ABSTRACT
Internet of Medical Things (IoMT) is on-demand research area, generally utilized in most of medical applications. Security is a challenging problem in decentralized platform while handling with medical data or images. An effective deep learning-based blockchain framework with reduced transaction cost is proposed to enhance the security of medical images in IoMT. The proposed study involves four different stages like image acquisition, encryption, optimal key generation, secured storing. The input images initially are collected in the image acquisition stage. Then, the collected medical images are encrypted using coupled map lattice (CML). This encryption process assists to preserve the input medical images from the attackers. In order to provide more confidentiality to the encrypted images, optimal keys are generated using opposition-based sparrow search optimization (O-SSO) algorithm. These encrypted images are stored using distributed ledger technology (DLT) and smart contract based blockchain technology. This blockchain technology enhances the data integrity and authenticity and allows secured transmission of medical images. After decrypting the image, the disease is diagnosed in the classification stage using proposed Recurrent Generative Neural Network (RGNN) model. The proposed study used python tool for simulation analysis and the medical images are gathered from CT images in COVID-19 dataset. © 2022 IEEE.
ABSTRACT
The handling of electronic health records (EHRs) from the Internet of Medical Things (IoMT) is one of the most challenging research areas as it consists of sensitive information which is a target for attackers. Also, it is highly complex and expensive to deal with modern healthcare systems as it requires a lot of secured storage space. However, these problems can be mitigated with the improvement in health record management using blockchain technology. To improve data security, patient privacy, and scalability, the proposed work develops a scalable lightweight framework based on blockchain technology. Initially, the COVID-19 related data records are hashed by using an enhanced Merkle tree (EMT) data structure. The hashed values are encrypted by lattice-based cryptography with a Homomorphic Proxy Re-Encryption scheme (LBC-HPRS) in which the input data are secured. After the completion of the encryption process, the blockchain uses IPFS to store secured information. Finally, the Proof of Work (PoW) concept is utilized to verify and validate the security of the input COVID-based data records. The experimental setup of the proposed work is performed by using a python tool and the performance metrics like encryption time, re-encryption time, decryption time, overall processing time and latency prove the efficacy of the proposed schemes. © 2022 IEEE.
ABSTRACT
Case Report Introduction Patients with mild to moderate diabetic ketoacidosis (DKA) can be safely treated with subcutaneous, rapidacting insulin analogs on the medical floor or in the emergency department. Here we describe a case of COVID pneumonia with DKA, effectively treated with a subcutaneous insulin regimen with anion gap closure in 4 hours since the presentation on medical floors. Case The patient is a 64-year-old male with no medical history, has not been in follow-up with a primary care physician for the past 20 years presents to the emergency department [ED] with a 2-week history of generalized weakness and fatigue. Reports feeling very thirsty and dehydrated with increased frequency of urination. On arrival he was noted to be saturating at 88 to 89% on room air, was switched to non 2 Litres nasal cannula with improvement in saturation to 94%, sinus tachycardia at 110 beats per minute, blood pressure 110/72 mmHg. Blood glucose was noted to be at 486 mg/dL with anion gap greater than 24 mEq/L, bicarbonate less than 10 mEq/L, creatinine at 1.62 mg/dL. Arterial blood gas analysis showed pH of 7.39, partial pressure of carbon dioxide at 16, partial pressure of oxygen at 61, bicarbonate of 10 suggestive of metabolic acidosis with respiratory compensation. He received a bolus of 0.3 units/kg [21 units] of subcutaneous insulin lispro (rapid-acting). Then was switched to 0.2 units/kg [14 units] subcutaneous insulin every 2 hours, the basic metabolic panel was done every 2 hours. Anion gap was closed in 4 hours. For transition, we calculated 0.5 units/kg [35 units] which was divided into basal - insulin glargine 17 units and bolus - sliding scale insulin lispro before meals and bedtime (insulin naive patient). His anion gap remained closed thereafter. He was treated with remdesivir and dexamethasone for COVID pneumonia. He was discharged after 5 days with improvement in his respiratory status from COVID pneumonia with outpatient follow-up. Discussion Subcutaneous insulin protocols are being used with increasing frequency to treat selected patients with mild to moderate DKA. Especially during this COVID pandemic, this helps to decrease the exposure frequency of staff (health care workers especially doctors and nursing staff) to patients given insulin dosing and lab frequency of 2-4 hours (compared with hourly checks for insulin intravenous drip), decreases the use of personal protective equipment (PPE), decreases the upgrade to intensive care units (ICU) that in turn helps with effective resources management in ICU for more critical patients. This protocol has not been studied in severe DKA yet but has similar efficacy and safety in mild or moderate DKA patients when compared to IV insulin therapy.