The innovation of AI-based software in oral diseases: clinical-histopathological correlation diagnostic accuracy primary study.

BACKGROUND: Machine learning (ML) through artificial intelligence (AI) could provide clinicians and oral pathologists to advance diagnostic problems in the field of potentially malignant lesions, oral cancer, periodontal diseases, salivary gland disease, oral infections, immune-mediated disease, and others. AI can detect micro-features beyond human eyes and provide solution in critical diagnostic cases. OBJECTIVE: The objective of this study was developing a software with all needed feeding data to act as AI-based program to diagnose oral diseases. So our research question was: Can we develop a Computer-Aided Software for accurate diagnosis of oral diseases based on clinical and histopathological data inputs? METHOD: The study sample included clinical images, patient symptoms, radiographic images, histopathological images and texts for the oral diseases of interest in the current study (premalignant lesions, oral cancer, salivary gland neoplasms, immune mediated oral mucosal lesions, oral reactive lesions) total oral diseases enrolled in this study was 28 diseases retrieved from the archives of oral maxillofacial pathology department. Total 11,200 texts and 3000 images (2800 images were used for training data to the program and 100 images were used as test data to the program and 100 cases for calculating accuracy, sensitivity& specificity). RESULTS: The correct diagnosis rates for group 1 (software users), group 2 (microscopic users) and group 3 (hybrid) were 87%, 90.6, 95% respectively. The reliability for inter-observer value was done by calculating Cronbach's alpha and interclass correlation coefficient. The test revealed for group 1, 2 and 3 the following values respectively 0.934, 0.712 & 0.703. All groups showed acceptable reliability especially for Diagnosis Oral Diseases Software (DODS) that revealed higher reliability value than other groups. However, The accuracy, sensitivity & specificity of this software was lower than those of oral pathologists (master's degree). CONCLUSION: The correct diagnosis rate of DODS was comparable to oral pathologists using standard microscopic examination. The DODS program could be utilized as diagnostic guidance tool with high reliability & accuracy.

Feasibility of Using Convalescent Plasma Immunotherapy for MERS-CoV Infection, Saudi Arabia.

We explored the feasibility of collecting convalescent plasma for passive immunotherapy of Middle East respiratory syndrome coronavirus (MERS-CoV) infection by using ELISA to screen serum samples from 443 potential plasma donors: 196 patients with suspected or laboratory-confirmed MERS-CoV infection, 230 healthcare workers, and 17 household contacts exposed to MERS-CoV. ELISA-reactive samples were further tested by indirect fluorescent antibody and microneutralization assays. Of the 443 tested samples, 12 (2.7%) had a reactive ELISA result, and 9 of the 12 had reactive indirect fluorescent antibody and microneutralization assay titers. Undertaking clinical trials of convalescent plasma for passive immunotherapy of MERS-CoV infection may be feasible, but such trials would be challenging because of the small pool of potential donors with sufficiently high antibody titers. Alternative strategies to identify convalescent plasma donors with adequate antibody titers should be explored, including the sampling of serum from patients with more severe disease and sampling at earlier points during illness.

Feasibility, safety, clinical, and laboratory effects of convalescent plasma therapy for patients with Middle East respiratory syndrome coronavirus infection: a study protocol.

As of September 30, 2015, a total of 1589 laboratory-confirmed cases of infection with the Middle East respiratory syndrome coronavirus (MERS-CoV) have been reported to the World Health Organization (WHO). At present there is no effective specific therapy against MERS-CoV. The use of convalescent plasma (CP) has been suggested as a potential therapy based on existing evidence from other viral infections. We aim to study the feasibility of CP therapy as well as its safety and clinical and laboratory effects in critically ill patients with MERS-CoV infection. We will also examine the pharmacokinetics of the MERS-CoV antibody response and viral load over the course of MERS-CoV infection. This study will inform a future randomized controlled trial that will examine the efficacy of CP therapy for MERS-CoV infection. In the CP collection phase, potential donors will be tested by the enzyme linked immunosorbent assay (ELISA) and the indirect fluorescent antibody (IFA) techniques for the presence of anti-MERS-CoV antibodies. Subjects with anti-MERS-CoV IFA titer of ≥1:160 and no clinical or laboratory evidence of MERS-CoV infection will be screened for eligibility for plasma donation according to standard donation criteria. In the CP therapy phase, 20 consecutive critically ill patients admitted to intensive care unit with laboratory-confirmed MERS-CoV infection will be enrolled and each will receive 2 units of CP. Post enrollment, patients will be followed for clinical and laboratory outcomes that include anti-MERS-CoV antibodies and viral load. This protocol was developed collaboratively by King Abdullah International Medical Research Center (KAIMRC), Gulf Cooperation Council (GCC) Infection Control Center Group and the World Health Organization-International Severe Acute Respiratory and Emerging Infection Consortium (ISARIC-WHO) MERS-CoV Working Group. It was approved in June 2014 by the Ministry of the National Guard Health Affairs Institutional Review Board (IRB). A data safety monitoring board (DSMB) was formulated. The study is registered at http://www.clinicaltrials.gov (NCT02190799).

Extremely elevated erythrocyte sedimentation rate: etiology at a tertiary care center in Saudi Arabia.

OBJECTIVE: To evaluate the etiology of extremely elevated erythrocyte sedimentation rate (ESR) in adolescents and adults at a tertiary care center. METHODS: This retrospective, cross-sectional, observational study was carried out at King Abdulaziz Medical City, Riyadh, Saudi Arabia using the Westergren method of determining ESR in adolescents and adults aged >or=12 years. The patients included inpatients and outpatients with medical, surgical, and gynecological problems. During a period from June 2007 to October 2008, consecutive, non-repetitive patients with ESR >or=100 mm/hour were evaluated for possible etiology by checking the electronic and paper data file of each patient. RESULTS: During the study period, out of the 44,366 ESR tests carried out at this center, 1864 (4.2%) had an ESR >or=100 mm/hour belonging to 567 patients. Out of 508 patients fulfilling the study criteria, the main associated causes included: infections (38.6%), autoimmune diseases (15.9%), malignancy (15.4%), miscellaneous causes (10.2%), ischemic tissue injury or trauma (8.7%), and renal diseases (8.4%). Ten common individual causes included: rheumatoid arthritis (7.3%), osteomyelitis (6.9%), tuberculosis (5.5%), trauma (5.3%), lymphoma and sepsis of unknown origin (5.1%) each, urinary tract infection (4.7%), septic arthritis (3.1%), abscesses (2.8%), and pregnancy (2.2%). Fourteen (2.4%) patients had no known cause. CONCLUSION: Most of the patients with extreme ESR elevation have an underlying cause and a focused evaluation of such patients needs to be carried out to reach a diagnosis.

Erythrocyte membrane proteins in healthy Saudis and patients with hereditary spherocytosis and hereditary elliptocytosis.

BACKGROUND: Little is known about hereditary spherocytosis (HS) and hereditary elliptocytosis (HE) in the native population of Saudi Arabia, even though these conditions are seemingly common. The purpose of this study was to ascertain the protein make-up of the red cell membrane in healthy Saudis and in patients with HS and HE. PATIENTS AND METHODS: Eighteen healthy Saudi subjects (13 males and 5 females), 11 patients with HS (6 males and 5 females) and 11 patients with HE (7 males and 4 females) were studied. All normal controls and patients underwent SDS-PAGE red cell membrane protein analysis in duplicate and the stained protein bands were identified and quantitated by densitometry. RESULTS: In normal, healthy Saudis, the mean values for seven membrane proteins ( I+/- spectrin, I(2) spectrin, ankyrin, band 3, protein 4.1, protein 4.2, and actin) were similar to those published for normal, healthy Americans. Of the eleven cases with HS, 7 (64%) demonstrated detectable protein abnormalities while 4 (36%) were apparently normal. The electrophoretic patterns of membrane proteins in Saudis with HS differed from those of patients with HS in other parts of the world. Of the 11 cases of HE, 7 (64%) displayed abnormalities while 4 (36%) were normal. CONCLUSION: The electrophoretic pattern of the main proteins in the membranes of red blood cells in healthy Saudis is similar to that reported from the USA. However, significant differences exist in the electrophoretic patterns between Saudi patients with HS and patients from other parts of the world.

Immunophenotyping of peripheral blood lymphocytes in Saudi men.

Flow cytometry is an important tool for the diagnosis and follow-up of immunodeficiency patients, as well as for patients with leukemia and lymphoma. Lymphocytes and their subsets show variations with race. The aim of this study was to establish reference ranges for lymphocytes and their subsets in an Saudi adult population by using flow cytometry. Blood samples obtained from 209 healthy Saudi men were used for this study. All blood donors were between 18 and 44 years old. Lymphocytes and their subsets were analyzed by flow cytometry, and the absolute and percentage values were calculated. We investigated the expression of T-cell markers (CD3, CD4, and CD8), B cells (CD19), and natural killer cells (CD16 and CD56). The absolute and percent values of each cell subset were compared with published data from different populations by using the Student t test. Reference ranges, each expressed as the mean +/- the standard deviation, were as follows: leukocytes (6,335 +/- 1759), total lymphocytes (2,224 +/- 717), CD3 cells (1,618 +/- 547), CD4 cells (869 +/- 310), CD8 cells (615 +/- 278), CD19 cells (230 +/- 130), and CD3-CD16(+)/CD56+ cells (262 +/- 178). The CD4/CD8 ratio was 1.6 +/- 0.7. Our results for B cells, CD4 cells, and CD8 cells and for the CD4/CD8 ratio fell in between the reported results for Ethiopian and Dutch subjects. Our results were also different from previously reported findings in an Saudi adult population that showed no increase in CD8 T cells. We thus establish here the reference ranges for lymphocytes and their subsets in a large cohort of Saudi men. The CD8 cell count was not abnormally high, as previously reported, and fell in between previous results obtained for African and European populations.