bigraph was the given condition (e.g., symptoms), and the other was the condition to be inferred (e.g., diseases). Each bigraph was regarded as a Markov random field (MRF) to support the inference. We proposed three graph-based energy functions and three likelihood-based energy functions. Two of these functions are based on knowledge representation learning and can provide distributed representations of medical entities. Two EMR datasets and three metrics were utilized to evaluate the performance. RESULTS As a whole, the evaluation results indicate that the proposed system outperformed the baseline methods. The distributed representation of medical entities does reflect similarity relationships with respect to knowledge level. CONCLUSION Combining EMKN and MRF is an effective approach for general medical knowledge representation and inference. Different tasks, however, require individually designed energy functions.
Collapse
Affiliation(s)
- Chao Zhao
- School of Computer Science and Technology, Harbin, Heilongjiang 150001, China.
| | - Jingchi Jiang
- School of Computer Science and Technology, Harbin, Heilongjiang 150001, China.
| | - Yi Guan
- School of Computer Science and Technology, Harbin, Heilongjiang 150001, China.
| | - Xitong Guo
- School of Management, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China.
| | - Bin He
- School of Computer Science and Technology, Harbin, Heilongjiang 150001, China.
| |
Collapse
|
14
|
Jiang J, Xie J, Zhao C, Su J, Guan Y, Yu Q. Max-margin weight learning for medical knowledge network. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2018; 156:179-190. [PMID: 29428070 DOI: 10.1016/j.cmpb.2018.01.005] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/30/2017] [Revised: 10/30/2017] [Accepted: 01/10/2018] [Indexed: 06/08/2023]
Abstract
BACKGROUND AND OBJECTIVE The application of medical knowledge strongly affects the performance of intelligent diagnosis, and method of learning the weights of medical knowledge plays a substantial role in probabilistic graphical models (PGMs). The purpose of this study is to investigate a discriminative weight-learning method based on a medical knowledge network (MKN). METHODS We propose a training model called the maximum margin medical knowledge network (M3KN), which is strictly derived for calculating the weight of medical knowledge. Using the definition of a reasonable margin, the weight learning can be transformed into a margin optimization problem. To solve the optimization problem, we adopt a sequential minimal optimization (SMO) algorithm and the clique property of a Markov network. Ultimately, M3KN not only incorporates the inference ability of PGMs but also deals with high-dimensional logic knowledge. RESULTS The experimental results indicate that M3KN obtains a higher F-measure score than the maximum likelihood learning algorithm of MKN for both Chinese Electronic Medical Records (CEMRs) and Blood Examination Records (BERs). Furthermore, the proposed approach is obviously superior to some classical machine learning algorithms for medical diagnosis. To adequately manifest the importance of domain knowledge, we numerically verify that the diagnostic accuracy of M3KN is gradually improved as the number of learned CEMRs increase, which contain important medical knowledge. CONCLUSIONS Our experimental results show that the proposed method performs reliably for learning the weights of medical knowledge. M3KN outperforms other existing methods by achieving an F-measure of 0.731 for CEMRs and 0.4538 for BERs. This further illustrates that M3KN can facilitate the investigations of intelligent healthcare.
Collapse
Affiliation(s)
- Jingchi Jiang
- School of Computer Science and Technology, Harbin Institute of Technology, Comprehensive Building 803 Harbin 150001, China.
| | - Jing Xie
- School of Computer Science and Technology, Harbin Institute of Technology, Comprehensive Building 803 Harbin 150001, China
| | - Chao Zhao
- School of Computer Science and Technology, Harbin Institute of Technology, Comprehensive Building 803 Harbin 150001, China
| | - Jia Su
- School of Computer Science and Technology, Harbin Institute of Technology, Comprehensive Building 803 Harbin 150001, China
| | - Yi Guan
- School of Computer Science and Technology, Harbin Institute of Technology, Comprehensive Building 803 Harbin 150001, China.
| | - Qiubin Yu
- Medical Record Room, The 2nd Affiliated Hospital of Harbin Medical University, Harbin 150086, China
| |
Collapse
|