The architecture of an IOMT network includes healthcare systems, software applications for medical diagnosis and treatment, and medical devices. Healthcare records, monitoring devices, and hospital equipment all make use of these gadgets. Hence, such devices store very delicate patient healthcare information, and are vulnerable to attacks and illegitimate gains. These data are vulnerable to manipulation and malfunction, which may lead to incorrect therapies, misdiagnoses, and even damaging bodily harm to patient. To detect such kind of assaults in IOMT devices, risk analysis should be performed and the devices constantly observed. This research proposes meta model for Intrusion detection in IOMT devices. It uses three models including LSTM, CNN, and Dense Neural Network and outcompete basic machine learning algorithms with accuracy of 99.87%.