@article{4786,
  author = {Hsing-Cheng Liu, Yao-Liang Chung},
  title = {Clinical Symptom Profiles and Phenotypic Clusters in Familial vs. Sporadic Neurofi bromatosis Type 1: A Comprehensive Exploratory Analysis of the UCI NF1 Dataset},
  journal = {Journal of Data Processing},
  year = {2026},
  volume = {16},
  number = {3},
  doi = {https://doi.org/10.6025/jdp/2026/16/3/143-160},
  url = {https://www.dline.info/jdp/fulltext/v16n3/jdpv16n3_2.pdf},
  abstract = {Neurofibromatosis type 1 (NF1) exhibits significant phenotypic heterogeneity, yet comprehensive exploratory
analyses comparing familial and sporadic forms remain limited. This study investigated clinical symptom
distributions and identified latent phenotypic clusters using the UCI NF1 dataset comprising 331 probands.
We employed descriptive statistics, correlation analyses, symptom co-occurrence networks, UpSet plots,
and hierarchical clustering to characterize phenotypic variability. Results revealed that café au lait spots,
freckling, and Lisch nodules are the most prevalent and interconnected core manifestations. While familial
(n=135) and sporadic (n=161) cases demonstrated substantial phenotypic overlap, familial cases exhibited
modestly higher rates of optic glioma, skeletal dysplasia, plexiform neurofibromas, and overall tumor burden.
Hierarchical clustering successfully delineated robust, biologically plausible symptom modules, including a
core pigmentary cluster, a neuro ophthalmic and tumor related cluster, and a skeletal and developmental
cluster. These findings underscore that NF1 manifestations form distinct, highly interconnected phenotypic
clusters rather than occurring randomly. Recognizing these latent subtypes can significantly enhance
diagnostic stratification, optimize longitudinal surveillance, and facilitate the early identification of highrisk
patients. Furthermore, we propose a conceptual multi layer clinical decision support framework
integrating machine learning and explainable artificial intelligence to translate these exploratory insights
into personalized precision medicine. Future prospective validation incorporating multimodal data is
warranted to refine these predictive models and ultimately improve long term clinical outcomes for NF1
patients.},
}