1
|
Qiao H, Chen Y, Qian C, Guo Y. Clinical data mining: challenges, opportunities, and recommendations for translational applications. J Transl Med 2024; 22:185. [PMID: 38378565 PMCID: PMC10880222 DOI: 10.1186/s12967-024-05005-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2023] [Accepted: 02/18/2024] [Indexed: 02/22/2024] Open
Abstract
Clinical data mining of predictive models offers significant advantages for re-evaluating and leveraging large amounts of complex clinical real-world data and experimental comparison data for tasks such as risk stratification, diagnosis, classification, and survival prediction. However, its translational application is still limited. One challenge is that the proposed clinical requirements and data mining are not synchronized. Additionally, the exotic predictions of data mining are difficult to apply directly in local medical institutions. Hence, it is necessary to incisively review the translational application of clinical data mining, providing an analytical workflow for developing and validating prediction models to ensure the scientific validity of analytic workflows in response to clinical questions. This review systematically revisits the purpose, process, and principles of clinical data mining and discusses the key causes contributing to the detachment from practice and the misuse of model verification in developing predictive models for research. Based on this, we propose a niche-targeting framework of four principles: Clinical Contextual, Subgroup-Oriented, Confounder- and False Positive-Controlled (CSCF), to provide guidance for clinical data mining prior to the model's development in clinical settings. Eventually, it is hoped that this review can help guide future research and develop personalized predictive models to achieve the goal of discovering subgroups with varied remedial benefits or risks and ensuring that precision medicine can deliver its full potential.
Collapse
Affiliation(s)
- Huimin Qiao
- Medical Big Data and Bioinformatics Research Centre, First Affiliated Hospital of Gannan Medical University, Ganzhou, China
| | - Yijing Chen
- School of Public Health and Health Management, Gannan Medical University, Ganzhou, China
| | - Changshun Qian
- School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China
| | - You Guo
- Medical Big Data and Bioinformatics Research Centre, First Affiliated Hospital of Gannan Medical University, Ganzhou, China.
- School of Public Health and Health Management, Gannan Medical University, Ganzhou, China.
- School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China.
- Ganzhou Key Laboratory of Medical Big Data, Ganzhou, China.
| |
Collapse
|
2
|
Usuki K, Ohtake S, Honda S, Matsuda M, Wakita A, Nawa Y, Takase K, Maeda A, Sezaki N, Yokoyama H, Takada S, Hirano D, Tomikawa T, Sumi M, Yano S, Handa H, Ota S, Fujita H, Fujimaki K, Mugitani A, Kojima K, Kajiguchi T, Fujimoto K, Asou N, Usui N, Ishikawa Y, Katsumi A, Matsumura I, Kiyoi H, Miyazaki Y. Real-world data of AML in Japan: results of JALSG clinical observational study-11 (JALSG-CS-11). Int J Hematol 2024; 119:24-38. [PMID: 38015362 DOI: 10.1007/s12185-023-03677-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2023] [Revised: 10/23/2023] [Accepted: 10/31/2023] [Indexed: 11/29/2023]
Abstract
This report covers acute myeloid leukemia (AML) results from a multicenter, prospective observational study of AML, myelodysplastic syndromes, and chronic myelomonocytic leukemia in Japan. From August 2011 to January 2016, 3728 AML patients were registered. Among them, 42% were younger than 65, and the male-to-female ratio was 1.57:1. With a median follow-up time of 1807 days (95% confidence interval [CI]: 1732-1844 days), the estimated 5-year overall survival (OS) rate in AML patients (n = 3707) was 31.1% (95% CI: 29.5-32.8%). Trial-enrolled patients had a 1.7-fold higher OS rate than non-enrolled patients (5-year OS, 58.9% [95% CI: 54.5-63.1%] vs 35.5% [33.3-37.8%], p < 0.0001). Women had a higher OS rate than men (5-year OS, 34% [95% CI; 31.4-36.7%] vs 27.7% [25.7-29.7%], p < 0.0001). The OS rate was lower in patients aged 40 and older than those under 40, and even lower in those over 65 (5-year OS for ages < 40, 40-64, 65-74, ≥ 75: 74.5% [95% CI; 69.3-79.0%] vs 47.5% [44.4-50.6%] vs 19.3% [16.8-22.0%] vs 7.3% [5.5-9.4%], respectively). This is the first paper to present large-scale data on survival and clinical characteristics in Japanese AML patients.
Collapse
Affiliation(s)
- Kensuke Usuki
- Department of Hematology, NTT Medical Center Tokyo, Higashi-Gotanda 5-9-22, Shinagawa-Ku, Tokyo, 141-8625, Japan.
| | | | - Sumihisa Honda
- Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan
| | | | - Atsushi Wakita
- Nagoya City University East Medical Center, Nagoya, Japan
| | - Yuichiro Nawa
- Division of Hematology, Ehime Prefectural Central Hospital, Matsuyama, Japan
| | | | | | | | | | - Satoru Takada
- Leukemia Research Center, Saiseikai Maebashi Hospital, Maebashi, Japan
| | - Daiki Hirano
- Department of Hematology, National Hospital Organization Nagoya Medical Center, Nagoya, Japan
| | - Tatsuki Tomikawa
- Department of Hematology, Saitama Medical Center, Saitama Medical University, Kawagoe, Japan
| | | | - Shingo Yano
- Division of Clinical Oncology and Hematology, The Jikei University School of Medicine, Tokyo, Japan
| | | | | | - Hiroyuki Fujita
- Department of Hematology, Yokohama Nanbu Hospital, Yokohama, Japan
| | | | | | - Kensuke Kojima
- Department of Hematology, Kochi Medical School, Kochi University, Nankoku, Japan
| | - Tomohiro Kajiguchi
- Department of Hematology and Oncology, Tosei General Hospital, Seto, Japan
| | - Ko Fujimoto
- Department of Hematology and Rheumatology, Faculty of Medicine, Kindai University, Osaka, Japan
| | - Norio Asou
- International Medical Center, Saitama Medical University, Hidaka, Japan
| | - Noriko Usui
- Department of Clinical Oncology and Hematology, The Jikei University Daisan Hospital, Tokyo, Japan
| | - Yuichi Ishikawa
- Department of Hematology and Oncology, Nagoya University Graduate School of Medicine, Nagoya, Japan
| | - Akira Katsumi
- Department of Hematology, National Center for Geriatrics and Gerontology, Obu, Japan
| | - Itaru Matsumura
- Department of Hematology and Rheumatology, Faculty of Medicine, Kindai University, Osaka, Japan
| | - Hitoshi Kiyoi
- Department of Hematology and Oncology, Nagoya University Graduate School of Medicine, Nagoya, Japan
| | - Yasushi Miyazaki
- Department of Hematology, Atomic Bomb Disease Institute, Nagasaki University, Nagasaki, Japan
| |
Collapse
|
3
|
Guo Y, Niu Y, Liang H, Yang X, Jian J, Tang X, Liu B. A nomogram based on clinical features and molecular abnormalities for predicting the prognosis of patients with acute myeloid leukemia. Transl Cancer Res 2023; 12:3432-3442. [PMID: 38192982 PMCID: PMC10774028 DOI: 10.21037/tcr-23-1192] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2023] [Accepted: 10/29/2023] [Indexed: 01/10/2024]
Abstract
Background The high clinical and molecular heterogeneity of acute myeloid leukemia (AML) has led to an unsatisfactory clinical prognosis, thus we sought to incorporate both clinical features and molecular abnormalities to construct a new prognostic model. Methods A database search of the Gene Expression Omnibus (GEO) revealed 238 cases of adult AML. The independent risk factors were assessed using both univariate and multivariate Cox regression, as well as least absolute shrinkage and selection operator (LASSO) regression. The predictive accuracy, discriminatory power and clinical applicability of the nomogram were determined by the consistency index (C-index), calibration curves and decision curve analysis (DCA). In addition, a single-centre cohort of 135 cases was used for external validation. Results Multivariate Cox regression analysis showed that the independent influences on overall survival (OS) were age, type of disease, DNMT3A, IDH2 and TP53 mutations. The area under the curve (AUC) values for the training set were 0.755, 0.745 and 0.757 at 1, 2 and 3 years respectively; the AUC for the validation set were 0.648, 0.648 and 0.654 at 1, 2 and 3 years; and the AUC for the northwest China set were 0.692, 0.724 and 0.689 at 1, 2 and 3 years. The calibration and DCA indicated good consistency and clinical utility of the nomogram. Finally, younger (age <60 years) and elderly (age ≥60 years) patients were each divided into two risk groups with significantly different survival rates. Conclusions A nomogram consisting of five risk factors was developed for forecasting the prognosis of AML with guaranteed reliability.
Collapse
Affiliation(s)
- Yuancheng Guo
- The First Clinical Medical School, Lanzhou University, Lanzhou, China
| | - Yujie Niu
- The First Clinical Medical School, Lanzhou University, Lanzhou, China
| | - Haiping Liang
- The First Clinical Medical School, Lanzhou University, Lanzhou, China
| | - Xiaoxiao Yang
- The First Clinical Medical School, Lanzhou University, Lanzhou, China
| | - Jinli Jian
- The First Clinical Medical School, Lanzhou University, Lanzhou, China
| | - Xiao Tang
- The First Clinical Medical School, Lanzhou University, Lanzhou, China
| | - Bei Liu
- The First Clinical Medical School, Lanzhou University, Lanzhou, China
- Department of hematology, The First Hospital of Lanzhou University, Lanzhou, China
| |
Collapse
|