In the field of health-care and bio-medical research, understanding the
relationship between the symptoms of diseases is crucial for early diagnosis
and determining hidden relationships between diseases. The study aimed to
understand the extent of symptom types in disease prediction tasks. In this
research, we analyze a pre-generated symptom-based human disease dataset and
demonstrate the degree of predictability for each disease based on the
Convolutional Neural Network and the Support Vector Machine. Ambiguity of
disease is studied using the K-Means and the Principal Component Analysis. Our
results indicate that machine learning can potentially diagnose diseases with
the 98-100% accuracy in the early stage, taking the characteristics of symptoms
into account. Our result highlights that types of unusual symptoms are a good
proxy for disease early identification accurately. We also highlight that
unusual symptoms increase the accuracy of the disease prediction task.

本研究分析通过卷积神经网络和支持向量机预测疾病，并使用 K-Means 和主成分分析研究了疾病的歧义性，结果表明机器学习可以在疾病早期阶段对疾病进行 98-100% 准确的诊断。异常症状是诊断疾病的良好代理，同时也提高了疾病预测任务的准确性。