Deep-Confidentiality : An IoT-Enabled Privacy-Preserving Framework for Unstructured Big Biomedical Data

Due to the Internet of Things evolution, the clinical data is exponentially growing and using smart technologies. The generated big biomedical data is confidential, as it contains a patient’s personal information and findings. Usually, big biomedical data is stored over the cloud, making it convenient to be accessed and shared. In this view, the data shared for research purposes helps to reveal useful and unexposed aspects. Unfortunately, sharing of such sensitive data also leads to certain privacy threats. Generally, the clinical data is available in textual format (e.g., perception reports). Under the domain of natural language processing, many research studies have been published to mitigate the privacy breaches in textual clinical data. However, there are still limitations and shortcomings in the current studies that are inevitable to be addressed. In this article, a novel framework for textual medical data privacy has been proposed as Deep-Confidentiality . The proposed framework improves Medical Entity Recognition (MER) using deep neural networks and sanitization compared to the current state-of-the-art techniques. Moreover, the new and generic utility metric is also proposed, which overcomes the shortcomings of the existing utility metric. It provides the true representation of sanitized documents as compared to the original documents. To check our proposed framework’s effectiveness, it is evaluated on the i2b2-2010 NLP challenge dataset, which is considered one of the complex medical data for MER. The proposed framework improves the MER with 7.8% recall, 7% precision, and 3.8% F1-score compared to the existing deep learning models. It also improved the data utility of sanitized documents up to 13.79%, where the value of the k is 3.

Using a Deep Learning Model to Explore the Impact of Clinical Data on COVID-19 Diagnosis Using Chest X-ray

The coronavirus pandemic (COVID-19) is disrupting the entire world; its rapid global spread threatens to affect millions of people. Accurate and timely diagnosis of COVID-19 is essential to control the spread and alleviate risk. Due to the promising results achieved by integrating machine learning (ML), particularly deep learning (DL), in automating the multiple disease diagnosis process. In the current study, a model based on deep learning was proposed for the automated diagnosis of COVID-19 using chest X-ray images (CXR) and clinical data of the patient. The aim of this study is to investigate the effects of integrating clinical patient data with the CXR for automated COVID-19 diagnosis. The proposed model used data collected from King Fahad University Hospital, Dammam, KSA, which consists of 270 patient records. The experiments were carried out first with clinical data, second with the CXR, and finally with clinical data and CXR. The fusion technique was used to combine the clinical features and features extracted from images. The study found that integrating clinical data with the CXR improves diagnostic accuracy. Using the clinical data and the CXR, the model achieved an accuracy of 0.970, a recall of 0.986, a precision of 0.978, and an F-score of 0.982. Further validation was performed by comparing the performance of the proposed system with the diagnosis of an expert. Additionally, the results have shown that the proposed system can be used as a tool that can help the doctors in COVID-19 diagnosis.

Novel Insight into the Mechanisms of the Bidirectional Relationship between Diabetes and Periodontitis

Periodontitis and diabetes are two major global health problems despite their prevalence being significantly underreported and underestimated. Both epidemiological and intervention studies show a bidirectional relationship between periodontitis and diabetes. The hypothesis of a potential causal link between the two diseases is corroborated by recent studies in experimental animals that identified mechanisms whereby periodontitis and diabetes can adversely affect each other. Herein, we will review clinical data on the existence of a two-way relationship between periodontitis and diabetes and discuss possible mechanistic interactions in both directions, focusing in particular on new data highlighting the importance of the host response. Moreover, we will address the hypothesis that trained immunity may represent the unifying mechanism explaining the intertwined association between diabetes and periodontitis. Achieving a better mechanistic insight on clustering of infectious, inflammatory, and metabolic diseases may provide new therapeutic options to reduce the risk of diabetes and diabetes-associated comorbidities.

An Accelerated Thrombosis Model for Computational Fluid Dynamics Simulations in Rotary Blood Pumps

Purpose Thrombosis ranks among the major complications in blood-carrying medical devices and a better understanding to influence the design related contribution to thrombosis is desirable. Over the past years many computational models of thrombosis have been developed. However, numerically cheap models able to predict localized thrombus risk in complex geometries are still lacking. The aim of the study was to develop and test a computationally efficient model for thrombus risk prediction in rotary blood pumps. Methods We used a two-stage approach to calculate thrombus risk. The first stage involves the computation of velocity and pressure fields by computational fluid dynamic simulations. At the second stage, platelet activation by mechanical and chemical stimuli was determined through species transport with an Eulerian approach. The model was compared with existing clinical data on thrombus deposition within the HeartMate II. Furthermore, an operating point and model parameter sensitivity analysis was performed. Results Our model shows good correlation (R2 > 0.93) with clinical data and identifies the bearing and outlet stator region of the HeartMate II as the location most prone to thrombus formation. The calculation of thrombus risk requires an additional 10–20 core hours of computation time. Conclusion The concentration of activated platelets can be used as a surrogate and computationally low-cost marker to determine potential risk regions of thrombus deposition in a blood pump. Relative comparisons of thrombus risk are possible even considering the intrinsic uncertainty in model parameters and operating conditions.

Clinical Features and Early Recognition of 242 Cases of Autoimmune Encephalitis

Objective: To analyze the clinical features of common autoimmune encephalitis and evaluate the sensitivity of antibodies contributing to focal epilepsy signs and symptoms (ACES) score.Methods: Collecting and analyzing the data of 242 patients with autoimmune encephalitis (AE) diagnosed in the First Affiliated Hospital of Zhengzhou University from August 2015 to December 2020 in this retrospective study. The six items of the ACES score (cognitive symptoms, behavioral changes, autonomic symptoms, speech problems, autoimmune diseases, temporal MRI hyperintensities) were screened in patients with complete clinical data.Results: (1) In total, 242 patients were included, with 147 cases of anti-N-methyl-D-aspartate receptor encephalitis, 47 cases of anti-γ-aminobutyric acid type B (GABA-B) receptor encephalitis, and 48 cases of anti-leucine-rich glioma inactivating protein 1 (LGI1) encephalitis. The most common clinical symptoms are cognitive impairment (77%), behavioral changes (79%), and seizures (71%). In total, 129 cases (54%) combined with autonomic dysfunction, such as gastrointestinal dysmotility, sinus tachycardia, and central hypoventilation. Twelve patients had autoimmune diseases, most of which were of thyroid diseases. (2) One hundred and twenty-seven patients with complete clinical data evaluated ACES score, 126 cases of whom (126/127, 99.2%) were equal to or >2 points, 1 case (1/127, 0.8%) was of <2 points.Interpretation: (1) Cognitive impairment, abnormal behavior, and seizures are the most common manifestations of AE and autonomic symptoms. Thyroid disease is the most autoimmune disease in AE. Clinically, for patients of suspected AE, increasing the knowledge and testing of thyroid function and rheumatism is necessary. (2) ACES score is a simple, effective, and easy-to-operate score, with a certain screening value for most patients suspected of AE.

Nanoparticle albumin-bound paclitaxel and PD-1 inhibitor (sintilimab) combination therapy for soft tissue sarcoma: a retrospective study

Background There is increasing evidence that combination therapy with nanoparticle albumin-bound paclitaxel (nab-paclitaxel) and programmed cell death protein 1 (PD-1) inhibitor is safe and efficacious in treating many types of malignant tumors. However, clinical data demonstrating the effect of this treatment combination for patients with metastatic soft tissue sarcoma (STS) are currently limited. Methods The clinical data of patients with metastatic STS who received nab-paclitaxel plus PD-1 inhibitor (sintilimab) therapy between January 2019 and February 2021 were retrospectively analyzed. The effectiveness and safety of the combined treatment were evaluated in terms of the median progression-free survival (PFS), estimated using the Kaplan–Meier method. The univariate Cox proportional hazards model was used to analyze the relationship between clinicopathological parameters and PFS. All statistical analyses were two-sided; P < 0.05 was considered statistically significant. Results A total of 28 patients treated with nab-paclitaxel plus sintilimab were enrolled in this study. The objective response rate was 25%, the disease control rate was 50%, and the median PFS was 2.25 months (95% CI = 1.8–3.0 months). The most common grade 1 or 2 adverse events (AEs) were alopecia (89.3%; 25/28), leukopenia (25.0%; 7/28), fatigue (21.4%; 6/28), anemia (21.4%; 6/28), and nausea (21.4%; 6/28). The most common grade 3 AEs were neutropenia (10.7%; 3/28) and peripheral neuropathy (10.7%; 3/28). No grade 4 AEs were observed. Among the present study cohort, patients with angiosarcoma (n = 5) had significantly longer PFS (P = 0.012) than patients with other pathological subtypes, including undifferentiated pleomorphic sarcoma (n = 7), epithelioid sarcoma (n = 5), fibrosarcoma (n = 4), synovial sarcoma (n = 3), leiomyosarcoma (n = 2), pleomorphic liposarcoma (n = 1), and rhabdomyosarcoma (n = 1); those who experienced three or more AEs had significantly longer median PFS than those who experienced less than three AEs (P = 0.018). Conclusion Nab-paclitaxel plus PD-1 inhibitor is a promising treatment regimen for advanced STS. Randomized controlled clinical trials are required to further demonstrate its efficacy and optimal application scenario.

Investigation of PALB2 Mutation and Correlation With Immunotherapy Biomarker in Chinese Non-Small Cell Lung Cancer Patients

BackgroundPALB2, a gene in the homologous recombination repair (HRR) pathway of the DNA damage response (DDR), is associated with the efficacy of platinum-based chemotherapy, immunotherapy, and PARP inhibitor therapy in several tumors. However, the PALB2 characteristics, its correlation with immunotherapy biomarker, and the prognostic effect of immunotherapy in non-small cell lung cancer (NSCLC) were unknown.MethodsTumor tissue samples from advanced Chinese NSCLC patients were analyzed by next-generation sequencing (NGS) (panel on 381/733-gene). Tumor mutation burden (TMB) is defined as the total number of somatic non-synonymous mutations in the coding region. Microsatellite instability (MSI) was evaluated by NGS of 500 known MSI loci. Programmed Cell Death-Ligand 1 (PD-L1) expression was evaluated using immunohistochemistry (Dako 22C3 or SP263). One independent cohort (Rizvi2018.NSCLC.240.NGS cohort) containing genomic and clinical data from 240 patients with advanced NSCLC and two cohorts (the OAK and POPLAR study cohort) containing genomic and clinical data from 429 patients with advanced NSCLC were used to analyze the prognostic effect of PALB2 on immunotherapy.ResultsGenetic mutation of 5,227 NSCLC patients were analyzed using NGS, of which 162 (3.1%) harbored germline PALB2 mutation (PALB2gmut) and 87 (1.66%) harbored somatic PALB2 mutation (PALB2smut). In NSCLC patients with PALB2gmut and PALB2smut, the most frequently mutated gene was TP53 (65%, 64%). PALB2smut (14.52 Muts/Mb) was associated with higher TMB (p &lt; 0.001) than PALB wild-type (PALB2wt) (6.15 Muts/Mb). However, there was no significant difference in TMB between PALB2gmut (6.45 Muts/Mb) and PALB2wt (6.15 Muts/Mb) (p = 0.64). There was no difference in PD-L1 expression among PALB2gmut, PALB2smut, and PALB2wt. In the Rizvi2018.NSCLC.240.NGS cohort, there was no difference in progression-free survival (PFS) (HR =1.06, p = 0.93) between PALB2 mutation (3.15 months) and PALB2wt (3.17 months). The OAK and POPLAR study cohort of NSCLC patients showed that there was no difference in overall survival (OS) (HR =1.1, p = 0.75) between PALB2 mutation (10.38 months) and PALB2wt (11.07 months).ConclusionsThese findings suggest that PALB2 may not be used as a biomarker for determining prognosis on immunotherapy in NSCLC.

Integrating gene expression and clinical data to identify drug repurposing candidates for hyperlipidemia and hypertension

Discovering novel uses for existing drugs, through drug repurposing, can reduce the time, costs, and risk of failure associated with new drug development. However, prioritizing drug repurposing candidates for downstream studies remains challenging. Here, we present a high-throughput approach to identify and validate drug repurposing candidates. This approach integrates human gene expression, drug perturbation, and clinical data from publicly available resources. We apply this approach to find drug repurposing candidates for two diseases, hyperlipidemia and hypertension. We screen >21,000 compounds and replicate ten approved drugs. We also identify 25 (seven for hyperlipidemia, eighteen for hypertension) drugs approved for other indications with therapeutic effects on clinically relevant biomarkers. For five of these drugs, the therapeutic effects are replicated in the All of Us Research Program database. We anticipate our approach will enable researchers to integrate multiple publicly available datasets to identify high priority drug repurposing opportunities for human diseases.

The effect of Q.Clear reconstruction on quantification and spatial resolution of 18F-FDG PET in simultaneous PET/MR

Background Q.Clear is a block sequential regularized expectation maximization penalized-likelihood reconstruction algorithm for Positron Emission Tomography (PET). It has shown high potential in improving image reconstruction quality and quantification accuracy in PET/CT system. However, the evaluation of Q.Clear in PET/MR system, especially for clinical applications, is still rare. This study aimed to evaluate the impact of Q.Clear on the 18F-fluorodeoxyglucose (FDG) PET/MR system and to determine the optimal penalization factor β for clinical use. Methods A PET National Electrical Manufacturers Association/ International Electrotechnical Commission (NEMA/IEC) phantom was scanned on GE SIGNA PET/MR, based on NEMA NU 2-2012 standard. Metrics including contrast recovery (CR), background variability (BV), signal-to-noise ratio (SNR) and spatial resolution were evaluated for phantom data. For clinical data, lesion SNR, signal to background ratio (SBR), noise level and visual scores were evaluated. PET images reconstructed from OSEM + TOF and Q.Clear were visually compared and statistically analyzed, where OSEM + TOF adopted point spread function as default procedure, and Q.Clear used different β values of 100, 200, 300, 400, 500, 800, 1100 and 1400. Results For phantom data, as β value increased, CR and BV of all sizes of spheres decreased in general; images reconstructed from Q.Clear reached the peak SNR with β value of 400 and generally had better resolution than those from OSEM + TOF. For clinical data, compared with OSEM + TOF, Q.Clear with β value of 400 achieved 138% increment in median SNR (from 58.8 to 166.0), 59% increment in median SBR (from 4.2 to 6.8) and 38% decrement in median noise level (from 0.14 to 0.09). Based on visual assessment from two physicians, Q.Clear with β values ranging from 200 to 400 consistently achieved higher scores than OSEM + TOF, where β value of 400 was considered optimal. Conclusions The present study indicated that, on 18F-FDG PET/MR, Q.Clear reconstruction improved the image quality compared to OSEM + TOF. β value of 400 was optimal for Q.Clear reconstruction.