Abstract: This research explores the application of artificial neural networks (ANNs) in predicting cancer using a synthetically generated dataset designed for research purposes. The dataset comprises 10,000 pseudo-patient records, each characterized by gender, age, smoking history, fatigue, and allergy status, along with a binary indicator for the presence or absence of cancer. The 'Gender,' 'Smoking,' 'Fatigue,' and 'Allergy' attributes are binary, while 'Age' spans a range from 18 to 100 years. The study employs a three-layer ANN architecture to develop a predictive model. The achieved accuracy of 97.24% and a low loss value of 0.02 indicate promising performance. Further analysis involves a comprehensive examination of the confusion matrix, precision, recall, and F1 score metrics, along with the ROC curve and AUC score, to provide a detailed understanding of the model's strengths and weaknesses. Additionally, considerations for cross-validation, hyperparameter tuning, and interpretability are discussed. It is emphasized that while the synthetic nature of the dataset allows for controlled experimentation, results should be cautiously interpreted and validated on authentic clinical data before extrapolation to real-world medical scenarios. This research serves as a valuable contribution to the exploration of predictive models for cancer detection, encouraging continued investigation and development in the field.