Malignant hyperthermia (MH) is a rare life threatening inherited disorder that is triggered by drugs used for general anesthesia in susceptible persons. The symptoms include rapid increase of body temperature and severe muscle contractions. The present study includes 3 cases of MH and highlights the timely identification of symptoms for rescuing the patient. In case I, a 7-year-old male child underwent surgery with ketamine at a dose of 250 mg. After 4 h of operation, the child went through convulsions, high fever and succumbed within a few hours. High fever was not detected in a timely manner, which is one of the main symptoms of MH. In case II, a 12-year-old male child had convulsions and high fever after simple surgery caused by MH. Once confirmed, immediate measures were taken to lower the body temperature and the child was rescued. In case III, a male 57-year-old was admitted to hospital due to paraplegia. The patient underwent more critical conditions once symptoms of MH appeared. Additionally, antidote dantrolene was unavailable in the first and third case; thus, the progression of disease was not alleviated although active symptomatic and supportive treatment were employed.

The paper proposes a method based on dense-sparse-dense optimization algorithm. It uses sparsity to tune network weights. By adding fuzzy membership, the optimization strategy can enhance the feature information with larger weights and weaken the feature information with less weight. Through accurate cutting of network weights, parameters in network are effectively reduced. The experimental results show that the performance of this method is better than the existing method.