Machine learning prediction models for clinical management of blood-borne viral infections: a systematic review of current applications and future impact.

BACKGROUND: Machine learning (ML) prediction models to support clinical management of blood-borne viral infections are becoming increasingly abundant in medical literature, with a number of competing models being developed for the same outcome or target population. However, evidence on the quality of these ML prediction models are limited. OBJECTIVE: This study aimed to evaluate the development and quality of reporting of ML prediction models that could facilitate timely clinical management of blood-borne viral infections. METHODS: We conducted narrative evidence synthesis following the synthesis without meta-analysis guidelines. We searched PubMed and Cochrane Central Register of Controlled Trials for all studies applying ML models for predicting clinical outcomes associated with hepatitis B virus (HBV), human immunodeficiency virus (HIV), or hepatitis C virus (HCV). RESULTS: We found 33 unique ML prediction models aiming to support clinical decision making. Overall, 12 (36.4%) focused on HBV, 10 (30.3%) on HCV, 10 on HIV (30.3%) and two (6.1%) on co-infection. Among these, six (18.2%) addressed the diagnosis of infection, 16 (48.5%) the prognosis of infection, eight (24.2%) the prediction of treatment response, two (6.1%) progression through a cascade of care, and one (3.03%) focused on the choice of antiretroviral therapy (ART). Nineteen prediction models (57.6%) were developed using data from high-income countries. Evaluation of prediction models was limited to measures of performance. Detailed information on software code accessibility was often missing. Independent validation on new datasets and/or in other institutions was rarely done. CONCLUSION: Promising approaches for ML prediction models in blood-borne viral infections were identified, but the lack of robust validation, interpretability/explainability, and poor quality of reporting hampered their clinical relevance. Our findings highlight important considerations that can inform standard reporting guidelines for ML prediction models in the future (e.g., TRIPOD-AI), and provides critical data to inform robust evaluation of the models.

Routine blood test markers for predicting liver disease post HBV infection: precision pathology and pattern recognition.

BACKGROUND: Early stages of hepatitis B virus (HBV) infection usually involve inflammation of the liver. Patients with chronic infection have an increased risk of progressive liver fibrosis, cirrhosis, and life-threatening clinical complications of end-stage hepatocellular carcinoma (HCC). CONTENT: Early diagnosis of hepatic fibrosis and timely clinical management are critical to controlling disease progression and decreasing the burden of end-stage liver cancer. Fibrosis staging, through its current gold standard, liver biopsy, improves patient outcomes, but the clinical procedure is invasive with unpleasant post-procedural complications. Routine blood test markers offer promising diagnostic potential for early detection of liver disease without biopsy. There is a plethora of candidate routine blood test markers that have gone through phases of biomarker validation and have shown great promise, but their current limitations include a predictive ability that is limited to only a few stages of fibrosis. However, the advent of machine learning, notably pattern recognition, presents an opportunity to refine blood-based non-invasive models of hepatic fibrosis in the future. SUMMARY: In this review, we highlight the current landscape of routine blood-based non-invasive models of hepatic fibrosis, and appraise the potential application of machine learning (pattern recognition) algorithms to refining these models and optimising clinical predictions of HBV-associated liver disease. OUTLOOK: Machine learning via pattern recognition algorithms takes data analytics to a new realm, and offers the opportunity for enhanced multi-marker fibrosis stage prediction using pathology profile that leverages information across patient routine blood tests.

Clinical Validity of a Machine Learning Decision Support System for Early Detection of Hepatitis B Virus: A Binational External Validation Study.

HepB LiveTest is a machine learning decision support system developed for the early detection of hepatitis B virus (HBV). However, there is a lack of evidence on its generalisability. In this study, we aimed to externally assess the clinical validity and portability of HepB LiveTest in predicting HBV infection among independent patient cohorts from Nigeria and Australia. The performance of HepB LiveTest was evaluated by constructing receiver operating characteristic curves and estimating the area under the curve. Delong's method was used to estimate the 95% confidence interval (CI) of the area under the receiver-operating characteristic curve (AUROC). Compared to the Australian cohort, patients in the derivation cohort of HepB LiveTest and the hospital-based Nigerian cohort were younger (mean age, 45.5 years vs. 38.8 years vs. 40.8 years, respectively; p < 0.001) and had a higher incidence of HBV infection (1.9% vs. 69.4% vs. 57.3%). In the hospital-based Nigerian cohort, HepB LiveTest performed optimally with an AUROC of 0.94 (95% CI, 0.91-0.97). The model provided tailored predictions that ensured most cases of HBV infection did not go undetected. However, its discriminatory measure dropped to 0.60 (95% CI, 0.56-0.64) in the Australian cohort. These findings indicate that HepB LiveTest exhibits adequate cross-site transportability and clinical validity in the hospital-based Nigerian patient cohort but shows limited performance in the Australian cohort. Whilst HepB LiveTest holds promise for reducing HBV prevalence in underserved populations, caution is warranted when implementing the model in older populations, particularly in regions with low incidence of HBV infection.

Liver and cardiometabolic markers and conditions in a cross-sectional study of three Australian communities living with environmental per- and polyfluoroalkyl substances contamination.

BACKGROUND: Per- and polyfluoroalkyl substances (PFAS) have been associated with higher cholesterol and liver function markers in some studies, but the evidence for specific cardiometabolic conditions has been inconclusive. OBJECTIVES: We quantified the associations of single and combined PFAS with cardiometabolic markers and conditions in a cross-sectional study of three Australian communities with PFAS-contaminated water from the historical use of aqueous film-forming foam in firefighting activities, and three comparison communities. METHODS: Participants gave blood samples for measurement of nine PFAS, four lipids, six liver function markers, and completed a survey on sociodemographic characteristics and eight cardiometabolic conditions. We estimated differences in mean biomarker concentrations per doubling in single PFAS concentrations (linear regression) and per interquartile range increase in the PFAS mixture (Bayesian kernel machine regression). We estimated prevalence ratios of biomarker concentrations outside reference limits and self-reported cardiometabolic conditions (Poisson regression). RESULTS: We recruited 881 adults in exposed communities and 801 in comparison communities. We observed higher mean total cholesterol with higher single and mixture PFAS concentrations in blood serum (e.g., 0.18 mmol/L, 95% credible interval -0.06 to 0.42, higher total cholesterol concentrations with an interquartile range increase in all PFAS concentrations in Williamtown, New South Wales), with varying certainty across communities and PFAS. There was less consistency in direction of associations for liver function markers. Serum perfluorooctanoic acid (PFOA) concentrations were positively associated with the prevalence of self-reported hypercholesterolemia in one of three communities, but PFAS concentrations were not associated with self-reported type II diabetes, liver disease, or cardiovascular disease. DISCUSSION: Our study is one of few that has simultaneously quantified the associations of blood PFAS concentrations with multiple biomarkers and cardiometabolic conditions in multiple communities. Our findings for total cholesterol were consistent with previous studies; however, substantial uncertainty in our estimates and the cross-sectional design limit causal inference.

The development of a machine learning algorithm for early detection of viral hepatitis B infection in Nigerian patients.

Access to Hepatitis B Virus (HBV) testing for people in low-resource settings has long been challenging due to the gold standard, enzyme immunoassay, being prohibitively expensive, and requiring specialised skills and facilities that are not readily available, particularly in remote and isolated laboratories. Routine pathology data in tandem with cutting-edge machine learning shows promising diagnostic potential. In this study, recursive partitioning ("trees") and Support Vector Machines (SVMs) were applied to interrogate patient dataset (n = 916) that comprised results for Hepatitis B Surface Antigen (HBsAg) and routine clinical chemistry and haematology blood tests. These algorithms were used to develop a predictive diagnostic model of HBV infection. Our SVM-based diagnostic model of infection (accuracy = 85.4%, sensitivity = 91%, specificity = 72.6%, precision = 88.2%, F1-score = 0.89, Area Under the Receiver Operating Curve, AUC = 0.90) proved to be highly accurate for discriminating HBsAg positive from negative patients, and thus rivals with immunoassay. Therefore, we propose a predictive model based on routine blood tests as a novel diagnostic for early detection of HBV infection. Early prediction of HBV infection via routine pathology markers and pattern recognition algorithms will offer decision-support to clinicians and enhance early diagnosis, which is critical for optimal clinical management and improved patient outcomes.

Could the kynurenine pathway be the key missing piece of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) complex puzzle?

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is a complex and debilitating disease with a substantial social and economic impact on individuals and their community. Despite its importance and deteriorating impact, progresses in diagnosis and treatment of ME/CFS is limited. This is due to the unclear pathophysiology of the disease and consequently lack of prognostic biomarkers. To investigate pathophysiology of ME/CFS, several potential pathologic hallmarks have been investigated; however, these studies have failed to report a consistent result. These failures in introducing the underlying reason for ME/CFS have stimulated considering other possible contributing mechanisms such as tryptophan (TRP) metabolism and in particular kynurenine pathway (KP). KP plays a central role in cellular energy production through the production of nicotinamide adenine dinucleotide (NADH). In addition, this pathway has been shown to mediate immune response and neuroinflammation through its metabolites. This review, we will discuss the pathology and management of ME/CFS and provide evidence pertaining KP abnormalities and symptoms that are classic characteristics of ME/CFS. Targeting the KP regulation may provide innovative approaches to the management of ME/CFS.

Hepatitis B virus infection in Nigeria: a systematic review and meta-analysis of data published between 2010 and 2019.

BACKGROUND: Hepatitis B virus (HBV) is an infectious disease of global significance, causing a significant health burden in Africa due to complications associated with infection, such as cirrhosis and liver cancer. In Nigeria, which is considered a high prevalence country, estimates of HBV cases are inconsistent, and therefore additional clarity is required to manage HBV-associated public health challenges. METHODS: A systematic review of the literature (via PubMed, Advanced Google Scholar, African Index Medicus) was conducted to retrieve primary studies published between 1 January 2010 and 31 December 2019, with a random-effects model based on proportions used to estimate the population-based prevalence of HBV in the Nigerian population. RESULTS: The final analyses included 47 studies with 21,702 participants that revealed a pooled prevalence of 9.5%. A prevalence estimate above 8% in a population is classified as high. Sub-group analyses revealed the highest HBV prevalence in rural settings (10.7%). The North West region had the highest prevalence (12.1%) among Nigeria's six geopolitical zones/regions. The estimate of total variation between studies indicated substantial heterogeneity. These variations could be explained by setting and geographical region. The statistical test for Egger's regression showed no evidence of publication bias (p = 0.879). CONCLUSIONS: We present an up-to-date review on the prevalence of HBV in Nigeria, which will provide critical data to optimise and assess the impact of current prevention and control strategies, including disease surveillance and diagnoses, vaccination policies and management for those infected.

Ross River Virus Immune Evasion Strategies and the Relevance to Post-viral Fatigue, and Myalgic Encephalomyelitis Onset.

Ross River virus (RRV) is an endemic Australian arbovirus, and member of the Alphavirus family that also includes Chikungunya virus (CHIK). RRV is responsible for the highest prevalence of human disease cases associated with mosquito-borne transmission in Australia, and has long been a leading suspect in cases of post-viral fatigue syndromes, with extrapolation of this link to Myalgic Encephalomyelitis (ME). Research into RRV pathogenesis has revealed a number of immune evasion strategies, impressive for a virus with a genome size of 12 kb (plus strand RNA), which resonate with insights into viral pathogenesis broadly. Drawing from observations on RRV immune evasion, mechanisms of relevance to long term idiopathic fatigue are featured as a perspective on infection and eventual ME symptoms, which include considerations of; (1) selective pro-inflammatory gene suppression post antibody-dependent enhancement (ADE) of RRV infection, (2) Evidence from other virus families of immune disruption and evasion post-ADE, and (3) how virally-driven immune evasion may impact on mitochondrial function via target of rapamycin (TOR) complexes. In light of these RRV measures to counter the host immune - inflammatory responses, links to recent discoveries explaining cellular, immune and metabolomic markers of ME will be explored and discussed, with the implications for long-COVID post SARS-CoV-2 also considered. Compelling issues on the connections between virally-induced alterations in cytokine expression, for example, will be of particular interest in light of energy pathways, and how these perturbations manifest clinically.

Gamma-Glutamyl Transferase (GGT) Is the Leading External Quality Assurance Predictor of ISO15189 Compliance for Pathology Laboratories.

Pathology results are central to modern medical practice, informing diagnosis and patient management. To ensure high standards from pathology laboratories, regulators require compliance with international and local standards. In Australia, the monitoring and regulation of medical laboratories are achieved by conformance to ISO15189-National Pathology Accreditation Advisory Council standards, as assessed by the National Association of Testing Authorities (NATA), and an external quality assurance (EQA) assessment via the Royal College of Pathologists of Australasia Quality Assurance Program (RCPAQAP). While effective individually, integration of data collected by NATA and EQA testing promises advantages for the early detection of technical or management problems in the laboratory, and enhanced ongoing quality assessment. Random forest (RF) machine learning (ML) previously identified gamma-glutamyl transferase (GGT) as a leading predictor of NATA compliance condition reporting. In addition to further RF investigations, this study also deployed single decision trees and support vector machines (SVM) models that included creatinine, electrolytes and liver function test (LFT) EQA results. Across all analyses, GGT was consistently the top-ranked predictor variable, validating previous observations from Australian laboratories. SVM revealed broad patterns of predictive EQA marker interactions with NATA outcomes, and the distribution of GGT relative deviation suggested patterns by which to identify other strong EQA predictors of NATA outcomes. An integrated model of pathology quality assessment was successfully developed, via the prediction of NATA outcomes by EQA results. GGT consistently ranked as the best predictor variable, identified by combining recursive partitioning and SVM ML strategies.

One Health Approach: A Data-Driven Priority for Mitigating Outbreaks of Emerging and Re-Emerging Zoonotic Infectious Diseases.

This paper discusses the contributions that One Health principles can make in improving global response to zoonotic infectious disease. We highlight some key benefits of taking a One Health approach to a range of complex infectious disease problems that have defied a more traditional sectoral approach, as well as public health policy and practice, where gaps in surveillance systems need to be addressed. The historical examples demonstrate the scope of One Health, partly from an Australian perspective, but also with an international flavour, and illustrate innovative approaches and outcomes with the types of collaborative partnerships that are required.

An Isolated Complex V Inefficiency and Dysregulated Mitochondrial Function in Immortalized Lymphocytes from ME/CFS Patients.

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is an enigmatic condition characterized by exacerbation of symptoms after exertion (post-exertional malaise or "PEM"), and by fatigue whose severity and associated requirement for rest are excessive and disproportionate to the fatigue-inducing activity. There is no definitive molecular marker or known underlying pathological mechanism for the condition. Increasing evidence for aberrant energy metabolism suggests a role for mitochondrial dysfunction in ME/CFS. Our objective was therefore to measure mitochondrial function and cellular stress sensing in actively metabolizing patient blood cells. We immortalized lymphoblasts isolated from 51 ME/CFS patients diagnosed according to the Canadian Consensus Criteria and an age- and gender-matched control group. Parameters of mitochondrial function and energy stress sensing were assessed by Seahorse extracellular flux analysis, proteomics, and an array of additional biochemical assays. As a proportion of the basal oxygen consumption rate (OCR), the rate of ATP synthesis by Complex V was significantly reduced in ME/CFS lymphoblasts, while significant elevations were observed in Complex I OCR, maximum OCR, spare respiratory capacity, nonmitochondrial OCR and "proton leak" as a proportion of the basal OCR. This was accompanied by a reduction of mitochondrial membrane potential, chronically hyperactivated TOR Complex I stress signaling and upregulated expression of mitochondrial respiratory complexes, fatty acid transporters, and enzymes of the ß-oxidation and TCA cycles. By contrast, mitochondrial mass and genome copy number, as well as glycolytic rates and steady state ATP levels were unchanged. Our results suggest a model in which ME/CFS lymphoblasts have a Complex V defect accompanied by compensatory upregulation of their respiratory capacity that includes the mitochondrial respiratory complexes, membrane transporters and enzymes involved in fatty acid ß-oxidation. This homeostatically returns ATP synthesis and steady state levels to "normal" in the resting cells, but may leave them unable to adequately respond to acute increases in energy demand as the relevant homeostatic pathways are already activated.

Biomedical Insights that Inform the Diagnosis of ME/CFS.

It is well known that myalgic encephalomyelitis (ME) and chronic fatigue syndrome (CFS) [...].

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome: A Comprehensive Review.

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a debilitating chronic disease of unknown aetiology that is recognized by the World Health Organization (WHO) and the United States Center for Disease Control and Prevention (US CDC) as a disorder of the brain. The disease predominantly affects adults, with a peak age of onset of between 20 and 45 years with a female to male ratio of 3:1. Although the clinical features of the disease have been well established within diagnostic criteria, the diagnosis of ME/CFS is still of exclusion, meaning that other medical conditions must be ruled out. The pathophysiological mechanisms are unclear but the neuro-immuno-endocrinological pattern of CFS patients gleaned from various studies indicates that these three pillars may be the key point to understand the complexity of the disease. At the moment, there are no specific pharmacological therapies to treat the disease, but several studies' aims and therapeutic approaches have been described in order to benefit patients' prognosis, symptomatology relief, and the recovery of pre-existing function. This review presents a pathophysiological approach to understanding the essential concepts of ME/CFS, with an emphasis on the population, clinical, and genetic concepts associated with ME/CFS.

Rethinking ME/CFS Diagnostic Reference Intervals via Machine Learning, and the Utility of Activin B for Defining Symptom Severity.

Biomarker discovery applied to myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS), a disabling disease of inconclusive aetiology, has identified several cytokines to potentially fulfil a role as a quantitative blood/serum marker for laboratory diagnosis, with activin B a recent addition. We explored further the potential of serum activin B as a ME/CFS biomarker, alone and in combination with a range of routine test results obtained from pathology laboratories. Previous pilot study results showed that activin B was significantly elevated for the ME/CFS participants compared to healthy (control) participants. All the participants were recruited via CFS Discovery and assessed via the Canadian/International Consensus Criteria. A significant difference for serum activin B was also detected for ME/CFS and control cohorts recruited for this study, but median levels were significantly lower for the ME/CFS cohort. Random Forest (RF) modelling identified five routine pathology blood test markers that collectively predicted ME/CFS at ≥62% when compared via weighted standing time (WST) severity classes. A closer analysis revealed that the inclusion of activin B to the panel of pathology markers improved the prediction of mild to moderate ME/CFS cases. Applying correct WST class prediction from RFA modelling, new reference intervals were calculated for activin B and associated pathology markers, where 24-h urinary creatinine clearance, serum urea and serum activin B showed the best potential as diagnostic markers. While the serum activin B results remained statistically significant for the new participant cohorts, activin B was found to also have utility in enhancing the prediction of symptom severity, as represented by WST class.

Weighting of orthostatic intolerance time measurements with standing difficulty score stratifies ME/CFS symptom severity and analyte detection.

BACKGROUND: Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is clinically defined and characterised by persistent disabling tiredness and exertional malaise, leading to functional impairment. METHODS: This study introduces the weighted standing time (WST) as a proxy for ME/CFS severity, and investigates its behaviour in an Australian cohort. WST was calculated from standing time and subjective standing difficulty data, collected via orthostatic intolerance assessments. The distribution of WST for healthy controls and ME/CFS patients was correlated with the clinical criteria, as well as pathology and cytokine markers. Included in the WST cytokine analyses were activins A and B, cytokines causally linked to inflammation, and previously demonstrated to separate ME/CFS from healthy controls. Forty-five ME/CFS patients were recruited from the CFS Discovery Clinic (Victoria) between 2011 and 2013. Seventeen healthy controls were recruited concurrently and identically assessed. RESULTS: WST distribution was significantly different between ME/CFS participants and controls, with six diagnostic criteria, five analytes and one cytokine also significantly different when comparing severity via WST. On direct comparison of ME/CFS to study controls, only serum activin B was significantly elevated, with no significant variation observed for a broad range of serum and urine markers, or other serum cytokines. CONCLUSIONS: The enhanced understanding of standing test behaviour to reflect orthostatic intolerance as a ME/CFS symptom, and the subsequent calculation of WST, will encourage the greater implementation of this simple test as a measure of ME/CFS diagnosis, and symptom severity, to the benefit of improved diagnosis and guidance for potential treatments.

Enhancement of hepatitis virus immunoassay outcome predictions in imbalanced routine pathology data by data balancing and feature selection before the application of support vector machines.

BACKGROUND: Data mining techniques such as support vector machines (SVMs) have been successfully used to predict outcomes for complex problems, including for human health. Much health data is imbalanced, with many more controls than positive cases. METHODS: The impact of three balancing methods and one feature selection method is explored, to assess the ability of SVMs to classify imbalanced diagnostic pathology data associated with the laboratory diagnosis of hepatitis B (HBV) and hepatitis C (HCV) infections. Random forests (RFs) for predictor variable selection, and data reshaping to overcome a large imbalance of negative to positive test results in relation to HBV and HCV immunoassay results, are examined. The methodology is illustrated using data from ACT Pathology (Canberra, Australia), consisting of laboratory test records from 18,625 individuals who underwent hepatitis virus testing over the decade from 1997 to 2007. RESULTS: Overall, the prediction of HCV test results by immunoassay was more accurate than for HBV immunoassay results associated with identical routine pathology predictor variable data. HBV and HCV negative results were vastly in excess of positive results, so three approaches to handling the negative/positive data imbalance were compared. Generating datasets by the Synthetic Minority Oversampling Technique (SMOTE) resulted in significantly more accurate prediction than single downsizing or multiple downsizing (MDS) of the dataset. For downsized data sets, applying a RF for predictor variable selection had a small effect on the performance, which varied depending on the virus. For SMOTE, a RF had a negative effect on performance. An analysis of variance of the performance across settings supports these findings. Finally, age and assay results for alanine aminotransferase (ALT), sodium for HBV and urea for HCV were found to have a significant impact upon laboratory diagnosis of HBV or HCV infection using an optimised SVM model. CONCLUSIONS: Laboratories looking to include machine learning via SVM as part of their decision support need to be aware that the balancing method, predictor variable selection and the virus type interact to affect the laboratory diagnosis of hepatitis virus infection with routine pathology laboratory variables in different ways depending on which combination is being studied. This awareness should lead to careful use of existing machine learning methods, thus improving the quality of laboratory diagnosis.

Activin B is a novel biomarker for chronic fatigue syndrome/myalgic encephalomyelitis (CFS/ME) diagnosis: a cross sectional study.

BACKGROUND: Investigations of activin family proteins as serum biomarkers for chronic fatigue syndrome/myalgic encephalomyelitis (CFS/ME). CFS/ME is a disease with complex, wide-ranging symptoms, featuring persistent fatigue of 6 months or longer, particularly post exertion. No definitive biomarkers are available. METHODS: A cross-sectional, observational study of CFS/ME patients fulfilling the 2003 Canadian Consensus Criteria, in parallel with healthy non-fatigued controls, was conducted. Comparisons with a previously defined activin reference population were also performed. For the total study cohort the age range was 18-65 years with a female: male participant ratio of greater than 3:1. All participants were assessed via a primary care community clinic. Blood samples were collected for pathology testing after physical examination and orthostatic intolerance assessment. Cytokines, activin A, activin B and follistatin were also measured in sera from these samples. All data were compared between the CFS/ME and control cohorts, with the activins and follistatin also compared with previously defined reference intervals. RESULTS: Serum activin B levels for CFS/ME participants were significantly elevated when compared to the study controls, as well as the established reference interval. Serum activin A and follistatin were within their normal ranges. All routine and special pathology markers were within the normal laboratory reference intervals for the total study cohort, with no significant differences detected between CFS/ME and control groups. Also, no significant differences were detected for IL-2, IL-4, IL-6, IL-10, IL-17A, TNF or IFN-gamma. CONCLUSION: Elevated activin B levels together with normal activin A levels identified patients with the diagnostic symptoms of CFS/ME, thus providing a novel serum based test. The activins have multiple physiological roles and capture the diverse array of symptoms experienced by CFS/ME patients.

The kinetics of haemoglobin and ferritin in longitudinal community patients with iron deficiency or hypoxia.

BACKGROUND: Red cell distribution width (RDW) is well recognised as a marker of iron-deficient anaemia, as well as useful to the distinction between some anaemic states. A role in the prediction of patient mortality and for the laboratory diagnosis of organ dysfunction has been also investigated. RDW has recently been suggested as a marker of acute and chronic hypoxia. METHODS: In this paper we use RDW kinetics to identify different patient groups and then investigate the relationship between RDW, ferritin and haemoglobin kinetics in a large cross-sectional community patient dataset. RESULTS: A novel mathematical model of this relationship is developed that captures all aspects of variation in the data. A linear regression of RDW/log(ferritin) on days is combined with a multi-level random structure including random intercepts and slopes for each patient. CONCLUSIONS: No evidence of an age affect was found in the data. On the other hand, significant patterns in the rises and falls of log(ferritin) and haemoglobin with RDW over time are identified.

Clinical chemistry in higher dimensions: Machine-learning and enhanced prediction from routine clinical chemistry data.

Big Data is having an impact on many areas of research, not the least of which is biomedical science. In this review paper, big data and machine learning are defined in terms accessible to the clinical chemistry community. Seven myths associated with machine learning and big data are then presented, with the aim of managing expectation of machine learning amongst clinical chemists. The myths are illustrated with four examples investigating the relationship between biomarkers in liver function tests, enhanced laboratory prediction of hepatitis virus infection, the relationship between bilirubin and white cell count, and the relationship between red cell distribution width and laboratory prediction of anaemia.