ABSTRACT
With the emergence of COVID-19, smart healthcare, the Internet of Medical Things, and big data-driven medical applications have become even more important. The biomedical data produced is highly confidential and private. Unfortunately, conventional health systems cannot support such a colossal amount of biomedical data. Hence, data is typically stored and shared through the cloud. The shared data is then used for different purposes, such as research and discovery of unprecedented facts. Typically, biomedical data appear in textual form (e.g., test reports, prescriptions, and diagnosis). Unfortunately, such data is prone to several security threats and attacks, for example, privacy and confidentiality breach. Although significant progress has been made on securing biomedical data, most existing approaches yield long delays and cannot accommodate real-time responses. This paper proposes a novel fog-enabled privacy-preserving model called δ r sanitizer, which uses deep learning to improve the healthcare system. The proposed model is based on a Convolutional Neural Network with Bidirectional-LSTM and effectively performs Medical Entity Recognition. The experimental results show that δ r sanitizer outperforms the state-of-the-art models with 91.14% recall, 92.63% in precision, and 92% F1-score. The sanitization model shows 28.77% improved utility preservation as compared to the state-of-the-art.
ABSTRACT
Purpose To study the spectrum of chest dual-energy computed tomography (DECT) imaging findings in severe acute respiratory syndrome coronavirus 2 (SARS-COV-2) or COVID-19 infected Indian patients and classify them on the basis of the Radiological Society of North America CT classification. Method A total of 110 reverse transcription-polymerase chain reaction (RT-PCR)-positive patients (subjects) in which noncontrast chest DECT was done in our COVID-19 care center (CCC) were enrolled in this study. The prevalence of various abnormalities of lung parenchyma due to SARS-COV-2 and their distribution with extent was recorded. Various types of lung parenchyma abnormalities due to COVID-19 were evaluated in all patients. Data were analyzed and various prevalent abnormalities were calculated as a percentage for each type. All the cases were also sorted into four major groups on the basis of the Radiological Society of North America CT classification of COVID patients. Result Among the total 110 patients that were enrolled in this study, 80 (72.7%) were males and 30 (27.3%) were females with a mean age of 40.5 ± 7 years (range 24-84). Out of this, we observed that 59 (53.6%) cases had abnormalities of lung parenchyma and were designated as DECT positive, whereas 51 (46.3%) cases had completely normal DECT. Only 14 (12.7%) of the patients (cases) presented with dyspnoea, 10 (9%) had hyperpnoea, whereas 12 (10.8%) had other associated comorbidities. Among the patients having abnormal DECT findings, multilobar (86%), bilateral lung field involvement (72.8%) with the ascendancy of peripheral and posterior distribution was most commonly noted. With respect to the different types of opacities noted in various patients, we found that ground-glass opacity (GGO) was the common abnormality found in almost all cases for the greatest part. Pure GGO was reported in 16 (28%), GGO admixed with a crazy-paving pattern were elicited in 17 (28.8%) and GGO mixed with consolidation was noted in 25 (42.3%) cases. Thirty-eight (64.4%) cases were having peri-lesional or intra-lesional segments or involving a small segment enlargement of the pulmonary vessel. Among the cases showing DECT positivity, the typical pattern on the basis of the Radiological Society of North America (RSNA) classification was noted in 71.2% of cases, whereas the atypical pattern was found in 1.2% percent of cases and the intermediate type was depicted in 25.4% percent of cases. Forty-six point three percent (46.3%) of the total cases that were enrolled in the study were grouped as the no pneumonia category. Conclusion The result of this study proved that the maximum number of RT-PCR-positive COVID-19 patients had mild symptoms and few comorbidities with normal chest DECT and fell under the no pneumonia category of the RSNA CT classification of COVID patients. However, out of the remaining patients, the majority of patients had GGO on DECT as a typical finding mixed with other patterns in a bilateral distribution and peripheral predominance. A preponderance of patients presented with the typical appearance of pneumonia followed by an intermediate type.