The correlation between blood lipids and intrahepatic cholestasis syndrome during pregnancy.

BACKGROUND: To analyse changes in lipid levels during the development of intrahepatic cholestasis of pregnancy (ICP) and identify new biomarkers for predicting ICP. METHODS: A retrospective case-control study was conducted to analyse 473 pregnant women who underwent regular prenatal examinations and delivered at the Women and Children's Hospital, School of Medicine, Xiamen University, between June 2020 and June 2023, including 269 normal pregnancy controls and 204 pregnant women with cholestasis. RESULTS: Patients with ICP with gestational diabetes mellitus (GDM) have lower high-density lipoprotein (HDL) levels than in those without GDM. Total bile acid (TBA) levels were significantly higher in pregnant women with GDM than those without. The apolipoprotein A (APOA) level was lower in patients with ICP and hypothyroidism than those without hypothyroidism. TBA levels were significantly higher in pregnant women with hypothyroidism than those without. Triglyceride (TG) levels were significantly higher in patients with preeclampsia (PE) than those without. HDL and APOA levels were lower in women with ICP complicated by preterm delivery than those with normal delivery. The AUC (area under the curve) of the differential diagnosis of cholestasis of pregnancy for the APOA/APOB (apolipoprotein B) ratio was 0.727, with a sensitivity of 85.9% and specificity of 47.5%. CONCLUSIONS: The results suggested that dyslipidaemia is associated with an increased risk of ICP and its complications. The timely detection of blood lipid and bile acid levels can assist in the diagnosis of ICP and effectively prevent ICP and other complications.

Intrahepatic cholestasis of pregnancy (ICP) is recognized as one of the most severe complications during pregnancy. Currently, elevated fasting serum total bile acid (TBA) levels are commonly used as diagnostic markers for ICP. However, it has been observed that women diagnosed with ICP often do not exhibit elevated TBA levels. Additionally, other medical conditions can also lead to increased TBA levels. Our study has revealed a potential correlation between abnormal lipid metabolism and the occurrence and progression of ICP and its associated complications. Specifically, we found that patients with ICP who have higher serum bile acid levels tend to have more disrupted lipid metabolism, as well as a higher risk of complications and adverse pregnancy outcomes. This manuscript is the first to investigate the link between dyslipidemia and ICP, as well as other pregnancy complications. As a result, our findings offer a foundation for the clinical diagnosis and treatment of ICP and its comorbidities during pregnancy, while also highlighting the need for further research in this area.

CircORC2 promoted proliferation and inhibited the sensitivity of osteosarcoma cell lines to cisplatin by regulating the miR-485-3p/TRIM2 axis.

Resistance to chemotherapy leads to poor prognosis for osteosarcoma (OS) patients. However, due to the high metastasis of tumor and the decrease in sensitivity of tumor cells to cisplatin (DDP), the 5-year survival rate of OS patients is still unsatisfactory. This study explored a mechanism for improving the sensitivity of OS cells to DDP. A DDP-resistant OS cell model was established, and we have found that circORC2 and TRIM2 were upregulated in DDP-resistant OS cells, but miR-485-3p was downregulated. The cell viability and proliferation of the OS cells decreased gradually with the increase of DDP dose, but a gradual increase in apoptosis was noted. CircORC2 promoted OS cell proliferation and DDP resistance and upregulated TRIM2 expression by targeting miR-485-3p. Functionally, circORC2 downregulated miR-485-3p to promote OS cell proliferation and inhibit DDP sensitivity. Additionally, it promoted cell proliferation and inhibited the sensitivity of DDP by regulating the miR-485-3p/TRIM2 axis. In conclusion, circORC2 promoted cell proliferation and inhibited the DDP sensitivity in OS cells via the miR-485-3p/TRIM2 axis. These findings indicated the role of circORC2 in regulating the sensitivity of OS cells to DDP.

Genome-wide identification of GH28 family and insight into its contributions to pod shattering resistance in Brassica napus L.

Rapeseed (Brassica napus L.), accounts for nearly 16% of vegetable oil, is the world's second produced oilseed. However, pod shattering has caused significant yield loses in rapeseed production, particularly during mechanical harvesting. The GH28 genes can promote pod shattering by changing the structure of the pod cell wall in Arabidopsis. However, the role of the GH28 gene family in rapeseed was largely unknown. Therefore, a genome-wide comprehensive analysis was conducted to classify the role of GH28 gene family on rapeseed pod shattering. A total of 37 BnaGH28 genes in the rapeseed genome were identified. These BnaGH28s can be divided into five groups (Group A-E), based on phylogenetic and synteny analysis. Protein property, gene structure, conserved motif, cis-acting element, and gene expression profile of BnaGH28 genes in the same group were similar. Specially, the expression level of genes in group A-D was gradually decreased, but increased in group E with the development of silique. Among eleven higher expressed genes in group E, two BnaGH28 genes (BnaA07T0199500ZS and BnaC06T0206500ZS) were significantly regulated by IAA or GA treatment. And the significant effects of BnaA07T0199500ZS variation on pod shattering resistance were also demonstrated in present study. These results could open a new window for insight into the role of BnaGH28 genes on pod shattering resistance in rapeseed.

Artificial intelligence in wound care: diagnosis, assessment and treatment of hard-to-heal wounds: a narrative review.

OBJECTIVE: The effective assessment of wounds, both acute and hard-to-heal, is an important component in the delivery by wound care practitioners of efficacious wound care for patients. Improved wound diagnosis, optimising wound treatment regimens, and enhanced prevention of wounds aid in providing patients with a better quality of life (QoL). There is significant potential for the use of artificial intelligence (AI) in health-related areas such as wound care. However, AI-based systems remain to be developed to a point where they can be used clinically to deliver high-quality wound care. We have carried out a narrative review of the development and use of AI in the diagnosis, assessment and treatment of hard-to-heal wounds. We retrieved 145 articles from several online databases and other online resources, and 81 of them were included in this narrative review. Our review shows that AI application in wound care offers benefits in the assessment/diagnosis, monitoring and treatment of acute and hard-to-heal wounds. As well as offering patients the potential of improved QoL, AI may also enable better use of healthcare resources.

Scalable Swin Transformer network for brain tumor segmentation from incomplete MRI modalities.

BACKGROUND: Deep learning methods have shown great potential in processing multi-modal Magnetic Resonance Imaging (MRI) data, enabling improved accuracy in brain tumor segmentation. However, the performance of these methods can suffer when dealing with incomplete modalities, which is a common issue in clinical practice. Existing solutions, such as missing modality synthesis, knowledge distillation, and architecture-based methods, suffer from drawbacks such as long training times, high model complexity, and poor scalability. METHOD: This paper proposes IMS2Trans, a novel lightweight scalable Swin Transformer network by utilizing a single encoder to extract latent feature maps from all available modalities. This unified feature extraction process enables efficient information sharing and fusion among the modalities, resulting in efficiency without compromising segmentation performance even in the presence of missing modalities. RESULTS: Two datasets, BraTS 2018 and BraTS 2020, containing incomplete modalities for brain tumor segmentation are evaluated against popular benchmarks. On the BraTS 2018 dataset, our model achieved higher average Dice similarity coefficient (DSC) scores for the whole tumor, tumor core, and enhancing tumor regions (86.57, 75.67, and 58.28, respectively), in comparison with a state-of-the-art model, i.e. mmFormer (86.45, 75.51, and 57.79, respectively). Similarly, on the BraTS 2020 dataset, our model scored higher DSC scores in these three brain tumor regions (87.33, 79.09, and 62.11, respectively) compared to mmFormer (86.17, 78.34, and 60.36, respectively). We also conducted a Wilcoxon test on the experimental results, and the generated p-value confirmed that our model's performance was statistically significant. Moreover, our model exhibits significantly reduced complexity with only 4.47 M parameters, 121.89G FLOPs, and a model size of 77.13 MB, whereas mmFormer comprises 34.96 M parameters, 265.79 G FLOPs, and a model size of 559.74 MB. These indicate our model, being light-weighted with significantly reduced parameters, is still able to achieve better performance than a state-of-the-art model. CONCLUSION: By leveraging a single encoder for processing the available modalities, IMS2Trans offers notable scalability advantages over methods that rely on multiple encoders. This streamlined approach eliminates the need for maintaining separate encoders for each modality, resulting in a lightweight and scalable network architecture. The source code of IMS2Trans and the associated weights are both publicly available at https://github.com/hudscomdz/IMS2Trans.

Genome-wide characterization of SDR gene family and its potential role in seed dormancy of Brassica napus L.

Rapeseed (Brassica napus L.) with short or no dormancy period are easy to germinate before harvest (pre-harvest sprouting, PHS). PHS has seriously decreased seed weight and oil content in B. napus. Short-chain dehydrogenase/ reductase (SDR) genes have been found to related to seed dormancy by promoting ABA biosynthesis in rice and Arabidopsis. In order to clarify whether SDR genes are the key factor of seed dormancy in B. napus, homology sequence blast, protein physicochemical properties, conserved motif, gene structure, cis-acting element, gene expression and variation analysis were conducted in present study. Results shown that 142 BnaSDR genes, unevenly distributed on 19 chromosomes, have been identified in B. napus genome. Among them, four BnaSDR gene clusters present in chromosome A04、A05、C03、C04 were also identified. These 142 BnaSDR genes were divided into four subfamilies on phylogenetic tree. Members of the same subgroup have similar protein characters, conserved motifs, gene structure, cis-acting elements and tissue expression profiles. Specially, the expression levels of genes in subgroup A, B and C were gradually decreased, but increased in subgroup D with the development of seeds. Among seven higher expressed genes in group D, six BnaSDR genes were significantly higher expressed in weak dormancy line than that in nondormancy line. And the significant effects of BnaC01T0313900ZS and BnaC03T0300500ZS variation on seed dormancy were also demonstrated in present study. These findings provide a key information for investigating the function of BnaSDRs on seed dormancy in B. napus.

Ionic Liquid Boosting the Electrochemical Stability of a Poly(1,3-dioxolane) Gel Electrolyte for High-voltage Solid-State Lithium Batteries.

Poor interfacial contact between solid-state electrolytes and electrodes limits high-voltage performance of solid-state lithium batteries. A new gel electrolyte is proposed via in-situ polymerization, incorporating fluoroethylene carbonate (FEC) solvent and ionic liquid1-butyl-1-methylpiperidinium bis(trifluoromethylsulfonyl)imide (PP14 TFSI). This combination synergistically enhances Li ion transport, achieving a transfer number of 0.58 and improved electrochemical performance. FEC protects the Al current collectors from LiPF6 corrosion and promotes a protective interfacial layer formation. PP14 TFSI improves interfacial contact and provides stable components. An interface layer of fluorine and nitrogen composites forms, preventing side reactions. LiCoO2 ||PPE||Li cell exhibits robust cycling stability at 4.45 V, retaining ~80 % capacity after 200 cycles at room temperature with 0.2 C and 1 C rates, showing increased coulombic efficiency. NCM811||PPE||Li cell also displays exceptional cycling. In-situ polymerization and FEC-ionic liquid coordination enable high-voltage solid-state lithium metal batteries for practical use.

Detection Method of Fungal Spores Based on Fingerprint Characteristics of Diffraction-Polarization Images.

The most significant aspect of promoting greenhouse productivity is the timely monitoring of disease spores and applying proactive control measures. This paper introduces a method to classify spores of airborne disease in greenhouse crops by using fingerprint characteristics of diffraction-polarized images and machine learning. Initially, a diffraction-polarization imaging system was established, and the diffraction fingerprint images of disease spores were taken in polarization directions of 0°, 45°, 90° and 135°. Subsequently, the diffraction-polarization images were processed, wherein the fingerprint features of the spore diffraction-polarization images were extracted. Finally, a support vector machine (SVM) classification algorithm was used to classify the disease spores. The study's results indicate that the diffraction-polarization imaging system can capture images of disease spores. Different spores all have their own unique diffraction-polarization fingerprint characteristics. The identification rates of tomato gray mold spores, cucumber downy mold spores and cucumber powdery mildew spores were 96.02%, 94.94% and 96.57%, respectively. The average identification rate of spores was 95.85%. This study can provide a research basis for the identification and classification of disease spores.

Candidate Marker Genes for Diagnosis of Osteoarthritis and Prediction of Their Regulatory Mechanisms.

We have screened candidate marker genes for the diagnosis of osteoarthritis and predicted their regulatory mechanisms. Six expression chips of tissue samples and one expression chip of peripheral blood mononuclear cell (PMBC) samples were obtained from the GEO database. Differential analysis, GSEA, and WGCNA were performed on the integra-ted tissue sample data with batch correction. Can-didate genes were obtained from the intersection of the genes significantly related to osteoarthritis in the WGCNA and the differentially expressed genes. ROC analysis was performed on the candidate genes in the tissue and PMBC samples. Genes with AUC values greater than 0.6 were retained as final candidates, and their upstream regulatory miRNAs were predicted. A total of 106 genes with differential expression were found in osteoarthritis tissue samples, which were mainly enriched in cell cycle and p53 signalling pathways. WGCNA selected a gene module significantly correlated with the occurrence of osteoarthritis. Fourteen candidate genes were obtained from the intersection of the genes in the module and the differentially expressed genes. ROC analysis showed that among these 14 candidate genes, only ADM, CX3CR1 and GADD45A had AUC values greater than 0.6 in both tissue and PMBC samples. The AUC values of the gene set of these three genes were greater than 0.7. Multiple miRNAs were predicted to be regulators of these three genes. ADM, CX3CR1 and GADD45A have potential as diagnostic marker genes for osteoarthritis and may be regulated by multiple miRNAs.

Investigating the mental health of university students during the COVID-19 pandemic in a UK university: a machine learning approach using feature permutation importance.

Mental wellbeing of university students is a growing concern that has been worsening during the COVID-19 pandemic. Numerous studies have gathered empirical data to explore the mental health impact of the pandemic on university students and investigate factors associated with higher levels of distress. While the online questionnaire survey has been a prevalent means to collect data, regression analysis has been observed a dominating approach to interpret and understand the impact of independent factors on a mental wellbeing state of interest. Drawbacks such as sensitivity to outliers, ineffectiveness in case of multiple predictors highly correlated may limit the use of regression in complex scenarios. These observations motivate the underlying research to propose alternative computational methods to investigate the questionnaire data. Inspired by recent machine learning advances, this research aims to construct a framework through feature permutation importance to empower the application of a variety of machine learning algorithms that originate from different computational frameworks and learning theories, including algorithms that cannot directly provide exact numerical contributions of individual factors. This would enable to explore quantitative impact of predictors in influencing student mental wellbeing from multiple perspectives as a result of using different algorithms, thus complementing the single view due to the dominant use of regression. Applying the proposed approach over an online survey in a UK university, the analysis suggests the past medical record and wellbeing history and the experience of adversity contribute significantly to mental wellbeing states; and the frequent communication with families and friends to keep good relationship as well as regular exercise are generally contributing to improved mental wellbeing.

Paeonol accelerates skin wound healing by regulating macrophage polarization and inflammation in diabetic rats.

Diabetic ulcer is usually seen in people with uncontrolled blood sugar. Reportedly, many factors such as impaired glucose metabolism, and macrovascular and microvascular diseases caused angiogenesis disorders and delayed the healing of diabetic ulcers, thus affecting the body's metabolism, nutrition, and immune function. This study aimed to explore the effect of paeonol on skin wound healing in diabetic rats and the related mechanism. A rat model of diabetic ulcer was established. High glucose-treated mouse skin fibroblasts were co-cultured with M1 or M2-polarized macrophages treated with or without paeonol. H&E and Masson staining were used to reveal inflammatory cell infiltration and collagen deposition, respectively. Immunohistochemistry visualized the expression of Ki67, CD31, and vascular endothelial growth factor (VEGF). Western blot was used to detect interleukin (IL)-1ß, tumor necrosis factor (TNF)-α, IL-4, IL-10, CD31, VEGFA, and collagen I/III. The expression of iNOS and arginase 1 was revealed by immunofluorescence staining. Paeonol treatment augmented collagen deposition and the expression of Ki67, CD31, VEGF, and macrophage M2 polarization markers (IL-4 and IL-10) and reduced wound area, inflammatory cell infiltration, and macrophage M1 polarization markers (IL-1ß and TNF-α) in the ulcerated area. In vitro, paeonol treatment promoted M2-polarization and repressed M1-polarization in macrophages, thereby improving the repair of cell damage induced by high glucose. Paeonol accelerates the healing of diabetic ulcers by promoting M2 macrophage polarization and inhibiting M1 macrophage polarization.

Identification and Expression Analysis of DFR Gene Family in Brassica napus L.

Dihydroflavonol 4-reductase (DFR) is a key enzyme in the flavonoid biosynthetic pathway and is essential for the formation of plants' color. In this study, 26 BnDFR genes were identified using 6 Arabidopsis DFR genes as reference. The physicochemical properties, subcellular localization, and conserved structure of BnDFR proteins were analyzed; the evolutionary relationship, collinearity analysis, and expression characteristics of BnDFR genes were studied; and the correlation between the expression level of BnDFR genes and anthocyanin content in rape petals were analyzed. The results showed that the 26 BnDFRs were located in chloroplasts, cytoplasm, nuclei, and mitochondria, distributed on 17 chromosomes, and divided into 4 groups; members of the same group have a similar function, which may be related to the environmental response elements and plant hormone response elements. Intraspecific collinearity analysis showed 51 pairs of collinear genes, and interspecific collinearity analysis showed 30 pairs of collinear genes. Analysis of the expression levels of BnDFRs and anthocyanin content in different color rape petals showed that BnDFR6 and BnDFR26 might play an important role in the synthesis of anthocyanins in rape petals. This provides theoretical guidance for further analysis of the anthocyanin anabolism mechanism involved in the DFR gene in Brassica napus.

Diagnosing attention-deficit hyperactivity disorder (ADHD) using artificial intelligence: a clinical study in the UK.

Attention-deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder affecting a large percentage of the adult population. A series of ongoing efforts has led to the development of a hybrid AI algorithm (a combination of a machine learning model and a knowledge-based model) for assisting adult ADHD diagnosis, and its clinical trial currently operating in the largest National Health Service (NHS) for adults with ADHD in the UK. Most recently, more data was made available that has lead to a total collection of 501 anonymized records as of 2022 July. This prompted the ongoing research to carefully examine the model by retraining and optimizing the machine learning algorithm in order to update the model with better generalization capability. Based on the large data collection so far, this paper also pilots a study to examine the effectiveness of variables other than the Diagnostic Interview for ADHD in adults (DIVA) assessment, which adds considerable cost in the screenining process as it relies on specially trained senior clinicians. Results reported in this paper demonstrate that the newly trained machine learning model reaches an accuracy of 75.03% when all features are used; the hybrid model obtains an accuracy of 93.61%. Exceeding what clinical experts expected in the absence of DIVA, achieving an accuracy of 65.27% using a rule-based machine learning model alone encourages the development of a cost effective model in the future.

EGCG Restores Keratinocyte Autophagy to Promote Diabetic Wound Healing through the AMPK/ULK1 Pathway.

BACKGROUND: Delayed wound healing, a common problem in patients with diabetes mellitus (DM), is associated with impaired keratinocyte autophagy. Epigallocatechin gallate (EGCG), a catechin, has been proven to promote diabetic wound healing. This study aims to explore the therapeutic mechanism of EGCG on diabetic wound healing. METHODS: High glucose (HG)-induced keratinocytes and streptozotocin (STZ)-induced DM rats were prepared and intervened with EGCG to examine its therapeutic effects in in vivo and in vitro settings. The AMPK inhibitor, Compound C, was utilized to determine whether EGCG exerted its therapeutic effects through the AMPK/ULK1 pathway. RESULTS: In vitro, EGCG improved HG-induced autophagy impairment in keratinocytes by increasing LC3II/LC3I, Becline1, and ATG5 levels and decreasing p62 level. Mechanically, EGCG activated the AMPK/ULK1 pathway, thereby promoting keratinocyte autophagy through the phosphorylation of AMPK and ULK1. Notably, EGCG promoted the proliferation, migration, synthesis and release of C-C motif chemokine ligand 2 (CCL2) in HG-treated keratinocytes. Furthermore, EGCG indirectly promoted the activation of fibroblasts, as evidenced by increased alpha-smooth muscle actin (α-SMA) and Collagen I levels. In vivo, EGCG promoted wound healing in DM rats, primarily by reducing inflammatory infiltration and increasing granulation tissue to promote wound epithelialization. Besides, EGCG promoted ATG5, KRT10, KRT14, TGF-ß1, Collagen I, and α-SMA expressions in the neonatal epithelial tissues of DM rats. However, the use of Compound C reversed the effects of EGCG. CONCLUSIONS: These findings indicated that EGCG restored keratinocyte autophagy to promote diabetic wound healing through the AMPK/ULK1 pathway.

A dominant set-informed interpretable fuzzy system for automated diagnosis of dementia.

Dementia is an incurable neurodegenerative disease primarily affecting the older population, for which the World Health Organisation has set to promoting early diagnosis and timely management as one of the primary goals for dementia care. While a range of popular machine learning algorithms and their variants have been applied for dementia diagnosis, fuzzy systems, which have been known effective in dealing with uncertainty and offer to explicitly reason how a diagnosis can be inferred, sporadically appear in recent literature. Given the advantages of a fuzzy rule-based model, which could potentially result in a clinical decision support system that offers understandable rules and a transparent inference process to support dementia diagnosis, this paper proposes a novel fuzzy inference system by adapting the concept of dominant sets that arise from the study of graph theory. A peeling-off strategy is used to iteratively extract from the constructed edge-weighted graph a collection of dominant sets. Each dominant set is further converted into a parameterized fuzzy rule, which is finally optimized in a supervised adaptive network-based fuzzy inference framework. An illustrative example is provided that demonstrates the interpretable rules and the transparent reasoning process of reaching a decision. Further systematic experiments conducted on data from the Open Access Series of Imaging Studies (OASIS) repository, also validate its superior performance over alternative methods.

DDIT3 antagonizes innate immune response to promote bovine alphaherpesvirus 1 replication via the DDIT3-SQSTM1-STING pathway.

DNA damage-inducible transcript 3 (DDIT3), a transcription factor, is typically involved in virus replication control. We are the first to report that DDIT3 promotes the replication of bovine viral diarrhea virus, an RNA virus, by inhibiting innate immunity. However, whether the DDIT3 gene participates in DNA virus replication by regulating innate immunity remains unclear. This study reported that DDIT3 suppressed the innate immune response caused by DNA viruses to promote bovine herpesvirus 1 (BoHV-1) replication. After BoHV-1 infection of Madin-Darby bovine kidney (MDBK) cells, upregulated expression of DDIT3 induced SQSTM1-mediated autophagy and promoted STING degradation. Overexpression of the SQSTM1 protein effectively reduced STING protein levels, whereas SQSTM1 knockdown increased STING protein levels. Coimmunoprecipitation experiments and confocal laser scanning microscopy revealed that the SQSTM1 protein interacts with and colocalizes with STING. Knockdown of SQSTM1 expression in DDIT3-overexpressing cell lines restored STING protein levels. Moreover, a dual-luciferase reporter assay revealed that DDIT3 directly binds to the bovine SQSTM1 promoter and induces SQSTM1 transcription. Overexpression of SQSTM1 promoted BoHV-1 replication by inhibiting IFN-ß and IFN-stimulated genes (ISGs) production; silencing of SQSTM1 promoted the expression of IFN-ß and ISGs to inhibit BoHV-1 replication. In conclusion, DDIT3 targets STING via SQSTM1-mediated autophagy to promote BoHV-1 replication. These results suggest a novel mechanism by which DDIT3 regulates DNA virus replication by targeting innate immunity. DDIT3 antagonizes the innate immune response to promote bovine alphaherpesvirus 1 replication via the DDIT3-SQSTM1-STING pathway.

A Predictive Analysis of Heart Rates Using Machine Learning Techniques.

Heart disease, caused by low heart rate, is one of the most significant causes of mortality in the world today. Therefore, it is critical to monitor heart health by identifying the deviation in the heart rate very early, which makes it easier to detect and manage the heart's function irregularities at a very early stage. The fast-growing use of advanced technology such as the Internet of Things (IoT), wearable monitoring systems and artificial intelligence (AI) in the healthcare systems has continued to play a vital role in the analysis of huge amounts of health-based data for early and accurate disease detection and diagnosis for personalized treatment and prognosis evaluation. It is then important to analyze the effectiveness of using data analytics and machine learning to monitor and predict heart rates using wearable device (accelerometer)-generated data. Hence, in this study, we explored a number of powerful data-driven models including the autoregressive integrated moving average (ARIMA) model, linear regression, support vector regression (SVR), k-nearest neighbor (KNN) regressor, decision tree regressor, random forest regressor and long short-term memory (LSTM) recurrent neural network algorithm for the analysis of accelerometer data to make future HR predictions from the accelerometer's univariant HR time-series data from healthy people. The performances of the models were evaluated under different durations. Evaluated on a very recently created data set, our experimental results demonstrate the effectiveness of using an ARIMA model with a walk-forward validation and linear regression for predicting heart rate under all durations and other models for durations longer than 1 min. The results of this study show that employing these data analytics techniques can be used to predict future HR more accurately using accelerometers.

The mental health of university students during the COVID-19 pandemic: An online survey in the UK.

Higher education students' mental health has been a growing concern in recent years even before the COVID-19 pandemic. The stresses and restrictions associated with the pandemic have put university students at greater risk of developing mental health issues, which may significantly impair their academic success, social interactions and their future career and personal opportunities. This paper aimed to understand the mental health status of University students at an early stage in the pandemic and to investigate factors associated with higher levels of distress. An online survey including demographics, lifestyle/living situations, brief mental well-being history, questions relating to COVID-19 and standardised measures of depression, anxiety, resilience and quality of life was completed by 1173 students at one University in the North of England. We found high levels of anxiety and depression, with more than 50% experiencing levels above the clinical cut offs, and females scoring significantly higher than males. The survey also suggested relatively low levels of resilience which we attribute to restrictions and isolation which reduced the opportunities to engage in helpful coping strategies and activities rather than enduring personality characteristics. Higher levels of distress were associated with lower levels of exercising, higher levels of tobacco use, and a number of life events associated with the pandemic and lockdown, such as cancelled events, worsening in personal relationships and financial concerns. We discuss the importance of longer-term monitoring and mental health support for university students.

A Decision Tree-Initialised Neuro-fuzzy Approach for Clinical Decision Support.

Apart from the need for superior accuracy, healthcare applications of intelligent systems also demand the deployment of interpretable machine learning models which allow clinicians to interrogate and validate extracted medical knowledge. Fuzzy rule-based models are generally considered interpretable that are able to reflect the associations between medical conditions and associated symptoms, through the use of linguistic if-then statements. Systems built on top of fuzzy sets are of particular appealing to medical applications since they enable the tolerance of vague and imprecise concepts that are often embedded in medical entities such as symptom description and test results. They facilitate an approximate reasoning framework which mimics human reasoning and supports the linguistic delivery of medical expertise often expressed in statements such as 'weight low' or 'glucose level high' while describing symptoms. This paper proposes an approach by performing data-driven learning of accurate and interpretable fuzzy rule bases for clinical decision support. The approach starts with the generation of a crisp rule base through a decision tree learning mechanism, capable of capturing simple rule structures. The crisp rule base is then transformed into a fuzzy rule base, which forms the input to the framework of adaptive network-based fuzzy inference system (ANFIS), thereby further optimising the parameters of both rule antecedents and consequents. Experimental studies on popular medical data benchmarks demonstrate that the proposed work is able to learn compact rule bases involving simple rule antecedents, with statistically better or comparable performance to those achieved by state-of-the-art fuzzy classifiers.