MicroRNA classification and discovery for major depressive disorder diagnosis: Towards a robust and interpretable machine learning approach.

BACKGROUND: Major depressive disorder (MDD) is notably underdiagnosed and undertreated due to its complex nature and subjective diagnostic methods. Biomarker identification would help provide a clearer understanding of MDD aetiology. Although machine learning (ML) has been implemented in previous studies to study the alteration of microRNA (miRNA) levels in MDD cases, clinical translation has not been feasible due to the lack of interpretability (i.e. too many miRNAs for consideration) and stability. METHODS: This study applied logistic regression (LR) model to the blood miRNA expression profile to differentiate patients with MDD (n = 60) from healthy controls (HCs, n = 60). Embedded (L1-regularised logistic regression) feature selector was utilised to extract clinically relevant miRNAs, and optimized for clinical application. RESULTS: Patients with MDD could be differentiated from HCs with the area under the receiver operating characteristic curve (AUC) of 0.81 on testing data when all available miRNAs were considered (which served as a benchmark). Our LR model selected miRNAs up to 5 (known as LR-5 model) emerged as the best model because it achieved a moderate classification ability (AUC = 0.75), relatively high interpretability (feature number = 5) and stability (ϕ̂Z=0.55) compared to the benchmark. The top-ranking miRNAs identified by our model have demonstrated associations with MDD pathways involving cytokine signalling in the immune system, the reelin signalling pathway, programmed cell death and cellular responses to stress. CONCLUSION: The LR-5 model, which is optimised based on ML design factors, may lead to a robust and clinically usable MDD diagnostic tool.

Using an Interpretable Amino Acid-Based Machine Learning Method to Enhance the Diagnosis of Major Depressive Disorder.

Background: Major depressive disorder (MDD) is a leading cause of disability worldwide. At present, however, there are no established biomarkers that have been validated for diagnosing and treating MDD. This study sought to assess the diagnostic and predictive potential of the differences in serum amino acid concentration levels between MDD patients and healthy controls (HCs), integrating them into interpretable machine learning models. Methods: In total, 70 MDD patients and 70 HCs matched in age, gender, and ethnicity were recruited for the study. Serum amino acid profiling was conducted by means of chromatography-mass spectrometry. A total of 21 metabolites were analysed, with 17 from a preset amino acid panel and the remaining 4 from a preset kynurenine panel. Logistic regression was applied to differentiate MDD patients from HCs. Results: The best-performing model utilised both feature selection and hyperparameter optimisation and yielded a moderate area under the receiver operating curve (AUC) classification value of 0.76 on the testing data. The top five metabolites identified as potential biomarkers for MDD were 3-hydroxy-kynurenine, valine, kynurenine, glutamic acid, and xanthurenic acid. Conclusions: Our study highlights the potential of using an interpretable machine learning analysis model based on amino acids to aid and increase the diagnostic accuracy of MDD in clinical practice.

Systematic Review on Treatment and Outcomes of Tuberculous Peritonitis in Patients on Peritoneal Dialysis.

Introduction: Peritoneal dialysis (PD)-associated peritonitis due to tuberculosis (TB) is associated with poor outcomes and optimal treatment strategies for this condition remain unknown. Our study aimed to: (i) systematically review the published literature on peritonitis caused by Mycobacterium tuberculosis in patients on PD and (ii) review cases of peritonitis due to M tuberculosis in patients on PD reported in Australia and New Zealand to determine the epidemiology, management strategies, and outcomes of this condition. Methods: A literature search of Medline, Scopus, Embase, ClinicalTrials.gov, Cochrane CENTRAL Register of Controlled Trials and Google Scholar for articles published from inception date to June 2022 was conducted. To be eligible, articles had to describe patient characteristics, initial anti-TB therapy, and treatment outcomes in all patients on PD with peritonitis caused by M tuberculosis. Data from the Australia and New Zealand Dialysis and Transplant (ANZDATA) Registry of patients on PD who developed peritonitis due to M tuberculosis between September 2001 and December 2020 were included and analyzed. Results: The systematic literature review identified 70 case studies (151 patients) and 8 cohort studies (97 patients), whereas the ANZDATA Registry identified 17 cases of peritonitis due to M tuberculosis. Overall, in patients diagnosed with peritonitis due to M tuberculosis, the rates of PD catheter removal and permanent transfer to hemodialysis (HD) were numerically higher in the ANZDATA Registry cases (82%) than in the case studies (23%) and cohort studies (20%). Observed all-cause mortality rates were also higher as observed in the case studies (33%) and cohort studies (26%) than in the ANZDATA Registry cases (6%). Conclusion: Tuberculous peritonitis is uncommon in patients on PD and is associated with poor outcomes. Prospective studies are warranted to study the effect of retaining PD catheters after M tuberculosis infection on patient outcomes.

MRI economics: Balancing sample size and scan duration in brain wide association studies.

A pervasive dilemma in neuroimaging is whether to prioritize sample size or scan duration given fixed resources. Here, we systematically investigate this trade-off in the context of brain-wide association studies (BWAS) using resting-state functional magnetic resonance imaging (fMRI). We find that total scan duration (sample size × scan duration per participant) robustly explains individual-level phenotypic prediction accuracy via a logarithmic model, suggesting that sample size and scan duration are broadly interchangeable. The returns of scan duration eventually diminish relative to sample size, which we explain with principled theoretical derivations. When accounting for fixed costs associated with each participant (e.g., recruitment, non-imaging measures), we find that prediction accuracy in small-scale BWAS might benefit from much longer scan durations (>50 min) than typically assumed. Most existing large-scale studies might also have benefited from smaller sample sizes with longer scan durations. Both logarithmic and theoretical models of the relationships among sample size, scan duration and prediction accuracy explain well-predicted phenotypes better than poorly-predicted phenotypes. The logarithmic and theoretical models are also undermined by individual differences in brain states. These results replicate across phenotypic domains (e.g., cognition and mental health) from two large-scale datasets with different algorithms and metrics. Overall, our study emphasizes the importance of scan time, which is ignored in standard power calculations. Standard power calculations inevitably maximize sample size at the expense of scan duration. The resulting prediction accuracies are likely lower than would be produced with alternate designs, thus impeding scientific discovery. Our empirically informed reference is available for future study design: WEB_APPLICATION_LINK.

Febrile Phase Soluble Urokinase Plasminogen Activator Receptor and Olfactomedin 4 as Prognostic Biomarkers for Severe Dengue in Adults.

BACKGROUND: Dengue cases continue to rise and can overwhelm healthcare systems during outbreaks. In dengue, neutrophil mediators, soluble urokinase plasminogen activator receptor (suPAR) and olfactomedin 4, and mast cell mediators, chymase and tryptase, have not been measured longitudinally across the dengue phases. The utility of these proteins as prognostic biomarkers for severe dengue has also not been assessed in an older adult population. METHODS: We prospectively enrolled 99 adults with dengue-40 dengue fever, 46 dengue with warning signs and 13 severe dengue, along with 30 controls. Plasma levels of suPAR, olfactomedin 4, chymase and tryptase were measured at the febrile, critical and recovery phases in dengue patients. RESULTS: The suPAR levels were significantly elevated in severe dengue compared to the other dengue severities and controls in the febrile (P < .001), critical (P < .001), and recovery (P = .005) phases. In the febrile phase, suPAR was a prognostic biomarker of severe dengue, with an AUROC of 0.82. Using a cutoff derived from Youden's index (5.4 ng/mL) and an estimated prevalence of severe dengue (16.5%) in our healthcare institution, the sensitivity was 71.4% with a specificity of 87.9% in the febrile phase, and the positive and negative predictive values were 54.7% and 95.8%, respectively. Olfactomedin 4 was elevated in dengue patients but not in proportion to disease severity in the febrile phase (P = .04) There were no significant differences in chymase and tryptase levels between dengue patients and controls. CONCLUSIONS: In adult dengue, suPAR may be a reliable prognostic biomarker for severe dengue in the febrile phase.

Relationship between prediction accuracy and feature importance reliability: An empirical and theoretical study.

There is significant interest in using neuroimaging data to predict behavior. The predictive models are often interpreted by the computation of feature importance, which quantifies the predictive relevance of an imaging feature. Tian and Zalesky (2021) suggest that feature importance estimates exhibit low split-half reliability, as well as a trade-off between prediction accuracy and feature importance reliability across parcellation resolutions. However, it is unclear whether the trade-off between prediction accuracy and feature importance reliability is universal. Here, we demonstrate that, with a sufficient sample size, feature importance (operationalized as Haufe-transformed weights) can achieve fair to excellent split-half reliability. With a sample size of 2600 participants, Haufe-transformed weights achieve average intra-class correlation coefficients of 0.75, 0.57 and 0.53 for cognitive, personality and mental health measures respectively. Haufe-transformed weights are much more reliable than original regression weights and univariate FC-behavior correlations. Original regression weights are not reliable even with 2600 participants. Intriguingly, feature importance reliability is strongly positively correlated with prediction accuracy across phenotypes. Within a particular behavioral domain, there is no clear relationship between prediction performance and feature importance reliability across regression models. Furthermore, we show mathematically that feature importance reliability is necessary, but not sufficient, for low feature importance error. In the case of linear models, lower feature importance error is mathematically related to lower prediction error. Therefore, higher feature importance reliability might yield lower feature importance error and higher prediction accuracy. Finally, we discuss how our theoretical results relate with the reliability of imaging features and behavioral measures. Overall, the current study provides empirical and theoretical insights into the relationship between prediction accuracy and feature importance reliability.

Arcobacter Butzleri in an AIDS Patient.

Background: Arcobacter butzleri (A. butzleri) is an emerging enteric pathogen increasingly identified in Europe and is likely under-reported in other global regions. We describe to our knowledge the first case report of A. butzleri in an AIDS patient, along with the first documented local (Singapore) case of A. butzleri infection. Case Presentation. A 38-year-old AIDS patient presented with diarrhoea of 2 weeks' duration. Stool cultures yielded A. butzleri. The patient was treated with 3 days of ciprofloxacin with clinical resolution of diarrhoea. Conclusion: A. butzleri is likely to be present, although under-reported in AIDS patients, and it should be noted as a pathogen of increasing significance.

Improving the diagnostic accuracy for major depressive disorder using machine learning algorithms integrating clinical and near-infrared spectroscopy data.

BACKGROUND: Given that major depressive disorder (MDD) is both biologically and clinically heterogeneous, a diagnostic system integrating neurobiological markers and clinical characteristics would allow for better diagnostic accuracy and, consequently, treatment efficacy. OBJECTIVE: Our study aimed to evaluate the discriminative and predictive ability of unimodal, bimodal, and multimodal approaches in a total of seven machine learning (ML) models-clinical, demographic, functional near-infrared spectroscopy (fNIRS), combinations of two unimodal models, as well as a combination of all three-for MDD. METHODS: We recruited 65 adults with MDD and 68 matched healthy controls, who provided both sociodemographic and clinical information, and completed the HAM-D questionnaire. They were also subject to fNIRS measurement when participating in the verbal fluency task. Using the nested cross validation procedure, the classification performance of each ML model was evaluated based on the area under the receiver operating characteristic curve (ROC), balanced accuracy, sensitivity, and specificity. RESULTS: The multimodal ML model was able to distinguish between depressed patients and healthy controls with the highest balanced accuracy of 87.98 ± 8.84% (AUC = 0.92; 95% CI (0.84-0.99) when compared with the uni- and bi-modal models. CONCLUSIONS: Our multimodal ML model demonstrated the highest diagnostic accuracy for MDD. This reinforces the biological and clinical heterogeneity of MDD and highlights the potential of this model to improve MDD diagnosis rates. Furthermore, this model is cost-effective and clinically applicable enough to be established as a robust diagnostic system for MDD based on patients' biosignatures.

Coronavirus Disease 2019 (COVID-19): The Singapore Experience. A Review of the First Eight Months.

As of 27 October 2020, there have been 57,980 confirmed cases of COVID-19 in Singapore, with 28 fatalities. To summarise the Singapore experience in managing and containing COVID-19 based on available published data and from relevant sources, a review of literature using research databases such as PubMed and OVID Medline, along with non-peer-reviewed articles and other sources, was conducted with the search terms 'COVID-19' and 'Singapore'. Research conducted in Singapore has provided insight into the clinical manifestations and period of infectivity of COVID-19, demonstrated evidence of pre-symptomatic transmission, linked infection clusters using serological tools, and highlighted aspects of hospital-based environmental contamination. It has also provided guidance for diagnostic testing and has described immune and virologic correlates with disease severity. Evidence of effectiveness of containment measures such as early border control, rigorous contact training, and calibrated social distancing measures have also been demonstrated. Singapore's multipronged strategy has been largely successful at containing COVID-19 and minimising fatalities, but the risk of re-emergence is high.

Novel use of a balloon dilatation catheter to enable mechanical lithotripsy of difficult common bile duct stones after initial failed attempt: A case report.

INTRODUCTION: Difficult and large common bile duct stones can be crushed and removed using a mechanical lithotripter. Very often the lack of working space within the common bile duct causing the failure of mechanical lithotripsy would inevitably mean repeat or further invasive procedures. PRESENTATION OF CASE: A patient with large and multiple common bile duct stones underwent ERCP, and initial deployment of a mechanical lithotripter failed due to the lack of working space within the common bile duct. A through-the-scope (TTS) dilator was utilized to increase the working space before successful deployment of the mechanical lithotripter, and subsequent clearance of all stones within the same setting. DISCUSSION: We herein describe a novel and ingenious technique of utilizing a through-the-scope (TTS) dilator in helping to expand the space within the common bile duct to allow for full deployment of a mechanical lithotripter and successful clearance of common bile duct stones. This method can be easily applied by advanced endoscopists and is expected to lead to increased success rates of difficult common bile duct stones clearance in a single setting. CONCLUSION: Use of TTS dilators to increase working space within the common bile duct can be useful in increasing the success rates of mechanical lithotripsy in the setting of large and multiple common bile duct stones.