Financial fraud, considered as deceptive tactics for gaining financial benefits, has recently become a widespread menace in companies and organizations. Conventional techniques such as manual verifications and inspections are imprecise, costly, and time consuming for identifying such fraudulent activities. With the advent of artificial intelligence, machine-learning-based approaches can be used intelligently to detect fraudulent transactions by analyzing a large number of financial data. Therefore, this paper attempts to present a systematic literature review (SLR) that systematically reviews and synthesizes the existing literature on machine learning (ML)-based fraud detection. Particularly, the review employed the Kitchenham approach, which uses well-defined protocols to extract and synthesize the relevant articles; it then report the obtained results. Based on the specified search strategies from popular electronic database libraries, several studies have been gathered. After inclusion/exclusion criteria, 93 articles were chosen, synthesized, and analyzed. The review summarizes popular ML techniques used for fraud detection, the most popular fraud type, and evaluation metrics. The reviewed articles showed that support vector machine (SVM) and artificial neural network (ANN) are popular ML algorithms used for fraud detection, and credit card fraud is the most popular fraud type addressed using ML techniques. The paper finally presents main issues, gaps, and limitations in financial fraud detection areas and suggests possible areas for future research.

Artificial intelligence has revolutionized medical diagnosis, particularly for cancers. Acute myeloid leukemia (AML) diagnosis is a tedious protocol that is prone to human and machine errors. In several instances, it is difficult to make an accurate final decision even after careful examination by an experienced pathologist. However, computer-aided diagnosis (CAD) can help reduce the errors and time associated with AML diagnosis. White Blood Cells (WBC) detection is a critical step in AML diagnosis, and deep learning is considered a state-of-the-art approach for WBC detection. However, the accuracy of WBC detection is strongly associated with the quality of the extracted features used in training the pixel-wise classification models. CAD depends on studying the different patterns of changes associated with WBC counts and features. In this study, a new hybrid feature extraction method was developed using image processing and deep learning methods. The proposed method consists of two steps: 1) a region of interest (ROI) is extracted using the CMYK-moment localization method and 2) deep learning-based features are extracted using a CNN-based feature fusion method. Several classification algorithms are used to evaluate the significance of the extracted features. The proposed feature extraction method was evaluated using an external dataset and benchmarked against other feature extraction methods. The proposed method achieved excellent performance, generalization, and stability using all the classifiers, with overall classification accuracies of 97.57% and 96.41% using the primary and secondary datasets, respectively. This method has opened a new alternative to improve the detection of WBCs, which could lead to a better diagnosis of AML.

Background: Locally advanced nasopharyngeal carcinoma (LA-NPC) is a relatively rare disease in the west but more common in East Asia and areas of the Middle East like Saudi Arabia. Despite the advances in radiation therapy techniques, some patients relapse after treatment. In the coming era of cancer immunotherapy, prognostic factors for LA-NPC need to be further defined using immune-relevant markers. Several markers are available; however, the most robust and accessible/affordable marker is not well-defined. Methods: Retrospectively, tumor-infiltrating lymphocytes (TIL), their subsets as well as tumoral PD-L1 expression were analyzed in tumor tissues from 63 LA-NPC patients treated with platinum-based concurrent chemo-radiotherapy (CCRT) in addition to 20 cases with metastatic (MET) disease. Immunostaining was done using a validated and fully automated system. Scoring was done by two independent pathologists and results were compared. Results: There was no statistical difference between LA-NPC and MET disease in terms of CD3+, CD8+ TIL infiltration, or tumoral PD-L1 expression. In LA-NPC, low CD3+ TIL infiltration highly correlated with shorter disease-free survival (DFS, HR = 8.5, p = < 0.001) and overall survival (OS, HR = 13, p = 0.015) with substantial agreement between scoring pathologists. A similar correlation was found between low CD8+ TIL and survival. Correlation of total TIL was significant with DFS (HR = 4.0, p = 0.008), borderline with OS and the correlation was dependent on the scoring pathologist. Having histological WHO type I&II correlated significantly with shorter DFS (HR 4.03, p = 0.008) and low CD3+ TIL (p = 0.009). Subgroup analysis of LA-NPC that included undifferentiated type (WHO type III) cases only (n = 58), showed a strong correlation between low CD3+ TIL and shorter DFS (HR = 7.2, p = < 0.001) and OS (HR = 17.3, p = 0.008). PD-L1 was expressed in 72% of type III LA-NPC cases while lacking PD-L1 expression correlated with shorter OS (HR = 6.1, p = 0.031). Patients with a combination of low CD3+ TIL and lack of PD-L1 expression had the worst OS (p < 0.001). Conclusions: CD3+ TIL is promising as a robust and independent prognostic marker for DFS and OS of LA-NPC patients treated with platinum-based CCRT. We would suggest the use of CD3 + TIL as a stratifying factor for LA-NPC, which warrants further validation in prospective trials.

Glucocorticoids have been the primary treatment of graft-versus-host disease (GVHD) over the past decade. Complete responses to steroid therapy are usually expected in almost one-third of aGVHD cases and partial response is anticipated in another one-third of patients. However, for those patients not responding to corticosteroid treatment, there is no standard second-line therapy for acute or chronic GVHD. Methotrexate (MTX) for treatment of steroid refractory GVHD has been evaluated in a number of studies. Results from peer-reviewed original articles were identified and the pooled data analyzed. Despite several limitations in data collection and analysis, weekly administration of methotrexate at a median dose of 7.5 mg/m²seems to be safe with minimal toxicities in the context of both aGVHD and cGVHD treatments. The observed overall response (OR) in patients with aGVHD to MTX treatment in the published studies was 69.9%, with complete response (CR) in 59.2% and PR in 10.6%. In cGVHD the OR was 77.6%, with CR reported in 49.6% and PR in 28% of patients. Predictors of better responses were lower grade GVHD, cutaneous involvement, and isolated organ involvement. MTX as a steroid sparing agent might reduce long-term complications and improve the quality of life of GVHD affected individuals.

Incidence of malignant ovarian germ cell tumors (MOGCTs) in the Saudi Arabian population has not been studied before. Therefore, the primary objective of this study was to define the population-based incidence rates and histopathological types of MOGCTs in the Saudi Arabian population from 1999 to 2008. Our study showed that MOGCTs are a common type of ovarian tumors in the Saudi Arabian population, and the incidence rates and histopathological types are relatively comparable to the international populations with few differences.

Objectives: Ovarian granulosa cell tumour is rare. This study aims to report the clinical characteristics and long-term outcomes of adult-type ovarian granulosa cell tumour (AOGCT) at King Faisal Specialist Hospital and Research Centre (KFSH&RC) and to determine the prognostic factors affecting relapse and survival. Methods: We retrospectively reviewed patients with AOGCT, from 1988 to 2014, who were treated at our institution. Baseline characteristics, pathological findings, and outcomes were analysed and reported. Results: Sixty-one patients with AOGCT were identified with a median age of 49 years. Median follow-up was 5.0 years (range 2.1-8.2 years). 74% of patients were FIGO (International Federation of Gynecology and Obstetrics) stage I, whereas 7% were stage II, 5% were stage III, and unknown in 14% of the cases. The most common presenting symptoms included abdominal pain (43%) and vaginal bleeding (43%). The majority of patients (38 patients, 62%) were treated with total abdominal hysterectomy and bilateral salpingo-oophorectomy. Five (8%) patients received adjuvant chemotherapy. Sixteen patients (26%) relapsed with a median time to relapse of 5.5 years (0.7-8.1 years). Half of the recurrences (eight patients, 50%) occurred after five years of diagnosis. Five-year overall survival and disease-free survival (DFS) were 93% and 84%, respectively. Factors associated with a high risk of recurrence were the presence of ascites (p=0.000) and elevated preoperative CA 125 level (p=0.048). The overall survival was significantly influenced by the menopausal status (premenopausal 100% vs. postmenopausal 84%; p=0.02), preoperative CA 125 (normal 100% vs. elevated 64%; p=0.005), ascites (present 33% vs. absent 100%; p=0.000), and age (<55 years 100% vs. ≥ 55 years 77%; p= 0.002). Conclusion: This study confirms a good outcome for patients with AOGCT. They require long-term follow-up as late recurrences can occur many years post definitive therapy. The presence of ascites and elevated preoperative CA 125 levels were associated with a higher risk of recurrence and poor prognosis. Outcomes appear unaffected by fertility-sparing surgery or adjuvant chemotherapy.