1.Gene expression-based machine learning model for diagnosis, prognosis, and treatment response prediction in hepatocellular carcinoma: a retrospective study
Tan Thinh NGUYEN ; Thanh Dat NGUYEN ; Phu Qui Le NGUYEN ; Phuong Thi BUI ; Minh Nam NGUYEN
Journal of Yeungnam Medical Science 2026;43(1):21-
Background:
Hepatocellular carcinoma (HCC) remains a leading cause of cancer-related mortality worldwide, largely because of challenges in early diagnosis and the limited sensitivity of conventional biomarkers. Therefore, reliable molecular tools for early detection, prognostic stratification, and individualized treatment predictions are urgently required.
Methods:
This retrospective study analyzed publicly available gene expression datasets. Candidate biomarkers were identified from the GSE14520 cohort using a multistep screening workflow that integrated differential expression analysis, diagnostic performance, and prognostic relevance. A 10-gene diagnostic model was constructed using least absolute shrinkage and selection operator logistic regression and subsequently validated across multiple independent cohorts. Survival outcomes were evaluated using the Kaplan-Meier analysis and treatment responses to sorafenib and transarterial chemoembolization (TACE) were assessed using receiver operating characteristic analysis.
Results:
A 10-gene signature (TOP2A, CDK1, CYP3A4, MASP2, EPHX2, HAO1, RACGAP1, GLYAT, ADH1B, and CYP4A11) was established. The model demonstrated robust internal performance and consistent accuracy across external validation cohorts (area under the curve [AUC], >0.9). This signature effectively identified early-stage HCC and distinguished malignancy from cirrhosis. High-risk scores were significantly associated with poor overall survival and recurrence-free survival (p<0.05). Furthermore, the model could predict treatment sensitivity, with higher risk scores associated with better outcomes for sorafenib (AUC, 0.791), whereas lower risk scores correlated with an improved response to TACE (AUC, 0.768).
Conclusion
Our gene expression-based machine learning model provides a robust tool for HCC diagnosis, prognosis, and treatment response prediction, with potential as a supportive system for personalized clinical decision-making.
2.Treatment hyperthyroidism in children with antithyroid drug at National Pediatric Hospital: Results and some influencing factors.
Hoang Bich Nguyen ; Dat Phu Nguyen
Journal of Medical Research 2007;55(6):104-108
Background: Hyperthyroidism is a disorder of thyroid function in which body tissues are exposed to excessive amount of circulating thyroid hormone. It causes the uncontrolable homeostatic. Objectives:This study aims to learn about the results of the treatment by antithyroid and some factors influencing these results in children at National Hospital for Pediatric. Subjects and method:A descriptive, cross sectional in combination with retrospective and prospective study was conducted on 51 patients with hyperthyroidism were treated by antithyroid in the National Hospital for Pediatric from May 1995 to May 2005 and with therapy duration from 12 months upward. Result: Remission rate was 58.8% (30/51) with an average follow - up period after therapy withdrawal of 2.5 \xb1 1.6 years (13 months in minimum) and the relapse rate was 41.2% (21/51) at the age over 10 years old. The antithyroid drug discontinuation, therapy duration <3 years, stress, infection were factors influencing treatment outcome. Relapse was of 90% when therapy duration was under 3 years. Goiter size at diagnosis moment was a significant determinant factor of relapse. Conclusion: Most patients reached remission. The factors affected treatment results were age, antithyroid drug discontinuation, therapy duration, stress, infection, late treatment, goiter size.
Hyperthyroidism/ pathology
;
therapy
;
Child
3.Physical development of patients with idiopathic nephrotic syndrome in nephrology department, national hospital of pediatrics
Dat Phu Nguyen ; Binh Thi Hoa Hoang
Journal of Medical Research 2007;55(6):117-120
Background: Idiopathic nephrotic syndrome is not uncommon in children. The disease affects children's physical development. Idiopathic nephrotic syndrome cause many complication in which effecting to physical development has been influenced much to their life, study and living activities of children. Objectives:This study aims to learn about the physical development and to find some factors impacting on physical development ofchildren with idiopathic nephrotic syndrome. Subjects and method: A prospective and descriptive study was conducted on 100 patients diagnosed with idiopathic nephrotic syndrome disease who have been followed up for from 1 year to 6 years in that duration since September 2006 to March 2007. Results:Height standard deviation score (SDS) was less than -2 SO in 15.0% patients. Six per cent of patients had weight SDS ofless than 250. Delayed puberty was seen in 21.6% patients. Some factors impacting on physical developmentwere duration of the disease, relapses, nephrtitis-nephrotic syndrome, prolonged corticoid treatment. Conclusion:Idiopathic nephrotic syndrome retarded physical development and puberty in children. It should be considered careful before indicate to use corticoid because using corticoid for a long period will effect to the height development of children.
Nephrotic Syndrome/ pathology
;
therapy
;
Idiopathic minimal change nephrotic syndrome
;
Child

Result Analysis
Print
Save
E-mail