Single-center retrospective assessment of robotic-assisted simultaneous pancreas-kidney transplants: Exploring clinical utility.

The diabetic population is witnessing a rise in obesity rates, creating specific hurdles for individuals seeking pancreas transplantation because they are frequently disqualified due to their elevated body weight. Introducing a robotic-assisted approach to transplantation has been proven to yield improved outcomes, particularly in patients with obesity. A retrospective analysis was conducted between January 2015 and September 2023. The study included a total of 140 patients, with 16 receiving robotic-assisted simultaneous pancreas-kidney transplantation (RSPK) and 124 undergoing open approach simultaneous pancreas-kidney transplantation (OSPK) during the study period. The median age was 45 (36.8-52.7) and 44.5 years (36.8-51.8) (RSPK vs OSPK, P = .487). There were no significant differences in demographics except body mass index (RSPK vs OSPK, 34.9 vs 28.1, P < .001) and a higher percentage of patients with high cardiac risk in the RSPK group. The robotic approach has a lengthier overall operative time and warm ischemia time. Surgical and nonsurgical complications at 30-days and 1-year grafts and patient survival (93.8% vs 96.8%, RSPK vs OSPK, P = .521) were similar. Our findings suggest that employing robotic assistance in simultaneous pancreas-kidney transplantation is safe. Wider adoption and utilization of this technique could potentially improve transplant accessibility for individuals with obesity and diabetes.

Artificial intelligence to enhance clinical value across the spectrum of cardiovascular healthcare.

Artificial intelligence (AI) is increasingly being utilized in healthcare. This article provides clinicians and researchers with a step-wise foundation for high-value AI that can be applied to a variety of different data modalities. The aim is to improve the transparency and application of AI methods, with the potential to benefit patients in routine cardiovascular care. Following a clear research hypothesis, an AI-based workflow begins with data selection and pre-processing prior to analysis, with the type of data (structured, semi-structured, or unstructured) determining what type of pre-processing steps and machine-learning algorithms are required. Algorithmic and data validation should be performed to ensure the robustness of the chosen methodology, followed by an objective evaluation of performance. Seven case studies are provided to highlight the wide variety of data modalities and clinical questions that can benefit from modern AI techniques, with a focus on applying them to cardiovascular disease management. Despite the growing use of AI, further education for healthcare workers, researchers, and the public are needed to aid understanding of how AI works and to close the existing gap in knowledge. In addition, issues regarding data access, sharing, and security must be addressed to ensure full engagement by patients and the public. The application of AI within healthcare provides an opportunity for clinicians to deliver a more personalized approach to medical care by accounting for confounders, interactions, and the rising prevalence of multi-morbidity.

Single-centre review of the management of intra-thoracic oesophageal perforation in a tertiary oesophageal unit: paradigm shift, short- and long-term outcomes over 15 years.

BACKGROUND: Oesophageal perforation is an uncommon surgical emergency associated with high morbidity and mortality. The timing and type of intervention is crucial and there has been a major paradigm shift towards minimal invasive management over the last 15 years. Herein, we review our management of spontaneous and iatrogenic oesophageal perforations and assess the short- and long-term outcomes. METHODS: We performed a retrospective review of consecutive patients presenting with intra-thoracic oesophageal perforation between January 2004 and Dec 2020 in a single tertiary hospital. RESULTS: Seventy-four patients were identified with oesophageal perforations: 58.1% were male; mean age of 68.28 ± 13.67 years. Aetiology was spontaneous in 42 (56.76%), iatrogenic in 29 (39.2%) and foreign body ingestion/related to trauma in 3 (4.1%). The diagnosis was delayed in 29 (39.2%) cases for longer than 24 h. There was change in the primary diagnostic modality over the period of this study with CT being used for diagnosis for 19 of 20 patients (95%). Initial management of the oesophageal perforation included a surgical intervention in 34 [45.9%; primary closure in 28 (37.8%), resection in 6 (8.1%)], endoscopic stenting in 18 (24.3%) and conservative management in 22 (29.7%) patients. On multivariate analysis, there was an effect of pathology (malignant vs. benign; p = 0.003) and surgical treatment as first line (p = 0.048) on 90-day mortality. However, at 1-year and overall follow-up, time to presentation (≤ 24 h vs. > 24 h) remained the only significant variable (p = 0.017 & p = 0.02, respectively). CONCLUSION: Oesophageal perforation remains a condition with high mortality. The paradigm shift in our tertiary unit suggests the more liberal use of CT to establish an earlier diagnosis and a higher rate of oesophageal stenting as a primary management option for iatrogenic perforations. Time to diagnosis and management continues to be the most critical variable in the overall outcome.

Redefining ß-blocker response in heart failure patients with sinus rhythm and atrial fibrillation: a machine learning cluster analysis.

BACKGROUND: Mortality remains unacceptably high in patients with heart failure and reduced left ventricular ejection fraction (LVEF) despite advances in therapeutics. We hypothesised that a novel artificial intelligence approach could better assess multiple and higher-dimension interactions of comorbidities, and define clusters of ß-blocker efficacy in patients with sinus rhythm and atrial fibrillation. METHODS: Neural network-based variational autoencoders and hierarchical clustering were applied to pooled individual patient data from nine double-blind, randomised, placebo-controlled trials of ß blockers. All-cause mortality during median 1·3 years of follow-up was assessed by intention to treat, stratified by electrocardiographic heart rhythm. The number of clusters and dimensions was determined objectively, with results validated using a leave-one-trial-out approach. This study was prospectively registered with ClinicalTrials.gov (NCT00832442) and the PROSPERO database of systematic reviews (CRD42014010012). FINDINGS: 15 659 patients with heart failure and LVEF of less than 50% were included, with median age 65 years (IQR 56-72) and LVEF 27% (IQR 21-33). 3708 (24%) patients were women. In sinus rhythm (n=12 822), most clusters demonstrated a consistent overall mortality benefit from ß blockers, with odds ratios (ORs) ranging from 0·54 to 0·74. One cluster in sinus rhythm of older patients with less severe symptoms showed no significant efficacy (OR 0·86, 95% CI 0·67-1·10; p=0·22). In atrial fibrillation (n=2837), four of five clusters were consistent with the overall neutral effect of ß blockers versus placebo (OR 0·92, 0·77-1·10; p=0·37). One cluster of younger atrial fibrillation patients at lower mortality risk but similar LVEF to average had a statistically significant reduction in mortality with ß blockers (OR 0·57, 0·35-0·93; p=0·023). The robustness and consistency of clustering was confirmed for all models (p<0·0001 vs random), and cluster membership was externally validated across the nine independent trials. INTERPRETATION: An artificial intelligence-based clustering approach was able to distinguish prognostic response from ß blockers in patients with heart failure and reduced LVEF. This included patients in sinus rhythm with suboptimal efficacy, as well as a cluster of patients with atrial fibrillation where ß blockers did reduce mortality. FUNDING: Medical Research Council, UK, and EU/EFPIA Innovative Medicines Initiative BigData@Heart.

Early onset of immune-mediated diseases in minority ethnic groups in the UK.

BACKGROUND: The prevalence of some immune-mediated diseases (IMDs) shows distinct differences between populations of different ethnicities. The aim of this study was to determine if the age at diagnosis of common IMDs also differed between different ethnic groups in the UK, suggestive of distinct influences of ethnicity on disease pathogenesis. METHODS: This was a population-based retrospective primary care study. Linear regression provided unadjusted and adjusted estimates of age at diagnosis for common IMDs within the following ethnic groups: White, South Asian, African-Caribbean and Mixed-race/Other. Potential disease risk confounders in the association between ethnicity and diagnosis age including sex, smoking, body mass index and social deprivation (Townsend quintiles) were adjusted for. The analysis was replicated using data from UK Biobank (UKB). RESULTS: After adjusting for risk confounders, we observed that individuals from South Asian, African-Caribbean and Mixed-race/Other ethnicities were diagnosed with IMDs at a significantly younger age than their White counterparts for almost all IMDs. The difference in the diagnosis age (ranging from 2 to 30 years earlier) varied for each disease and by ethnicity. For example, rheumatoid arthritis was diagnosed at age 49, 48 and 47 years in individuals of African-Caribbean, South Asian and Mixed-race/Other ethnicities respectively, compared to 56 years in White ethnicities. The earlier diagnosis of most IMDs observed was validated in UKB although with a smaller effect size. CONCLUSION: Individuals from non-White ethnic groups in the UK had an earlier age at diagnosis for several IMDs than White adults.

30-day morbidity and mortality of sleeve gastrectomy, Roux-en-Y gastric bypass and one anastomosis gastric bypass: a propensity score-matched analysis of the GENEVA data.

BACKGROUND: There is a paucity of data comparing 30-day morbidity and mortality of sleeve gastrectomy (SG), Roux-en-Y gastric bypass (RYGB), and one anastomosis gastric bypass (OAGB). This study aimed to compare the 30-day safety of SG, RYGB, and OAGB in propensity score-matched cohorts. MATERIALS AND METHODS: This analysis utilised data collected from the GENEVA study which was a multicentre observational cohort study of bariatric and metabolic surgery (BMS) in 185 centres across 42 countries between 01/05/2022 and 31/10/2020 during the Coronavirus Disease-2019 (COVID-19) pandemic. 30-day complications were categorised according to the Clavien-Dindo classification. Patients receiving SG, RYGB, or OAGB were propensity-matched according to baseline characteristics and 30-day complications were compared between groups. RESULTS: In total, 6770 patients (SG 3983; OAGB 702; RYGB 2085) were included in this analysis. Prior to matching, RYGB was associated with highest 30-day complication rate (SG 5.8%; OAGB 7.5%; RYGB 8.0% (p = 0.006)). On multivariate regression modelling, Insulin-dependent type 2 diabetes mellitus and hypercholesterolaemia were associated with increased 30-day complications. Being a non-smoker was associated with reduced complication rates. When compared to SG as a reference category, RYGB, but not OAGB, was associated with an increased rate of 30-day complications. A total of 702 pairs of SG and OAGB were propensity score-matched. The complication rate in the SG group was 7.3% (n = 51) as compared to 7.5% (n = 53) in the OAGB group (p = 0.68). Similarly, 2085 pairs of SG and RYGB were propensity score-matched. The complication rate in the SG group was 6.1% (n = 127) as compared to 7.9% (n = 166) in the RYGB group (p = 0.09). And, 702 pairs of OAGB and RYGB were matched. The complication rate in both groups was the same at 7.5 % (n = 53; p = 0.07). CONCLUSIONS: This global study found no significant difference in the 30-day morbidity and mortality of SG, RYGB, and OAGB in propensity score-matched cohorts.

Evaluation and improvement of the National Early Warning Score (NEWS2) for COVID-19: a multi-hospital study.

BACKGROUND: The National Early Warning Score (NEWS2) is currently recommended in the UK for the risk stratification of COVID-19 patients, but little is known about its ability to detect severe cases. We aimed to evaluate NEWS2 for the prediction of severe COVID-19 outcome and identify and validate a set of blood and physiological parameters routinely collected at hospital admission to improve upon the use of NEWS2 alone for medium-term risk stratification. METHODS: Training cohorts comprised 1276 patients admitted to King's College Hospital National Health Service (NHS) Foundation Trust with COVID-19 disease from 1 March to 30 April 2020. External validation cohorts included 6237 patients from five UK NHS Trusts (Guy's and St Thomas' Hospitals, University Hospitals Southampton, University Hospitals Bristol and Weston NHS Foundation Trust, University College London Hospitals, University Hospitals Birmingham), one hospital in Norway (Oslo University Hospital), and two hospitals in Wuhan, China (Wuhan Sixth Hospital and Taikang Tongji Hospital). The outcome was severe COVID-19 disease (transfer to intensive care unit (ICU) or death) at 14 days after hospital admission. Age, physiological measures, blood biomarkers, sex, ethnicity, and comorbidities (hypertension, diabetes, cardiovascular, respiratory and kidney diseases) measured at hospital admission were considered in the models. RESULTS: A baseline model of 'NEWS2 + age' had poor-to-moderate discrimination for severe COVID-19 infection at 14 days (area under receiver operating characteristic curve (AUC) in training cohort = 0.700, 95% confidence interval (CI) 0.680, 0.722; Brier score = 0.192, 95% CI 0.186, 0.197). A supplemented model adding eight routinely collected blood and physiological parameters (supplemental oxygen flow rate, urea, age, oxygen saturation, C-reactive protein, estimated glomerular filtration rate, neutrophil count, neutrophil/lymphocyte ratio) improved discrimination (AUC = 0.735; 95% CI 0.715, 0.757), and these improvements were replicated across seven UK and non-UK sites. However, there was evidence of miscalibration with the model tending to underestimate risks in most sites. CONCLUSIONS: NEWS2 score had poor-to-moderate discrimination for medium-term COVID-19 outcome which raises questions about its use as a screening tool at hospital admission. Risk stratification was improved by including readily available blood and physiological parameters measured at hospital admission, but there was evidence of miscalibration in external sites. This highlights the need for a better understanding of the use of early warning scores for COVID.

Safety outcomes of bariatric surgery in patients with advanced organ disease: the ONWARD study: a prospective cohort study.

INTRODUCTION: Increasing numbers of patients with advanced organ disease are being considered for bariatric and metabolic surgery (BMS). There is no prospective study on the safety of BMS in these patients. This study aimed to capture outcomes for patients with advanced cardiac, renal, or liver disease undergoing BMS. MATERIALS AND METHODS: This was a multinational, prospective cohort study on the safety of elective BMS in adults (≥18 years) with advanced disease of the heart, liver, or kidney. RESULTS: Data on 177 patients with advanced diseases of heart, liver, or kidney were submitted by 75 centres in 33 countries. Mean age and BMI was 48.56±11.23 years and 45.55±7.35 kg/m 2 , respectively. Laparoscopic sleeve gastrectomy was performed in 124 patients (70%). The 30-day morbidity and mortality were 15.9% ( n =28) and 1.1% ( n =2), respectively. Thirty-day morbidity was 16.4%, 11.7%, 20.5%, and 50.0% in patients with advanced heart ( n =11/61), liver ( n =8/68), kidney ( n =9/44), and multi-organ disease ( n =2/4), respectively. Cardiac patients with left ventricular ejection fraction less than or equal to 35% and New York Heart Association classification 3 or 4, liver patients with model for end-stage liver disease score greater than or equal to 12, and patients with advanced renal disease not on dialysis were at increased risk of complications. Comparison with a propensity score-matched cohort found advanced disease of the heart, liver, or kidney to be significantly associated with higher 30-day morbidity. CONCLUSION: Patients with advanced organ disease are at increased risk of 30-day morbidity following BMS. This prospective study quantifies that risk and identifies patients at the highest risk.

Correction: Evaluating the detection ability of a range of epistasis detection methods on simulated data for pure and impure epistatic models.

[This corrects the article DOI: 10.1371/journal.pone.0263390.].

Evaluating the detection ability of a range of epistasis detection methods on simulated data for pure and impure epistatic models.

BACKGROUND: Numerous approaches have been proposed for the detection of epistatic interactions within GWAS datasets in order to better understand the drivers of disease and genetics. METHODS: A selection of state-of-the-art approaches were assessed. These included the statistical tests, fast-epistasis, BOOST, logistic regression and wtest; swarm intelligence methods, namely AntEpiSeeker, epiACO and CINOEDV; and data mining approaches, including MDR, GSS, SNPRuler and MPI3SNP. Data were simulated to provide randomly generated models with no individual main effects at different heritabilities (pure epistasis) as well as models based on penetrance tables with some main effects (impure epistasis). Detection of both two and three locus interactions were assessed across a total of 1,560 simulated datasets. The different methods were also applied to a section of the UK biobank cohort for Atrial Fibrillation. RESULTS: For pure, two locus interactions, PLINK's implementation of BOOST recovered the highest number of correct interactions, with 53.9% and significantly better performing than the other methods (p = 4.52e - 36). For impure two locus interactions, MDR exhibited the best performance, recovering 62.2% of the most significant impure epistatic interactions (p = 6.31e - 90 for all but one test). The assessment of three locus interaction prediction revealed that wtest recovered the highest number (17.2%) of pure epistatic interactions(p = 8.49e - 14). wtest also recovered the highest number of three locus impure epistatic interactions (p = 6.76e - 48) while AntEpiSeeker ranked as the most significant the highest number of such interactions (40.5%). Finally, when applied to a real dataset for Atrial Fibrillation, most notably finding an interaction between SYNE2 and DTNB.

Eligibility for early rhythm control in patients with atrial fibrillation in the UK Biobank.

OBJECTIVE: The Early Treatment of Atrial Fibrillation for Stroke Prevention (EAST-AFNET4) trial showed a clinical benefit of early rhythm-control therapy in patients with recently diagnosed atrial fibrillation (AF). The generalisability of the results in the general population is not known. METHODS: Participants in the population-based UK Biobank were assessed for eligibility based on the EAST-AFNET4 inclusion/exclusion criteria. Treatment of all eligible participants was classified as early rhythm-control (antiarrhythmic drug therapy or AF ablation) or usual care. To assess treatment effects, primary care data and Hospital Episode Statistics were merged with UK Biobank data.Efficacy and safety outcomes were compared between groups in the entire cohort and in a propensity-matched data set. RESULTS: AF was present in 35 526/502 493 (7.1%) participants, including 8340 (988 with AF <1 year) with AF at enrolment and 27 186 with incident AF during follow-up. Most participants (22 003/27 186; 80.9%) with incident AF were eligible for early rhythm-control.Eligible participants were older (70 years vs 63 years) and more likely to be female (42% vs 21%) compared with ineligible patients. Of 9004 participants with full primary care data, 874 (9.02%) received early rhythm-control. Safety outcomes were not different between patients receiving early rhythm-control and controls. The primary outcome of EAST-AFNET 4, a composite of cardiovascular death, stroke/transient ischaemic attack and hospitalisation for heart failure or acute coronary syndrome occurred less often in participants receiving early rhythm-control compared with controls in the entire cohort (HR 0.82, 95% CI 0.71 to 0.94, p=0.005). In the propensity-score matched analysis, early rhythm-control did not significantly decrease of the primary outcome compared with usual care (HR 0.87, 95% CI 0.72 to 1.04, p=0.124). CONCLUSION: Around 80% of participants diagnosed with AF in the UK population are eligible for early rhythm-control. Early rhythm-control therapy was safe in routine care.

Implementation of patient-reported outcome measures in real-world evidence studies: Analysis of ClinicalTrials.gov records (1999-2021).

BACKGROUND: Real-world evidence (RWE) plays an increasingly important role within global regulatory and reimbursement processes. RWE generation can be enhanced by collecting and using patient-reported outcomes (PROs), which can provide valuable information on the effectiveness, safety, and tolerability of health interventions from the patient perspective. This analysis aims to examine and summarise the utilisation of patient-reported outcomes measures (PROMs) in real-world studies. METHODS: Descriptions of phase IV trials were downloaded on July 22, 2021 from the Clinicaltrials.gov database since its inception. An automated algorithm was built to detect trials utilising PROMs and composite measures including patient-reported components. Search terms were developed based on the PROQOLID database. RESULTS: Of 27,976 phase IV clinical trials posted on Clinicaltrials.gov between 1999 and July 2021, 21% and 4% used PROMs and composite measures, respectively. Recent years demonstrated a steady increase in the utilisation of PROMs in phase IV trials. CONCLUSIONS: The use of PROMs in phase IV trials seems to be lower than its use in earlier phases of clinical research. Increased uptake of PROMs in RWE studies can be facilitated in a number of ways including the development of standards for their collection, analysis and use.

Smartphone detection of atrial fibrillation using photoplethysmography: a systematic review and meta-analysis.

OBJECTIVES: Timely diagnosis of atrial fibrillation (AF) is essential to reduce complications from this increasingly common condition. We sought to assess the diagnostic accuracy of smartphone camera photoplethysmography (PPG) compared with conventional electrocardiogram (ECG) for AF detection. METHODS: This is a systematic review of MEDLINE, EMBASE and Cochrane (1980-December 2020), including any study or abstract, where smartphone PPG was compared with a reference ECG (1, 3 or 12-lead). Random effects meta-analysis was performed to pool sensitivity/specificity and identify publication bias, with study quality assessed using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies-2) risk of bias tool. RESULTS: 28 studies were included (10 full-text publications and 18 abstracts), providing 31 comparisons of smartphone PPG versus ECG for AF detection. 11 404 participants were included (2950 in AF), with most studies being small and based in secondary care. Sensitivity and specificity for AF detection were high, ranging from 81% to 100%, and from 85% to 100%, respectively. 20 comparisons from 17 studies were meta-analysed, including 6891 participants (2299 with AF); the pooled sensitivity was 94% (95% CI 92% to 95%) and specificity 97% (96%-98%), with substantial heterogeneity (p<0.01). Studies were of poor quality overall and none met all the QUADAS-2 criteria, with particular issues regarding selection bias and the potential for publication bias. CONCLUSION: PPG provides a non-invasive, patient-led screening tool for AF. However, current evidence is limited to small, biased, low-quality studies with unrealistically high sensitivity and specificity. Further studies are needed, preferably independent from manufacturers, in order to advise clinicians on the true value of PPG technology for AF detection.

A Causal Web between Chronotype and Metabolic Health Traits.

Observational and experimental evidence has linked chronotype to both psychological and cardiometabolic traits. Recent Mendelian randomization (MR) studies have investigated direct links between chronotype and several of these traits, often in isolation of outside potential mediating or moderating traits. We mined the EpiGraphDB MR database for calculated chronotype-trait associations (p-value < 5 × 10-8). We then re-analyzed those relevant to metabolic or mental health and investigated for statistical evidence of horizontal pleiotropy. Analyses passing multiple testing correction were then investigated for confounders, colliders, intermediates, and reverse intermediates using the EpiGraphDB database, creating multiple chronotype-trait interactions among each of the the traits studied. We revealed 10 significant chronotype-exposure associations (false discovery rate < 0.05) exposed to 111 potential previously known confounders, 52 intermediates, 18 reverse intermediates, and 31 colliders. Chronotype-lipid causal associations collided with treatment and diabetes effects; chronotype-bipolar associations were mediated by breast cancer; and chronotype-alcohol intake associations were impacted by confounders and intermediate variables including known zeitgebers and molecular traits. We have reported the influence of chronotype on several cardiometabolic and behavioural traits, and identified potential confounding variables not reported on in studies while discovering new associations to drugs and disease.

Multimorbidity prediction using link prediction.

Multimorbidity, frequently associated with aging, can be operationally defined as the presence of two or more chronic conditions. Predicting the likelihood of a patient with multimorbidity to develop a further particular disease in the future is one of the key challenges in multimorbidity research. In this paper we are using a network-based approach to analyze multimorbidity data and develop methods for predicting diseases that a patient is likely to develop. The multimorbidity data is represented using a temporal bipartite network whose nodes represent patients and diseases and a link between these nodes indicates that the patient has been diagnosed with the disease. Disease prediction then is reduced to a problem of predicting those missing links in the network that are likely to appear in the future. We develop a novel link prediction method for static bipartite network and validate the performance of the method on benchmark datasets. By using a probabilistic framework, we then report on the development of a method for predicting future links in the network, where links are labelled with a time-stamp. We apply the proposed method to three different multimorbidity datasets and report its performance measured by different performance metrics including AUC, Precision, Recall, and F-Score.

Ensemble learning for poor prognosis predictions: A case study on SARS-CoV-2.

OBJECTIVE: Risk prediction models are widely used to inform evidence-based clinical decision making. However, few models developed from single cohorts can perform consistently well at population level where diverse prognoses exist (such as the SARS-CoV-2 [severe acute respiratory syndrome coronavirus 2] pandemic). This study aims at tackling this challenge by synergizing prediction models from the literature using ensemble learning. MATERIALS AND METHODS: In this study, we selected and reimplemented 7 prediction models for COVID-19 (coronavirus disease 2019) that were derived from diverse cohorts and used different implementation techniques. A novel ensemble learning framework was proposed to synergize them for realizing personalized predictions for individual patients. Four diverse international cohorts (2 from the United Kingdom and 2 from China; N = 5394) were used to validate all 8 models on discrimination, calibration, and clinical usefulness. RESULTS: Results showed that individual prediction models could perform well on some cohorts while poorly on others. Conversely, the ensemble model achieved the best performances consistently on all metrics quantifying discrimination, calibration, and clinical usefulness. Performance disparities were observed in cohorts from the 2 countries: all models achieved better performances on the China cohorts. DISCUSSION: When individual models were learned from complementary cohorts, the synergized model had the potential to achieve better performances than any individual model. Results indicate that blood parameters and physiological measurements might have better predictive powers when collected early, which remains to be confirmed by further studies. CONCLUSIONS: Combining a diverse set of individual prediction models, the ensemble method can synergize a robust and well-performing model by choosing the most competent ones for individual patients.

A random forest based biomarker discovery and power analysis framework for diagnostics research.

BACKGROUND: Biomarker identification is one of the major and important goal of functional genomics and translational medicine studies. Large scale -omics data are increasingly being accumulated and can provide vital means for the identification of biomarkers for the early diagnosis of complex disease and/or for advanced patient/diseases stratification. These tasks are clearly interlinked, and it is essential that an unbiased and stable methodology is applied in order to address them. Although, recently, many, primarily machine learning based, biomarker identification approaches have been developed, the exploration of potential associations between biomarker identification and the design of future experiments remains a challenge. METHODS: In this study, using both simulated and published experimentally derived datasets, we assessed the performance of several state-of-the-art Random Forest (RF) based decision approaches, namely the Boruta method, the permutation based feature selection without correction method, the permutation based feature selection with correction method, and the backward elimination based feature selection method. Moreover, we conducted a power analysis to estimate the number of samples required for potential future studies. RESULTS: We present a number of different RF based stable feature selection methods and compare their performances using simulated, as well as published, experimentally derived, datasets. Across all of the scenarios considered, we found the Boruta method to be the most stable methodology, whilst the Permutation (Raw) approach offered the largest number of relevant features, when allowed to stabilise over a number of iterations. Finally, we developed and made available a web interface ( https://joelarkman.shinyapps.io/PowerTools/ ) to streamline power calculations thereby aiding the design of potential future studies within a translational medicine context. CONCLUSIONS: We developed a RF-based biomarker discovery framework and provide a web interface for our framework, termed PowerTools, that caters the design of appropriate and cost-effective subsequent future omics study.