Hairsentinel: A Time-Aware Anomaly Detection Framework for Forecasting Hairfall Trends Using Temporal Fusion Transformers
October 2025
in “
Frontiers in Artificial Intelligence
”
TLDR "HairSentinel" accurately detects hairfall trends using simple user data, helping identify health risks early.
The study introduces "HairSentinel," a framework for detecting hairfall trends using Temporal Fusion Transformers (TFT) with a focus on time-aware anomaly detection. Unlike traditional methods that rely on complex image-based techniques, this approach uses user-provided data collected daily or weekly through simple questions. The TFT model demonstrated superior performance with 97.5% accuracy and 97.4% precision, outperforming other models like LSTM, Random Forest, and ARIMAX. This framework allows for the proactive detection of hairfall anomalies, aiding in the early identification of potential health risks and suggesting dietary plans to address issues such as hormonal fluctuations.