1.The Current Issues and Thoughts on the Empowerment of Famous Doctors' Experience Inheritance by Artificial Intelligence
Xiaochen JIANG ; Fudong LIU ; Chuanlong ZHANG ; Yi LI ; Qian SHEN ; Bo PANG
Journal of Traditional Chinese Medicine 2026;67(7):710-715
In the context of the modernization of traditional Chinese medicine (TCM), the inheritance of the experiences of famous doctors faces significant challenges due to its complex nonlinear characteristics and dynamic evolution. There are still issues in the current inheritance system, such as the homogenization of talent cultivation models, lack of standardized mentoring practices, and monotonous evaluation method, which hinder the systematic inheritance and innovative development of famous doctors' experiences. Based on a systematic review of the current state of artificial intelligence (AI)-assisted inheritance of famous doctors' experiences, this study explores innovative pathways for deep integration of modern information technologies with famous doctors' experiences from key dimensions, including data authenticity assurance, interdisciplinary collaboration mechanisms, and the establishment of dynamic inheritance standards. It proposes a paradigm shift in the inheritance of TCM famous doctors' experiences in the AI era, aiming to build a new TCM inheritance system of "digital intelligence empowerment and cross-disciplinary innovation", providing theoretical support and practical pathways for the inheritance of famous doctors' experiences in TCM.
2.Clinical characteristics and genetic analysis of 22 Chinese pedigrees affected with Neurofibromatosis type I.
Bingjie HU ; Xianhong DING ; Yang LU ; Hongliang CHEN ; Shuaishuai CHEN ; Mengyi XU ; Yicheng FANG ; Bo SHEN
Chinese Journal of Medical Genetics 2026;43(1):19-30
OBJECTIVE:
To explore the genetic variants and phenotypic characteristics of patients with Neurofibromatosis type I (NF1).
METHODS:
Twenty two NF1 patients who presented at Enze Medical (Center) Group in Taizhou between 2018 and 2024 were selected as the study subjects. Clinical phenotype and family history were collected for the patients. Whole exome sequencing (WES) was carried out for the 22 probands to screen the variants of NF1 gene. Candidate variants were verified by Sanger sequencing of their family members. This study was approved by the Medical Ethics Committee of the Hospital (Ethics No.: K20230902).
RESULTS:
The 22 probands were diagnosed between the age of 5 months to 47 years old, and have all shown cafe au lait spots on their skin. Seventeen patients exhibited the phenotype at birth, and 11 had various degrees of neurofibromatosis. Among them, probands 1 and 13 underwent surgical resection of the tumor but had recurred, while proband 12 had amputation due to the huge size and serious impact of the neurofibroma and had no recurrence. Five patients had various degrees of scoliosis. In total 22 germline mutations and one somatic mutation were identified among the 22 families, with 5 variants unreported previously, including 1 nonsense mutation c.1603C>T (Q535*), 3 frameshift mutations [c.7268_7269delCA (Thr2423fs), c.2293del (Arg765Alafs*26), and c.5433_5438delinsGC (Phe1812ArgfsTer50)], and 1 deletion involving exons 41-44 of the NF1 gene and adjacent introns. Proband 13 was found to harbor germline mutation c.6796C>T (Gln2266Ter) and somatic mutation c.1019_1020del (Ser340Cysfs Ter12) in the peripheral blood and tumor tissue, respectively. Among the 22 NF1 probands, 6 had received treatment due to severe illness. Proband 1 had tumor resection in the right upper limb, but was found to have malignant lung tumor and died during follow-up. Proband 12 had multiple recurrence of neurofibroma in the left ring finger. Proband 4 underwent spinal correction surgery due to severe scoliosis. Proband 11 had died due to a central nervous system disease. Among the 22 germline mutations, 6 had led to the occurrence of truncated proteins, which may have a more severe impact on the phenotype.
CONCLUSION
This study investigated the genetic variants and clinical phenotypes of 22 NF1 families and identified 5 novel variants of the NF1 gene, which has expanded the genotypic and phenotypic spectra of the NF1. Preliminary studies have identified an association between truncated mutations, young age, and severe phenotypes, which may provide important clues for prognosis evaluation. For the clinical diagnosis and treatment of NF1, it is necessary to consider the phenotypic characteristics and genetic testing in combination with genetic counseling and long-term follow-up.
Humans
;
Neurofibromatosis 1/pathology*
;
Male
;
Female
;
Pedigree
;
Adult
;
Child
;
Child, Preschool
;
Middle Aged
;
Adolescent
;
Infant
;
Young Adult
;
Neurofibromin 1/genetics*
;
Phenotype
;
Asian People/genetics*
;
Mutation
;
Exome Sequencing
;
East Asian People
3.Differentiation and Treatment of Chemotherapy-Induced Nausea and Vomiting with Traditional Chinese Medicine Based on the Theory of "Yin Qi Descends,While All Yang Qi Ascends"
Borun LI ; Bo PANG ; Yi LI ; Qian SHEN ; Yuwei WANG ; Run YAN
Journal of Traditional Chinese Medicine 2026;67(11):1173-1177
This paper discussed the differentiation and treatment of chemotherapy-induced nausea and vomiting (CINV) in traditional Chinese medicine, based on the theory of "yin qi descends, while all yang qi ascends” from Inner Canon of Yellow Emperor (《黄帝内经》). The core pathogenesis of CINV is attributed to chemotherapy-induced injury to the middle jiao (焦), resulting in the separation of yin and yang and loss of their mutual communication. Acute and explosive CINV is often characterized by "all yang qi ascends", with stomach yang constraint transforming into fire, and qi counterflow leading to vomiting, which can be treated by unblocking stomach yang, draining fire and scattering the counterflow, with Huoxiang Zhengqi Powder (藿香正气散) and medicinals of clearing function. For delayed cases, which are often due to "yin qi descends", and the accumulation of turbid yin obstructs and constrains the deficient yang, the treatment should focus on promoting qi flow to eliminate turbidity, unblocking and boosting yang qi, and Chengqi-series Formulas (承气类方) or Xiao Banxia Decoction (小半夏汤) can be considered. Refractory and anticipated cases usually involve stomach-kidney deficiency and zang-fu (脏腑) organs disharmony, making yin and yang difficult to restore balance, for which the treatment should focus on nourishing both the stomach and kidneys and harmonize the zang-fu organs, with formulas such as Fuzi Lizhong Decoction (附子理中汤) or Xiaoyao Powder (逍遥散) modified as appropriate.
4.The Application of Quantum Dots in Disease Diagnosis and Treatment
Ji-Sheng SHEN ; Li-Li QI ; Jin-Bo WANG ; Zhi-Jian KE ; Qi-Chao WANG
Progress in Biochemistry and Biophysics 2025;52(8):1917-1931
Quantum dots (QDs), nanoscale semiconductor crystals, have emerged as a revolutionary class of nanomaterials with unique optical and electrochemical properties, making them highly promising for applications in disease diagnosis and treatment. Their tunable emission spectra, long-term photostability, high quantum yield, and excellent charge carrier mobility enable precise control over light emission and efficient charge utilization, which are critical for biomedical applications. This article provides a comprehensive review of recent advancements in the use of quantum dots for disease diagnosis and therapy, highlighting their potential and the challenges involved in clinical translation. Quantum dots can be classified based on their elemental composition and structural configuration. For instance, IB-IIIA-VIA group quantum dots and core-shell structured quantum dots are among the most widely studied types. These classifications are essential for understanding their diverse functionalities and applications. In disease diagnosis, quantum dots have demonstrated remarkable potential due to their high brightness, photostability, and ability to provide precise biomarker detection. They are extensively used in bioimaging technologies, enabling high-resolution imaging of cells, tissues, and even individual biomolecules. As fluorescent markers, quantum dots facilitate cell tracking, biosensing, and the detection of diseases such as cancer, bacterial and viral infections, and immune-related disorders. Their ability to provide real-time, in vivo tracking of cellular processes has opened new avenues for early and accurate disease detection. In the realm of disease treatment, quantum dots serve as versatile nanocarriers for targeted drug delivery. Their nanoscale size and surface modifiability allow them to transport therapeutic agents to specific sites, improving drug bioavailability and reducing off-target effects. Additionally, quantum dots have shown promise as photosensitizers in photodynamic therapy (PDT). When exposed to specific wavelengths of light, quantum dots interact with oxygen molecules to generate reactive oxygen species (ROS), which can selectively destroy malignant cells, vascular lesions, and microbial infections. This targeted approach minimizes damage to healthy tissues, making PDT a promising strategy for treating complex diseases. Despite these advancements, the translation of quantum dots from research to clinical application faces significant challenges. Issues such as toxicity, stability, and scalability in industrial production remain major obstacles. The potential toxicity of quantum dots, particularly to vital organs, has raised concerns about their long-term safety. Researchers are actively exploring strategies to mitigate these risks, including surface modification, coating, and encapsulation techniques, which can enhance biocompatibility and reduce toxicity. Furthermore, improving the stability of quantum dots under physiological conditions is crucial for their effective use in biomedical applications. Advances in surface engineering and the development of novel encapsulation methods have shown promise in addressing these stability concerns. Industrial production of quantum dots also presents challenges, particularly in achieving consistent quality and scalability. Recent innovations in synthesis techniques and manufacturing processes are paving the way for large-scale production, which is essential for their widespread adoption in clinical settings. This article provides an in-depth analysis of the latest research progress in quantum dot applications, including drug delivery, bioimaging, biosensing, photodynamic therapy, and pathogen detection. It also discusses the multiple barriers hindering their clinical use and explores potential solutions to overcome these challenges. The review concludes with a forward-looking perspective on the future directions of quantum dot research, emphasizing the need for further studies on toxicity mitigation, stability enhancement, and scalable production. By addressing these critical issues, quantum dots can realize their full potential as transformative tools in disease diagnosis and treatment, ultimately improving patient outcomes and advancing biomedical science.
5.Network Pharmacology and Experimental Verification Unraveled The Mechanism of Pachymic Acid in The Treatment of Neuroblastoma
Hang LIU ; Yu-Xin ZHU ; Si-Lin GUO ; Xin-Yun PAN ; Yuan-Jie XIE ; Si-Cong LIAO ; Xin-Wen DAI ; Ping SHEN ; Yu-Bo XIAO
Progress in Biochemistry and Biophysics 2025;52(9):2376-2392
ObjectiveTraditional Chinese medicine (TCM) constitutes a valuable cultural heritage and an important source of antitumor compounds. Poria (Poria cocos (Schw.) Wolf), the dried sclerotium of a polyporaceae fungus, was first documented in Shennong’s Classic of Materia Medica and has been used therapeutically and dietarily in China for millennia. Traditionally recognized for its diuretic, spleen-tonifying, and sedative properties, modern pharmacological studies confirm that Poria exhibits antioxidant, anti-inflammatory, antibacterial, and antitumor activities. Pachymic acid (PA; a triterpenoid with the chemical structure 3β-acetyloxy-16α-hydroxy-lanosta-8,24(31)-dien-21-oic acid), isolated from Poria, is a principal bioactive constituent. Emerging evidence indicates PA exerts antitumor effects through multiple mechanisms, though these remain incompletely characterized. Neuroblastoma (NB), a highly malignant pediatric extracranial solid tumor accounting for 15% of childhood cancer deaths, urgently requires safer therapeutics due to the limitations of current treatments. Although PA shows multi-mechanistic antitumor potential, its efficacy against NB remains uncharacterized. This study systematically investigated the potential molecular targets and mechanisms underlying the anti-NB effects of PA by integrating network pharmacology-based target prediction with experimental validation of multi-target interactions through molecular docking, dynamic simulations, and in vitro assays, aimed to establish a novel perspective on PA’s antitumor activity and explore its potential clinical implications for NB treatment by integrating computational predictions with biological assays. MethodsThis study employed network pharmacology to identify potential targets of PA in NB, followed by validation using molecular docking, molecular dynamics (MD) simulations, MM/PBSA free energy analysis, RT-qPCR and Western blot experiments. Network pharmacology analysis included target screening via TCMSP, GeneCards, DisGeNET, SwissTargetPrediction, SuperPred, and PharmMapper. Subsequently, potential targets were predicted by intersecting the results from these databases via Venn analysis. Following target prediction, topological analysis was performed to identify key targets using Cytoscape software. Molecular docking was conducted using AutoDock Vina, with the binding pocket defined based on crystal structures. MD simulations were performed for 100 ns using GROMACS, and RMSD, RMSF, SASA, and hydrogen bonding dynamics were analyzed. MM/PBSA calculations were carried out to estimate the binding free energy of each protein-ligand complex. In vitro validation included RT-qPCR and Western blot, with GAPDH used as an internal control. ResultsThe CCK-8 assay demonstrated a concentration-dependent inhibitory effect of PA on NB cell viability. GO analysis suggested that the anti-NB activity of PA might involve cellular response to chemical stress, vesicle lumen, and protein tyrosine kinase activity. KEGG pathway enrichment analysis suggested that the anti-NB activity of PA might involve the PI3K/AKT, MAPK, and Ras signaling pathways. Molecular docking and MD simulations revealed stable binding interactions between PA and the core target proteins AKT1, EGFR, SRC, and HSP90AA1. RT-qPCR and Western blot analyses further confirmed that PA treatment significantly decreased the mRNA and protein expression of AKT1, EGFR, and SRC while increasing the HSP90AA1 mRNA and protein levels. ConclusionIt was suggested that PA may exert its anti-NB effects by inhibiting AKT1, EGFR, and SRC expression, potentially modulating the PI3K/AKT signaling pathway. These findings provide crucial evidence supporting PA’s development as a therapeutic candidate for NB.
6.Inflammatory disorders that affect the cerebral small vessels.
Fei HAN ; Siyuan FAN ; Bo HOU ; Lixin ZHOU ; Ming YAO ; Min SHEN ; Yicheng ZHU ; Joanna M WARDLAW ; Jun NI
Chinese Medical Journal 2025;138(11):1301-1312
This comprehensive review synthesizes the latest advancements in understanding inflammatory disorders affecting cerebral small vessels, a distinct yet understudied category within cerebral small vessel diseases (SVD). Unlike classical SVD, these inflammatory conditions exhibit unique clinical presentations, imaging patterns, and pathophysiological mechanisms, posing significant diagnostic and therapeutic challenges. Highlighting their heterogeneity, this review spans primary angiitis of the central nervous system, cerebral amyloid angiopathy-related inflammation, systemic vasculitis, secondary vasculitis, and vasculitis in autoinflammatory diseases. Key discussions focus on emerging insights into immune-mediated processes, neuroimaging characteristics, and histopathological distinctions. Furthermore, this review underscores the importance of standardized diagnostic frameworks, individualized immunomodulation approaches, and novel targeted therapies to address unmet clinical demands.
Humans
;
Cerebral Small Vessel Diseases/pathology*
;
Inflammation/pathology*
;
Cerebral Amyloid Angiopathy/pathology*
;
Vasculitis, Central Nervous System/pathology*
;
Vasculitis/pathology*
7.Updates and amendments of the Chinese Pharmacopoeia 2025 Edition(Volume Ⅰ)
Hao LI ; Mingrui SHEN ; Peng ZHANG ; Weimin ZHAI ; Long NI ; Bo HAO ; Yuxin ZHAO ; Yi HE ; Shuangcheng MA ; Rong SHU
Drug Standards of China 2025;26(1):17-22
The Chinese Pharmacopoeia is the legal technical standard which should be followed during the research,production,use,and administration of drugs.At present,the new edition of the Chinese Pharmacopoeia is planned to be promulgated and implemented.This article summarizes and analyzes the main characteristics and the content of updates and amendments of the Chinese Pharmacopoeia 2025 Edition(Volume Ⅰ),to provide a reference for the correct understanding and accurate implementation the new edition of the pharmacopoeia.
8.Analysis of FBN1 gene mutations in six Chinese pedigrees affected with Marfan syndrome.
Xianhong DING ; Hongliang CHEN ; Yang LU ; Mengyi XU ; Bingjie HU ; Yicheng FANG ; Bo SHEN
Chinese Journal of Medical Genetics 2025;42(1):41-50
OBJECTIVE:
To determine the types of genetic variants in six Chinese pedigrees affected with Marfan syndrome (MFS) and analyze their clinical characteristics and molecular pathogenesis.
METHODS:
Six MFS pedigrees presented at the Taizhou Enze Medical Center (Group) between 2017 and 2022 were selected as the study subjects. Clinical data of pedigrees were retrospectively analyzed. Peripheral blood samples were collected from the probands and their family members for the extraction of genomic DNA. Whole exome sequencing (WES) was carried out. Candidate variants of the FBN1 gene were verified by Sanger sequencing. Based on the guidelines from the American College of Medical Genetics and Genomics (ACMG), pathogenicity of the candidate variants was assessed. AlphaFold3 and PyMOL software were used for homology modeling of the FBN1 protein and analysis of its three-dimensional structure and amino acid sequence conservation. This study was approved by the Medical Ethics Committee of Taizhou Enze Medical Center (Group) (Ethics No. 20231002).
RESULTS:
Cardiovascular system abnormalities were noted in all pedigrees, ocular abnormalities were present in pedigrees 2 and 5, skeletal system abnormalities were presented in pedigrees 1, and 4 to 6. FBN1 gene mutations were identified in all pedigrees, including c.1957_1958dupGT (p.Asp654fs), c.5014T>A (p.Cys1672Ser), c.8135delC (p.Pro2712fs), c.2302G>T (p.Glu768*), c.3473A>G (p.Glu1158Gly) and c.6169C>T (p.Arg2057*), with each involving a different exon. Four variants were rated as pathogenic, one as likely pathogenic, and one as variant of uncertain significance. Among these, c.5014T>A (p.Cys1672Ser), c.1957_1958dupGT (p.Asp654fs), c.8135delC (p.Pro2712fs), and c.2302G>T (p.Glu768*) were unreported previously. Bioinformatic analysis with SIFT and PolyPhen-2 predicted that the c.5014T>A (p.Cys1672Ser) and c.3473A>G (p.Glu1158Gly) variants were deleterious. Protein homologous sequence alignment analysis revealed that the four novel mutation sites are highly conserved across various species. Homology modeling of the FBN1 protein three-dimensional structure indicated that the six variant sites in the amino acid sequence are all close to hydrogen bonds and may alter the secondary and tertiary structures to varying degrees, thereby confirmed the relationship between the variants and MFS.
CONCLUSION
Four novel variants of the FBN1 gene have been discovered in this study, which has enriched the mutational and phenotypic spectrum of MFS and provided a basis for disease diagnosis and genetic counseling.
Adolescent
;
Adult
;
Child
;
Female
;
Humans
;
Male
;
Middle Aged
;
Young Adult
;
China
;
East Asian People/genetics*
;
Exome Sequencing
;
Fibrillin-1/genetics*
;
Marfan Syndrome/genetics*
;
Mutation
;
Pedigree
;
Retrospective Studies
;
Adipokines
9.Genetic re-analysis of a Chinese pedigree affected with Hypertrophic cardiomyopathy due to a heterozygous truncating variant of ALPK3 gene and literature review.
Chenliang HONG ; Xianhong DING ; Yang LU ; Jia ZHU ; Jinwei WANG ; Mengyi XU ; Shuaishuai CHEN ; Bo SHEN ; Weili GE
Chinese Journal of Medical Genetics 2025;42(11):1337-1346
OBJECTIVE:
To explore the clinical and genetic characteristics of a Chinese pedigree affected with Hypertrophic cardiomyopathy (HCM) due to a truncating variant of ALPK3 gene.
METHODS:
A 44-year-old male admitted to Taizhou Hospital of Zhejiang Province on December 29, 2018 was selected as the study subject. Whole-exome sequencing (WES) was carried out, and candidate variant was interpreted by following the guidelines from the American College of Medical Genetics and Genomics (ACMG). For ALPK3 was considered an autosomal recessive gene, the WES results was considered insufficient to explain his phenotype. In April 2023, the proband's WES data were re-analyzed using updated annotation pipelines, and peripheral blood samples were collected from his first-degree relatives (mother and brother) for Sanger sequencing validation. Conservation analysis and protein structural modeling were performed to assess the impact of the variant. Clinical evaluation and genetic counseling were provided to the proband's family members. Relevant literature on ALPK3tv-induced HCM patients were searched in Wanfang Data Knowledge Service Platform, CNKI, and PubMed database using "ALPK3" and "hypertrophic cardiomyopathy" as keywords. Clinical characteristics of HCM patients with heterozygous ALPK3tv variants were summarized and compared with the clinical characteristics of HCM patients with positive sarcomere-associated gene variants (SARC+). This study was approved by the Medical Ethics Committee of Taizhou Hospital of Zhejiang Province Affiliated to Wenzhou Medical University (Ethics No.: K20230314).
RESULTS:
The proband was a 44-year-old male who was transferred to our institution on December 29, 2018 due to "chest tightness and pain for 6 months, exacerbated for 2 days". Emergency coronary angiography was performed, which led to a preliminary diagnosis of "acute coronary syndrome", and the patient was admitted to the Cardiology Department for treatment. Based on electrocardiogram and echocardiogram findings, the diagnosis was revised as HCM. The patient's condition has stabilized post-coronary angiography, and he was discharged with improved condition. On January 2019, WES was conducted to determine the etiology of the proband's HCM. WES results identified a novel heterozygous c.2156dupC (p.Pro720ThrfsTer53) truncating variant in the ALPK3 gene. At that time, the inheritance pattern could not explain the phenotype. In 2022, a literature indicated that heterozygous ALPK3tv could lead to autosomal dominant HCM. Consequently, in April 2023, the proband's whole-exome data were re-annotated, revealing changes in the transcript and protein versions, with the updated site annotated as ALPK3 (NM_020778.5): c.1550dupC (p.Pro518ThrfsTer53). Sanger sequencing confirmed that the proband's mother and brother also carried this variant. The mother exhibited obstructive HCM, while the brother showed no related phenotype. Bioinformatics analysis demonstrated conservation of this site across multiple species, and the variant has resulted in the loss of a protein domain. Based on ACMG guidelines, the variant was classified as likely pathogenic. Literature review and Bayesian calculation further elevated the pathogenicity rating, indicating that this variant was the cause of HCM in the patient. Literature study revealed distinctions between HCM caused by this variant type and SARC+ HCM. The age of onset among heterozygous ALPK3tv patients was delayed by approximately 10 years compared to SARC+ patients. Both forms of HCM exhibited a male predominance, which was particularly marked in individuals with ALPK3tv. Electrocardiographic left ventricular hypertrophy was more prevalent in heterozygous ALPK3tv patients than in SARC+ patients. The incidence of apical or concentric hypertrophy patterns was higher in heterozygous ALPK3tv patients compared to asymmetric septal hypertrophy, which predominated in SARC+ patients. ALPK3tv patients exhibited lower penetrance and later onset compared to SARC+ patients. A positive correlation between left ventricular wall thickness and age was noted in female patients only.
CONCLUSION
In this pedigree, the proband has presented with HCM, characterized by echocardiographic evidence of apical left ventricular hypertrophy without significant outflow tract obstruction or extracardiac phenotypes. Although his mother and brother had carried the same heterozygous ALPK3 (NM_020778.5) c.1550dupC (p.Pro518ThrfsTer53), the mother exhibited severe obstructive HCM, while the brother was asymptomatic, suggesting incomplete or age-dependent penetrance within the family. This study has enriched the evidence for the pathogenicity of ALPK3tv among Chinese HCM pedigrees and underscored the importance of periodic literature reviews and genetic re-analysis for unresolved genetic testing results.
Humans
;
Male
;
Pedigree
;
Adult
;
Cardiomyopathy, Hypertrophic/genetics*
;
Heterozygote
;
Asian People/genetics*
;
Exome Sequencing
;
Mutation
;
China
;
Female
;
East Asian People
10.Exploration of the Predictive Value of Peripheral Blood-related Indicators for EGFR Mutations and Prognosis in Non-small Cell Lung Cancer Using Machine Learning.
Shulei FU ; Shaodi WEN ; Jiaqiang ZHANG ; Xiaoyue DU ; Ru LI ; Bo SHEN
Chinese Journal of Lung Cancer 2025;28(2):105-113
BACKGROUND:
Epidermal growth factor receptor (EGFR) sensitive mutation is one of the effective targets of targeted therapy for non-small cell lung cancer (NSCLC). However, due to the difficulty of obtaining some primary tissues and the economic factors in some underdeveloped areas, some patients cannot undergo traditional genetic testing. The aim of this study is to establish a machine learning (ML) model using non-invasive peripheral blood markers to explore the biomarkers closely related to EGFR mutation status in NSCLC and evaluate their potential prognostic value.
METHODS:
2642 lung cancer patients who visited Jiangsu Cancer Hospital from November 2016 to May 2023 were retrospectively enrolled and finally 175 NSCLC patients with complete follow-up data were included in the study. The ML model was constructed based on peripheral blood indicators and divided into training set and test set according to the ratio of 8:2. Unsupervised learning algorithms were used for clustering blood features and mutual information method for feature selection, and an ensemble learning algorithm based on Shapley value was designed to calculate the contribution of each feature to the model prediction result. The receiver operating characteristic (ROC) curve was used to evaluate the predictive ability of the model.
RESULTS:
Through the feature extraction and contribution analysis of the predictive results of the interpretable ML model based on the Shapley value, the top ten indicators with the highest contribution were: pathological type, phosphorus, eosinophils, monocyte count, activated partial thromboplastin time, potassium, total bilirubin, sodium, eosinophil percentage, and total cholesterol. The area under the curve (AUC) of the model was 0.80. In addition, patients with hyponatremia and squamous cell carcinoma group had a poor prognosis (P<0.05).
CONCLUSIONS
The interpretable model constructed in this study provides a new approach for the prediction of EGFR mutation status in NSCLC patients, which provides a scientific basis for the diagnosis and treatment of patients who cannot undergo genetic testing.
Humans
;
Carcinoma, Non-Small-Cell Lung/diagnosis*
;
Machine Learning
;
Lung Neoplasms/diagnosis*
;
Male
;
Female
;
Mutation
;
Middle Aged
;
ErbB Receptors/genetics*
;
Prognosis
;
Aged
;
Retrospective Studies
;
Adult
;
Biomarkers, Tumor/genetics*

Result Analysis
Print
Save
E-mail