Raman Spectroscopy-Based Deep Learning Model for Early Pan-Cancer Early Diagnosis

Condition(s) studied

Investigational drug(s) / intervention(s)

No Interventions: All blood samples from participating patients were obtained from routine clinical blood tests conducted during hospital admission or other necessary medical evaluations, followed by serum extraction.

Study summary

The goal of this observational study is to explore whether a Raman-based, deep learning-assisted approach can be used to develop an effective method for early pan-cancer screening. The study includes healthy individuals, patients at risk of cancer, and patients with diagnosed cancers. The main questions it aims to answer are:

* Evaluating the deep-learning model's accuracy and specificity in identifying cancer-specific features in Raman spectral data and determining whether this method can accurately classify patients based on risk.
* Identifying which model is more adaptable to the Raman spectrum
* Providing an interpretable analysis of the model-generated diagnosis Participants are already being diagnosed and follow-up to determine the type of cancer.

Eligibility

Primary outcome measure(s)

• A Deep Learning Model for High-Accuracy Pan-Cancer Classification — From patient enrollment to the completion of model construction, expected to be finalized within two months after data collection.
  Establish deep learning models with high specificity and sensitivity for pan-cancer classification, capable of distinguishing different pan-cancer types (Distinguish between patients in physiological conditions, precancerous lesion and malignant tumour) based on Raman spectroscopy.

Trial sites (4)

More Second Affiliated Hospital, Zhejiang University, School of Medicine trials in China

Other trials for the same condition