METHODS: A search of four databases was conducted: Web of Science, PubMed, Dimensions, and Scopus for research papers dated between January 2016 and September 2021. The search keywords are 'data mining', 'machine learning' in combination with 'suicidal behaviour', 'suicide', 'suicide attempt', 'suicidal ideation', 'suicide plan' and 'self-harm'. The studies that used machine learning techniques were synthesized according to the countries of the articles, sample description, sample size, classification tasks, number of features used to develop the models, types of machine learning techniques, and evaluation of performance metrics.

RESULTS: Thirty-five empirical articles met the criteria to be included in the current review. We provide a general overview of machine learning techniques, examine the feature categories, describe methodological challenges, and suggest areas for improvement and research directions. Ensemble prediction models have been shown to be more accurate and useful than single prediction models.

OBJECTIVE: This study examines the potential role of FO in suppressing LPS-induced neuroinflammation and cognitive impairment in diabetic animals (DA).

MATERIALS AND METHODS: Thirty male Wistar rats were divided into 5 groups: i) DA received LPS induction (DA-LPS); ii) DA received LPS induction and 1 g/kg FO (DA-LPS-1FO); iii) DA received LPS induction and 3 g/kg FO (DA-LPS-3FO); iv) animals received normal saline and 3 g/kg FO (NS-3FO) and v) control animals received normal saline (CTRL). Y-maze test was used to measure cognitive performance, while brain samples were collected for inflammatory markers and morphological analysis.

RESULTS: DA received LPS induction, and 1 or 3 g/kg FO significantly inhibited hyperglycaemia and brain inflammation, as evidenced by lowered levels of pro-inflammatory mediators. Additionally, both DA-LPS-1FO and DA-LPS-3FO groups exhibited a notable reduction in neuronal damage and glial cell migration compared to the other groups. These results were correlated with the increasing number of entries and time spent in the novel arm of the Y-maze test.

METHODS: This cross-sectional study included 172 subjects with suspected or unknown COVID-19 status brought in dead to the institute's mortuary during the pandemic in Malaysia. PMCT images reported by forensic radiologists and their agreement with conventional autopsy findings by forensic pathologists regarding COD were analysed to look at the effectiveness of PMCT in determining COD during a pandemic.

RESULTS: Analysis showed that 78.7% (133) of cases reported by forensic radiologists concurred with the COD certified by forensic pathologists. Of these cases, 85 (63.9%) had undergone only external examination and real-time reverse transcriptase polymerase chain reaction (rRT-PCR) COVID-19 testing, meaning that imaging was the sole method used to determine the COD besides history from available medical records and the investigating police officer.

METHODS: CJ57BL/6 breeder F0 mice were fed with EBN (10 mg/kg) from different sources. After 6 weeks of diet supplementations, the F0 animals were bred to produce F1 and F2 animals. At 6 weeks of age, the F1 and F2 animals were tested for spatial recognition memory using a Y-maze test. The sialic acid content from EBN and brain gene expression were analyzed using HPLC and PCR, respectively.

RESULTS: All EBN samples contained glycoprotein with high level of sialic acid. Dietary EBN supplementation also showed an upregulation of GNE, ST8SiaIV, SLC17A5, and BDNF mRNA associated with an improvement in Y-maze cognitive performance in both generations of animal. Qualitatively, the densities of synaptic vesicles in the presynaptic terminal were higher in the F1 and F2 animals which might derive from maternal EBN supplementation.