Sleep apnea represents a widespread sleep condition which remains undiagnosed frequently because it causes repeated breathing interruptions that produce severe health complications including heart diseases and tiredness throughout the day and mental decline. This study introduces a new wearable neckband system that detects sleep apnea events by detecting and classifying them. The device uses several physiological sensors which include a contact microphone to analyze tracheal sounds and a pulse oximeter to track SpO2 levels and ECG electrodes to study heart rate variation as well as an acoustic sensor for snoring detection through machine learning and a respiratory effort sensor. Advanced algorithms process the signals from these sensors to detect Obstructive Sleep Apnea (OSA) and Central Sleep Apnea (CSA) through typical physiological patterns. The classification system of the device uses combined parameters from oxygen desaturation measurements and heart rate variation patterns together with tracheal sound changes and snoring detection and respiratory effort stability analysis. The integrated system functions as a portable and cost-effective alternative to traditional polysomnography by enabling continuous at-home monitoring while helping with early diagnosis. The neckband device provides accessible sleep apnea screening to patients while encouraging timely medical intervention and better patient compliance. We demonstrate a wearable neckband system that uses multiple sensing parameters for sleep apnea diagnosis through algorithmic classification.