Bayesian statistics in medicine: a 25 year review

Designing a Bayesian adaptive clinical trial to evaluate novel mechanical ventilation strategies in acute respiratory failure using integrated nested Laplace approximations

BACKGROUND

Adaptive trials usually require simulations to determine values for design parameters, demonstrate error rates, and establish the sample size. We designed a Bayesian adaptive trial comparing ventilation strategies for patients with acute hypoxemic respiratory failure using simulations. The complexity of the analysis would usually require computationally expensive Markov Chain Monte Carlo methods but this barrier to simulation was overcome using the Integrated Nested Laplace Approximations (INLA) algorithm to provide fast, approximate Bayesian inference.

METHODS

We simulated two-arm Bayesian adaptive trials with equal randomization that stratified participants into two disease severity states. The analysis used a proportional odds model, fit using INLA. Trials were stopped based on pre-specified posterior probability thresholds for superiority or futility, separately for each state. We calculated the type I error and power across 64 scenarios that varied the probability thresholds and the initial minimum sample size before commencing adaptive analyses. Two designs that maintained a type I error below 5%, a power above 80%, and a feasible mean sample size were evaluated further to determine the optimal design.

RESULTS

Power generally increased as the initial sample size and the futility threshold increased. The chosen design had an initial recruitment of 500 and a superiority threshold of 0.9925, and futility threshold of 0.95. It maintained high power and was likely to reach a conclusion before exceeding a feasible sample size.

CONCLUSIONS

We designed a Bayesian adaptive trial to evaluate novel strategies for ventilation using the INLA algorithm to efficiently evaluate a wide range of designs through simulation.

Heterogeneity in meta-analysis: a comprehensive overview

In recent years, meta-analysis has evolved to a critically important field of Statistics, and has significant applications in Medicine and Health Sciences. In this work we briefly present existing methodologies to conduct meta-analysis along with any discussion and recent developments accompanying them. Undoubtedly, studies brought together in a systematic review will differ in one way or another. This yields a considerable amount of variability, any kind of which may be termed heterogeneity. To this end, reports of meta-analyses commonly present a statistical test of heterogeneity when attempting to establish whether the included studies are indeed similar in terms of the reported output or not. We intend to provide an overview of the topic, discuss the potential sources of heterogeneity commonly met in the literature and provide useful guidelines on how to address this issue and to detect heterogeneity. Moreover, we review the recent developments in the Bayesian approach along with the various graphical tools and statistical software that are currently available to the analyst. In addition, we discuss sensitivity analysis issues and other approaches of understanding the causes of heterogeneity. Finally, we explore heterogeneity in meta-analysis for time to event data in a nutshell, pointing out its unique characteristics.

Bayesian estimation of the measurement of interactions in epidemiological studies

Background

Interaction identification is important in epidemiological studies and can be detected by including a product term in the model. However, as Rothman noted, a product term in exponential models may be regarded as multiplicative rather than additive to better reflect biological interactions. Currently, the additive interaction is largely measured by the relative excess risk due to interaction (RERI), the attributable proportion due to interaction (AP), and the synergy index (S), and confidence intervals are developed via frequentist approaches. However, few studies have focused on the same issue from a Bayesian perspective. The present study aims to provide a Bayesian view of the estimation and credible intervals of the additive interaction measures.

Methods

Bayesian logistic regression was employed, and estimates and credible intervals were calculated from posterior samples of the RERI, AP and S. Since Bayesian inference depends only on posterior samples, it is very easy to apply this method to preventive factors. The validity of the proposed method was verified by comparing the Bayesian method with the delta and bootstrap approaches in simulation studies with example data.

Results

In all the simulation studies, the Bayesian estimates were very close to the corresponding true values. Due to the skewness of the interaction measures, compared with the confidence intervals of the delta method, the credible intervals of the Bayesian approach were more balanced and matched the nominal 95% level. Compared with the bootstrap method, the Bayesian method appeared to be a competitive alternative and fared better when small sample sizes were used.

Conclusions

The proposed Bayesian method is a competitive alternative to other methods. This approach can assist epidemiologists in detecting additive-scale interactions.

A flexible multi-metric Bayesian framework for decision-making in Phase II multi-arm multi-stage studies

We propose a multi-metric flexible Bayesian framework to support efficient interim decision-making in multi-arm multi-stage phase II clinical trials. Multi-arm multi-stage phase II studies increase the efficiency of drug development, but early decisions regarding the futility or desirability of a given arm carry considerable risk since sample sizes are often low and follow-up periods may be short. Further, since intermediate outcomes based on biomarkers of treatment response are rarely perfect surrogates for the primary outcome and different trial stakeholders may have different levels of risk tolerance, a single hypothesis test is insufficient for comprehensively summarizing the state of the collected evidence. We present a Bayesian framework comprised of multiple metrics based on point estimates, uncertainty, and evidence towards desired thresholds (a Target Product Profile) for (1) ranking of arms and (2) comparison of each arm against an internal control. Using a large public-private partnership targeting novel TB arms as a motivating example, we find via simulation study that our multi-metric framework provides sufficient confidence for decision-making with sample sizes as low as 30 patients per arm, even when intermediate outcomes have only moderate correlation with the primary outcome. Our reframing of trial design and the decision-making procedure has been well-received by research partners and is a practical approach to more efficient assessment of novel therapeutics.

Can we nudge to reduce the perioperative low value care? Decision making factors influencing safe practice implementation

PURPOSE OF THE REVIEW

Highlight sources of low-value care (LVC) during the perioperative period help understanding the decision making behind its persistence, the barriers for change, and the potential implementation strategies to reduce it.

RECENT FINDINGS

The behavioural economics science spread of use through aligned strategies or nudge units offer an opportunity to improve success in the LVC reduction.

SUMMARY

LVC, such as unneeded surgeries, or preanaesthesia tests for low-risk surgeries in low-risk patients, is a relevant source of waste and preventable harm, most especially in the perioperative period. Despite the international focus on it, initial efforts to reduce it in the last decade have not clearly shown a sustainable improvement. Understanding the shared decision-making process and the barriers to be expected when tackling LVC is the first step to build the change. Applying a structured strategy based on the behavioural science principles may be the path to increasing high value care in an effective an efficient way. It is time to foster nudge units at different healthcare system levels.

Application of deep learning models for detection of subdural hematoma: a systematic review and meta-analysis

BACKGROUND

This study aimed to investigate the application of deep learning (DL) models for the detection of subdural hematoma (SDH).

METHODS

We conducted a comprehensive search using relevant keywords. Articles extracted were original studies in which sensitivity and/or specificity were reported. Two different approaches of frequentist and Bayesian inference were applied. For quality and risk of bias assessment we used Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2).

RESULTS

We analyzed 22 articles that included 1,997,749 patients. In the first step, the frequentist method showed a pooled sensitivity of 88.8% (95% confidence interval (CI): 83.9% to 92.4%) and a specificity of 97.2% (95% CI 94.6% to 98.6%). In the second step, using Bayesian methods including 11 studies that reported sensitivity and specificity, a sensitivity rate of 86.8% (95% CI: 77.6% to 92.9%) at a specificity level of 86.9% (95% CI: 60.9% to 97.2%) was achieved. The risk of bias assessment was not remarkable using QUADAS-2.

CONCLUSION

DL models might be an appropriate tool for detecting SDHs with a reasonably high sensitivity and specificity.

The impact of omitting confounders in parallel process latent growth curve mediation models: Three sensitivity analysis approaches

Parallel process latent growth curve mediation models (PP-LGCMMs) are frequently used to longitudinally investigate the mediation effects of treatment on the level and change of outcome through the level and change of mediator. An important but often violated assumption in empirical PP-LGCMM analysis is the absence of omitted confounders of the relationships among treatment, mediator, and outcome. In this study, we analytically examined how omitting pretreatment confounders impacts the inference of mediation from the PP-LGCMM. Using the analytical results, we developed three sensitivity analysis approaches for the PP-LGCMM, including the frequentist, Bayesian, and Monte Carlo approaches. The three approaches help investigate different questions regarding the robustness of mediation results from the PP-LGCMM, and handle the uncertainty in the sensitivity parameters differently. Applications of the three sensitivity analyses are illustrated using a real-data example. A user-friendly Shiny web application is developed to conduct the sensitivity analyses.

Validity and Reliability of Short-Term Heart Rate Variability Parameters in Older People in Response to Physical Exercise

BACKGROUND

Currently, and to the best of our knowledge, there is no standardized protocol to measure the effect of low- to moderate-intensity physical exercise on autonomic modulation focused in older people.

AIM

Validate a test-retest short-term exercise protocol for measuring the autonomic response through HRV in older people.

METHODS

A test-retest study design was used. The participants were selected through intentional non-probabilistic sampling. A total of 105 older people (male: 21.9%; female: 78.1%) were recruited from a local community. The assessment protocol evaluated HRV before and immediately after the 2-min step test. It was performed twice on the same day, considering a time of three chronological hours between the two measurements.

RESULTS

The posterior distribution of estimated responses in the Bayesian framework suggests moderate to strong evidence favoring a null effect between measurements. In addition, there was moderate to robust agreement between heart rate variability (HRV) indices and assessments, except for low frequency and very low frequency, which showed weak agreement.

CONCLUSIONS

Our results provide moderate to strong evidence for using HRV to measure cardiac autonomic response to moderate exercise, suggesting that it is sufficiently reliable to show similar results to those shown in this test-retest protocol.

Bayesian networks identify determinants of outcomes following cardiac surgery in a UK population

BACKGROUND

Traditional risk stratification tools do not describe the complex principle determinant relationships that exist amongst pre-operative and peri-operative factors and their influence on cardiac surgical outcomes. This paper reports on the use of Bayesian networks to investigate such outcomes.

METHODS

Data were prospectively collected from 4776 adult patients undergoing cardiac surgery at a single UK institute between April 2012 and May 2019. Machine learning techniques were used to construct Bayesian networks for four key short-term outcomes including death, stroke and renal failure.

RESULTS

Duration of operation was the most important determinant of death irrespective of EuroSCORE. Duration of cardiopulmonary bypass was the most important determinant of re-operation for bleeding. EuroSCORE was predictive of new renal replacement therapy but not mortality.

CONCLUSIONS

Machine-learning algorithms have allowed us to analyse the significance of dynamic processes that occur between pre-operative and peri-operative elements. Length of procedure and duration of cardiopulmonary bypass predicted mortality and morbidity in patients undergoing cardiac surgery in the UK. Bayesian networks can be used to explore potential principle determinant mechanisms underlying outcomes and be used to help develop future risk models.

A Bayesian network model for prediction of low or failed fertilization in assisted reproductive technology based on a large clinical real-world data

STUDY QUESTION

To construct prediction models based on the Bayesian network (BN) learning method for the probability of fertilization failure (including low fertilization rate [LRF] and total fertilization failure [TFF]) in assisted reproductive technology (ART) treatment. A BN model was developed to predict TFF/LFR. The model showed relatively high calibration in external validation, which could facilitate the identification of risk factors for fertilization disorders and improve the efficiency of in vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) treatment.

WHAT IS KNOWN ALREADY

The prediction of TFF/LFR is very complex. Although some studies attempted to construct prediction models for TFF/LRF, most of the reported models were based on limited variables and traditional regression-based models, which are unsuitable for analyzing real-world clinical data. Therefore, none of the reported models have been widely used in routine clinical practice. To date, BN modeling analysis is a prominent and increasingly popular machine learning method that is powerful in dealing with dynamic and complex real-world data.

STUDY DESIGN, SIZE, DURATION

A retrospective study was performed with 106,640 fresh embryo IVF/ICSI cycles from 2009 to 2019 in one of China's largest reproductive health centers.

PARTICIPANTS/MATERIALS, SETTING, METHODS

A total of 106, 640 cycles were included in this study, including 97,102 controls, 4,339 LFR cases, and 5,199 TFF cases. Twenty-four predictors were initially included, including 13 female-related variables, five male-related variables, and six variables related to IVF/ICSI treatment. BN modeling analysis with tenfold cross-validation was performed to construct the predictive model for TFF/LFR. The receiver operating characteristic (ROC) curves and the corresponding area under the curves (AUCs) were used to evaluate the performance of the BN model.

MAIN RESULTS AND THE ROLE OF CHANCE

All twenty-four predictors were first organized into seven hierarchical layers in a theoretical BN model, according to prior knowledge from previous literature and clinical practice. A machine-learning BN model was generated based on real-world clinical data, containing a total of eighteen predictors, of which the infertility type, ART method, and number of retrieved oocytes directly influence the probabilities of LFR/TFF. The prediction accuracy of the BN model was 91.7%. The AUC of the TFF versus control groups was 0.779 (95% CI: 0.766-0.791), with a sensitivity of 71.2% and specificity of 70.1%; the AUC of of TFF versus LFR groups was 0.807 (95% CI: 0.790-0.824), with a sensitivity of 49.0% and specificity of 99.0%.

LIMITATIONS, REASON FOR CAUTION

First, our study was based on clinical data from a single center, and the results of this study should be further verified by external data. In addition, some critical data (e.g., the detailed IVF laboratory parameters of the sperm and oocytes used for insemination) were not available in this study, which should be given full consideration when further improving the performance of the BN model.

WIDER IMPLICATIONS OF THE FINDINGS

Based on extensive clinical real-world data, we developed a BN model to predict the probabilities of fertilization failures in ART, which provides new clues for clinical decision-making support for clinicians in formulating personalized treatment plans and further improving ART treatment outcomes.

STUDY FUNDING/COMPETING INTEREST(S)

Dr. Y. Wang was supported by grants from the Beijing Municipal Science & Technology Commission (Z191100006619086). We declare that there are no conflicts of interest.

TRIAL REGISTRATION NUMBER

N/A.

Setting course for a translational pharmacology and a predictive toxicology based on the numerical probability of clinical relevance

For a significant share of the chemicals, current bioassays mispredicted the outcomes in the reference methods they simulate. For any drug or chemical, and depending on the regulatory or corporate situation, three different approaches calculate the numerical probability by which agreement (or discrepancy) can be statistically expected between (1) the result of a predictive bioassay, and (2) the outcome on its reference method. If such concordance is expected with enough confidence based on a sufficient percentage probability, then specific results from that bioassay can be considered as correctly predictive. The statistical approaches analyzed in this article assist in valuable tasks, including (1) a better translation of the clinical relevance (or insignificance) of specific preclinical findings; (2) waiving unnecessary animal testing (or any other unpredictive testing; e.g., a given in vitro bioassay), and (3) in advancing only the most promising candidates in the pharmaceutical, pesticide, or chemical development process.

A Bayesian Approach to Extracting Kinetic Information from Artificial Enzymatic Networks

In order to create artificial enzymatic networks capable of increasingly complex behavior, an improved methodology in understanding and controlling the kinetics of these networks is needed. Here, we introduce a Bayesian analysis method allowing for the accurate inference of enzyme kinetic parameters and determination of most likely reaction mechanisms, by combining data from different experiments and network topologies in a single probabilistic analysis framework. This Bayesian approach explicitly allows us to continuously improve our parameter estimates and behavior predictions by iteratively adding new data to our models, while automatically taking into account uncertainties introduced by the experimental setups or the chemical processes in general. We demonstrate the potential of this approach by characterizing systems of enzymes compartmentalized in beads inside flow reactors. The methods we introduce here provide a new approach to the design of increasingly complex artificial enzymatic networks, making the design of such networks more efficient, and robust against the accumulation of experimental errors.

How to Train Novices in Bayesian Reasoning

Bayesian Reasoning is both a fundamental idea of probability and a key model in applied sciences for evaluating situations of uncertainty. Bayesian Reasoning may be defined as the dealing with, and understanding of, Bayesian situations. This includes various aspects such as calculating a conditional probability (performance), assessing the effects of changes to the parameters of a formula on the result (covariation) and adequately interpreting and explaining the results of a formula (communication). Bayesian Reasoning is crucial in several non-mathematical disciplines such as medicine and law. However, even experts from these domains struggle to reason in a Bayesian manner. Therefore, it is desirable to develop a training course for this specific audience regarding the different aspects of Bayesian Reasoning. In this paper, we present an evidence-based development of such training courses by considering relevant prior research on successful strategies for Bayesian Reasoning (e.g., natural frequencies and adequate visualizations) and on the 4C/ID model as a promising instructional approach. The results of a formative evaluation are described, which show that students from the target audience (i.e., medicine or law) increased their Bayesian Reasoning skills and found taking part in the training courses to be relevant and fruitful for their professional expertise.

Integrating expert knowledge for dementia risk prediction in individuals with mild cognitive impairment (MCI): a study protocol

INTRODUCTION

To date, there is no broadly accepted dementia risk score for use in individuals with mild cognitive impairment (MCI), partly because there are few large datasets available for model development. When evidence is limited, the knowledge and experience of experts becomes more crucial for risk stratification and providing MCI patients with prognosis. Structured expert elicitation (SEE) includes formal methods to quantify experts' beliefs and help experts to express their beliefs in a quantitative form, reducing biases in the process. This study proposes to (1) assess experts' beliefs about important predictors for 3-year dementia risk in persons with MCI through SEE methodology and (2) to integrate expert knowledge and patient data to derive dementia risk scores in persons with MCI using a Bayesian approach.

METHODS AND ANALYSIS

This study will use a combination of SEE methodology, prospectively collected clinical data, and statistical modelling to derive a dementia risk score in persons with MCI . Clinical expert knowledge will be quantified using SEE methodology that involves the selection and training of the experts, administration of questionnaire for eliciting expert knowledge, discussion meetings and results aggregation. Patient data from the Prospective Registry for Persons with Memory Symptoms of the Cognitive Neurosciences Clinic at the University of Calgary; the Alzheimer's Disease Neuroimaging Initiative; and the National Alzheimer's Coordinating Center's Uniform Data Set will be used for model training and validation. Bayesian Cox models will be used to incorporate patient data and elicited data to predict 3-year dementia risk.

DISCUSSION

This study will develop a robust dementia risk score that incorporates clinician expert knowledge with patient data for accurate risk stratification, prognosis and management of dementia.

External validation of Machine Learning models for COVID-19 detection based on Complete Blood Count

Purpose

The rRT-PCR for COVID-19 diagnosis is affected by long turnaround time, potential shortage of reagents, high false-negative rates and high costs. Routine hematochemical tests are a faster and less expensive alternative for diagnosis. Thus, Machine Learning (ML) has been applied to hematological parameters to develop diagnostic tools and help clinicians in promptly managing positive patients. However, few ML models have been externally validated, making their real-world applicability unclear.

Methods

We externally validate 6 state-of-the-art diagnostic ML models, based on Complete Blood Count (CBC) and trained on a dataset encompassing 816 COVID-19 positive cases. The external validation was performed based on two datasets, collected at two different hospitals in northern Italy and encompassing 163 and 104 COVID-19 positive cases, in terms of both error rate and calibration.

Results and Conclusion

We report an average AUC of 95% and average Brier score of 0.11, out-performing existing ML methods, and showing good cross-site transportability. The best performing model (SVM) reported an average AUC of 97.5% (Sensitivity: 87.5%, Specificity: 94%), comparable with the performance of RT-PCR, and was also the best calibrated. The validated models can be useful in the early identification of potential COVID-19 patients, due to the rapid availability of CBC exams, and in multiple test settings.

BIKE: Dietary Exposure Model for Foodborne Microbiological and Chemical Hazards

BIKE is a Bayesian dietary exposure assessment model for microbiological and chemical hazards. A graphical user interface was developed for running the model and inspecting the results. It is based on connected Bayesian hierarchical models, utilizing OpenBUGS and R in tandem. According to occurrence and consumption data given as inputs, a specific BUGS code is automatically written for running the Bayesian model in the background. The user interface is based on shiny app. Chronic and acute exposures are estimated for chemical and microbiological hazards, respectively. Uncertainty and variability in exposures are visualized, and a few optional model structures can be used. Simulated synthetic data are provided with BIKE for an example, resembling real occurrence and consumption data. BIKE is open source and available from github.

Approximate Measurement Invariance of Willingness to Sacrifice for the Environment Across 30 Countries: The Importance of Prior Distributions and Their Visualization

Nationwide opinions and international attitudes toward climate and environmental change are receiving increasing attention in both scientific and political communities. An often used way to measure these attitudes is by large-scale social surveys. However, the assumption for a valid country comparison, measurement invariance, is often not met, especially when a large number of countries are being compared. This makes a ranking of countries by the mean of a latent variable potentially unstable, and may lead to untrustworthy conclusions. Recently, more liberal approaches to assessing measurement invariance have been proposed, such as the alignment method in combination with Bayesian approximate measurement invariance. However, the effect of prior variances on the assessment procedure and substantive conclusions is often not well understood. In this article, we tested for measurement invariance of the latent variable "willingness to sacrifice for the environment" using Maximum Likelihood Multigroup Confirmatory Factor Analysis and Bayesian approximate measurement invariance, both with and without alignment optimization. For the Bayesian models, we used multiple priors to assess the impact on the rank order stability of countries. The results are visualized in such a way that the effect of different prior variances and models on group means and rankings becomes clear. We show that even when models appear to be a good fit to the data, there might still be an unwanted impact on the rank ordering of countries. From the results, we can conclude that people in Switzerland and South Korea are most motivated to sacrifice for the environment, while people in Latvia are less motivated to sacrifice for the environment.

Bayesian Methods for Meta-Analyses of Binary Outcomes: Implementations, Examples, and Impact of Priors

Bayesian methods are an important set of tools for performing meta-analyses. They avoid some potentially unrealistic assumptions that are required by conventional frequentist methods. More importantly, meta-analysts can incorporate prior information from many sources, including experts’ opinions and prior meta-analyses. Nevertheless, Bayesian methods are used less frequently than conventional frequentist methods, primarily because of the need for nontrivial statistical coding, while frequentist approaches can be implemented via many user-friendly software packages. This article aims at providing a practical review of implementations for Bayesian meta-analyses with various prior distributions. We present Bayesian methods for meta-analyses with the focus on odds ratio for binary outcomes. We summarize various commonly used prior distribution choices for the between-studies heterogeneity variance, a critical parameter in meta-analyses. They include the inverse-gamma, uniform, and half-normal distributions, as well as evidence-based informative log-normal priors. Five real-world examples are presented to illustrate their performance. We provide all of the statistical code for future use by practitioners. Under certain circumstances, Bayesian methods can produce markedly different results from those by frequentist methods, including a change in decision on statistical significance. When data information is limited, the choice of priors may have a large impact on meta-analytic results, in which case sensitivity analyses are recommended. Moreover, the algorithm for implementing Bayesian analyses may not converge for extremely sparse data; caution is needed in interpreting respective results. As such, convergence should be routinely examined. When select statistical assumptions that are made by conventional frequentist methods are violated, Bayesian methods provide a reliable alternative to perform a meta-analysis.

Handling of uncertainty in medical data using machine learning and probability theory techniques: a review of 30 years (1991-2020)

Understanding the data and reaching accurate conclusions are of paramount importance in the present era of big data. Machine learning and probability theory methods have been widely used for this purpose in various fields. One critically important yet less explored aspect is capturing and analyzing uncertainties in the data and model. Proper quantification of uncertainty helps to provide valuable information to obtain accurate diagnosis. This paper reviewed related studies conducted in the last 30 years (from 1991 to 2020) in handling uncertainties in medical data using probability theory and machine learning techniques. Medical data is more prone to uncertainty due to the presence of noise in the data. So, it is very important to have clean medical data without any noise to get accurate diagnosis. The sources of noise in the medical data need to be known to address this issue. Based on the medical data obtained by the physician, diagnosis of disease, and treatment plan are prescribed. Hence, the uncertainty is growing in healthcare and there is limited knowledge to address these problems. Our findings indicate that there are few challenges to be addressed in handling the uncertainty in medical raw data and new models. In this work, we have summarized various methods employed to overcome this problem. Nowadays, various novel deep learning techniques have been proposed to deal with such uncertainties and improve the performance in decision making.

COVID-19-induced hyperinflammation, immunosuppression, recovery and survival: how causal inference may help draw robust conclusions

BACKGROUND

The CHIC study (COVID-19 High-intensity Immunosuppression in Cytokine storm syndrome) is a quasi-experimental treatment study exploring immunosuppressive treatment versus supportive treatment only in patients with COVID-19 with life-threatening hyperinflammation. Causal inference provides a means of investigating causality in non-randomised experiments. Here we report 14-day improvement as well as 30-day and 90-day mortality.

PATIENTS AND METHODS

The first 86 patients (period 1) received optimal supportive care only; the second 86 patients (period 2) received methylprednisolone and (if necessary) tocilizumab, in addition to optimal supportive care. The main outcomes were 14-day clinical improvement and 30-day and 90-day survival. An 80% decline in C reactive protein (CRP) was recorded on or before day 13 (CRP >100 mg/L was an inclusion criterion). Non-linear mediation analysis was performed to decompose CRP-mediated effects of immunosuppression (defined as natural indirect effects) and non-CRP-mediated effects attributable to natural prognostic differences between periods (defined as natural direct effects).

RESULTS

The natural direct (non-CRP-mediated) effects for period 2 versus period 1 showed an OR of 1.38 (38% better) for 14-day improvement and an OR of 1.16 (16% better) for 30-day and 90-day survival. The natural indirect (CRP-mediated) effects for period 2 showed an OR of 2.27 (127% better) for 14-day improvement, an OR of 1.60 (60% better) for 30-day survival and an OR of 1.49 (49% better) for 90-day survival. The number needed to treat was 5 for 14-day improvement, 9 for survival on day 30, and 10 for survival on day 90.

CONCLUSION

Causal inference with non-linear mediation analysis further substantiates the claim that a brief but intensive treatment with immunosuppressants in patients with COVID-19 and systemic hyperinflammation adds to rapid recovery and saves lives. Causal inference is an alternative to conventional trial analysis, when randomised controlled trials are considered unethical, unfeasible or impracticable.

COVID-19-induced hyperinflammation, immunosuppression, recovery and survival: how causal inference may help draw robust conclusions

BACKGROUND

The CHIC study (COVID-19 High-intensity Immunosuppression in Cytokine storm syndrome) is a quasi-experimental treatment study exploring immunosuppressive treatment versus supportive treatment only in patients with COVID-19 with life-threatening hyperinflammation. Causal inference provides a means of investigating causality in non-randomised experiments. Here we report 14-day improvement as well as 30-day and 90-day mortality.

PATIENTS AND METHODS

The first 86 patients (period 1) received optimal supportive care only; the second 86 patients (period 2) received methylprednisolone and (if necessary) tocilizumab, in addition to optimal supportive care. The main outcomes were 14-day clinical improvement and 30-day and 90-day survival. An 80% decline in C reactive protein (CRP) was recorded on or before day 13 (CRP >100 mg/L was an inclusion criterion). Non-linear mediation analysis was performed to decompose CRP-mediated effects of immunosuppression (defined as natural indirect effects) and non-CRP-mediated effects attributable to natural prognostic differences between periods (defined as natural direct effects).

RESULTS

The natural direct (non-CRP-mediated) effects for period 2 versus period 1 showed an OR of 1.38 (38% better) for 14-day improvement and an OR of 1.16 (16% better) for 30-day and 90-day survival. The natural indirect (CRP-mediated) effects for period 2 showed an OR of 2.27 (127% better) for 14-day improvement, an OR of 1.60 (60% better) for 30-day survival and an OR of 1.49 (49% better) for 90-day survival. The number needed to treat was 5 for 14-day improvement, 9 for survival on day 30, and 10 for survival on day 90.

CONCLUSION

Causal inference with non-linear mediation analysis further substantiates the claim that a brief but intensive treatment with immunosuppressants in patients with COVID-19 and systemic hyperinflammation adds to rapid recovery and saves lives. Causal inference is an alternative to conventional trial analysis, when randomised controlled trials are considered unethical, unfeasible or impracticable.

An Early Stage Researcher's Primer on Systems Medicine Terminology

Background: Systems Medicine is a novel approach to medicine, that is, an interdisciplinary field that considers the human body as a system, composed of multiple parts and of complex relationships at multiple levels, and further integrated into an environment. Exploring Systems Medicine implies understanding and combining concepts coming from diametral different fields, including medicine, biology, statistics, modeling and simulation, and data science. Such heterogeneity leads to semantic issues, which may slow down implementation and fruitful interaction between these highly diverse fields. Methods: In this review, we collect and explain more than100 terms related to Systems Medicine. These include both modeling and data science terms and basic systems medicine terms, along with some synthetic definitions, examples of applications, and lists of relevant references. Results: This glossary aims at being a first aid kit for the Systems Medicine researcher facing an unfamiliar term, where he/she can get a first understanding of them, and, more importantly, examples and references for digging into the topic.

The Bayesian Design of Adaptive Clinical Trials

This paper presents a brief overview of the recent literature on adaptive design of clinical trials from a Bayesian perspective for statistically not so sophisticated readers. Adaptive designs are attracting a keen interest in several disciplines, from a theoretical viewpoint and also—potentially—from a practical one, and Bayesian adaptive designs, in particular, have raised high expectations in clinical trials. The main conceptual tools are highlighted here, with a mention of several trial designs proposed in the literature that use these methods, including some of the registered Bayesian adaptive trials to this date. This review aims at complementing the existing ones on this topic, pointing at further interesting reading material.

Optimization of infliximab therapy in inflammatory bowel disease using a dashboard approach-an Indian experience

PURPOSE

Infliximab (IFX) therapy in inflammatory bowel disease (IBD) is associated with loss of response in half the patients, due to complex pharmacokinetic and immunological factors. Dashboard's Bayesian algorithms use information from model and individual multivariate determinants of IFX concentration and can predict dose and dosing interval.

AIM

To compare measured IFX concentrations in our laboratory with values predicted by iDose dashboard system and report its efficacy in managing patients not responding to conventional dosing schedule.

METHOD

Clinical history, demographic details, and laboratory findings such as albumin and C-reactive protein (CRP) data of IBD patients (n = 30; median age 23 years (IQR: 14.25 - 33.5)) referred for IFX drug monitoring in our laboratory from November 2017 to November 2019 were entered in iDose software. The IFX concentration predicted by iDose based on this information was compared with that measured in our laboratory. In addition, a prospective dashboard-guided dosing was prescribed in 11 of these 30 patients not responding to conventional dosing and was followed to assess their clinical outcome.

RESULT

IFX monitoring in our 30 patients had shown therapeutic concentration in 12, supratherapeutic in 2 and subtherapeutic concentration in 16 patients. The iDose predicted concentration showed concordance in 21 of these 30 patients. Of 11 patients managed with iDose-assisted prospective dosing, 8 achieved clinical remission, 2 showed partial response, and one developed antibodies.

CONCLUSION

Retrospective data analysis showed concordance between laboratory measured and iDose-predicted IFX level in 70% of patients. iDose-assisted management achieved clinical remission and cost reduction.

A Review of Capture-recapture Methods and Its Possibilities in Ophthalmology and Vision Sciences

Epidemiological information is expected to be used to develop key aspects of eye care such as to control and minimise the impact of diseases, to allocate resources, to monitor public health actions, to determine the best treatment options and to forecast the consequence of diseases in populations. Epidemiological studies are expected to provide information about the prevalence and/or incidence of eye diseases or conditions. To determine prevalence is necessary to perform a cross-sectional screening of the population at risk to ascertain the number of cases. The aim of this review is to describe and evaluate capture-recapture methods (or models) to ascertaining the number of individuals with a disease (e.g. diabetic retinopathy) or condition (e.g. vision impairment) in the population. The review covers the fundamental aspects of capture-recapture methods that would enable non-experts in epidemiology to use it in ophthalmic studies. The review provides information about theoretical aspects of the method with examples of studies in ophthalmology in which it has been used. We also provide a problem/solution approach for limitations arising from the lists obtained from registers or other reliable sources. We concluded that capture-recapture models can be considered reliable to estimate the total number of cases with eye conditions using incomplete information from registers. Accordingly, the method may be used to maintain updated epidemiological information about eye conditions helping to tackle the lack of surveillance information in many regions of the globe.

Risk Factors for Acute Exacerbations in Elderly Asthma: What Makes Asthma in Older Adults Distinctive?

Purpose

Asthma in the elderly (EA; ≥ 65 years of age) is increasing, adding a heavy socioeconomic burden to the healthcare system. However, little is known about risk factors associated with acute exacerbations in EA patients. The objective of this study was to investigate risk factors for acute exacerbation in EA compared to non-elderly asthma (NEA).

Methods

We combined data from 3 adult asthma cohorts under a unified protocol and database. Asthmatic patients with regular follow-up during a 1-year period were selected from the cohorts to identify the risk factors predicting acute exacerbations in EA compared to NEA.

Results

We selected a total of 1,086 patients from the merged cohort. During the observation period, 503 and 583 patients were assigned to the EA and NEA groups, respectively. The exacerbation rate was 31.0% in the EA and 33.2% in the NEA group. Multivariate logistic regression analysis revealed fixed airway obstruction, chronic rhinosinusitis (CRS), and male sex as independent risk factors for exacerbation in the EA group. In the NEA group, exacerbation increased along with an increase in eosinophil count. Bayesian analysis of the interactions among clinical factors revealed that forced expiratory volume in 1 second/forced vital capacity was directly related to exacerbation in the EA group, and eosinophil count was related to exacerbation in the NEA group.

Conclusions

We suggest that fixed airway obstruction and CRS as the important clinical factors predicting acute exacerbations in EA, whereas in NEA, eosinophil count was the strong predictor of exacerbation.

Machine Learning and Artificial Intelligence in Neurocritical Care: a Specialty-Wide Disruptive Transformation or a Strategy for Success

PURPOSE OF REVIEW

Neurocritical care combines the complexity of both medical and surgical disease states with the inherent limitations of assessing patients with neurologic injury. Artificial intelligence (AI) has garnered interest in the basic management of these complicated patients as data collection becomes increasingly automated.

RECENT FINDINGS

In this opinion article, we highlight the potential AI has in aiding the clinician in several aspects of neurocritical care, particularly in monitoring and managing intracranial pressure, seizures, hemodynamics, and ventilation. The model-based method and data-driven method are currently the two major AI methods for analyzing critical care data. Both are able to analyze the vast quantities of patient data that are accumulated in the neurocritical care unit. AI has the potential to reduce healthcare costs, minimize delays in patient management, and reduce medical errors. However, these systems are an aid to, not a replacement for, the clinician's judgment.

Contrast enhancement on 100- and 120 kVp hepatic CT scans at thin adults in a retrospective cohort study: Bayesian inference of the optimal enhancement probability

PURPOSE

To assess the probability of achieving optimal contrast enhancement in 100 kVp and 120 kVp-protocol on hepatic computed tomography (CT) scans.

MATERIALS AND METHODS

We enrolled 200 patients in a retrospective cohort study. Hundred patients were scanned with 120 kVp setting, and other 100 patients were scanned with 100 kVp setting. We measured the CT number in the abdominal aorta and hepatic parenchyma on unenhanced scans and hepatic arterial phase (HAP)-, and portal venous phase (PVP). The aortic enhancement at HAP and the hepatic parenchymal enhancement at PVP were compared between the two scanning protocols. Bayesian inference was used to assess the probability of achieving optimal contrast enhancement in each protocol.

RESULTS

The Bayesian analysis indicated that when 100 kVp-rotocol was used, the probability of achieving optimal aortic enhancement (>280 HU) was 98.8% ± 0.6%, whereas it was 88.7% ± 2.5% when 120 kVp-protocol was used. Also, the probability of achieving optimal hepatic parenchymal enhancement (>50 HU) was 95.3% ± 1.5%, whereas it was 64.7% ± 3.8% when 120 kVp-protocol was used.

CONCLUSION

Bayesian inference suggested that the post-test probability of optimal contrast enhancement at hepatic dynamic CT was lower under the 120 kVp than the 100 kVp-protocol.

Artificial intelligence in neurocritical care

BACKGROUND

Neurocritical care combines the management of extremely complex disease states with the inherent limitations of clinically assessing patients with brain injury. As the management of neurocritical care patients can be immensely complicated, the automation of data-collection and basic management by artificial intelligence systems have garnered interest.

METHODS

In this opinion article, we highlight the potential artificial intelligence has in monitoring and managing several aspects of neurocritical care, specifically intracranial pressure, seizure monitoring, blood pressure, and ventilation.

RESULTS

The two major AI methods of analytical technique currently exist for analyzing critical care data: the model-based method and data driven method. Both of these methods have demonstrated an ability to analyze vast quantities of patient data, and we highlight the ways in which these modalities of artificial intelligence might one day play a role in neurocritical care.

CONCLUSIONS

While none of these artificial intelligence systems are meant to replace the clinician's judgment, these systems have the potential to reduce healthcare costs and errors or delays in medical management.

Incremental clinical utility of continuous performance tests in childhood ADHD - an evidence-based assessment approach

Despite extensive research on attention deficit hyperactivity disorder (ADHD), there are still uncertainties regarding the clinical utility of different ADHD assessment methods. This study aimed to examine the incremental clinical utility of Conners’ continuous performance test (CPT) II and QbTest in diagnostic assessments and treatment monitoring of attention deficit hyperactivity disorder (ADHD). Retrospective data from child and adolescent psychiatric records of two populations were studied. The diagnostic clinical utility of Conners’ CPT II and QbTest was analysed using receiver operator characteristics (ROC) and post‐test probability in 80 children with and 38 without ADHD. Dose titrations of central stimulants in 56 children with ADHD were evaluated using QbTest and the Swanson, Nolan, Pelham, version IV (SNAP‐IV) scale. Conners’ CPT II, but not QbTest, had incremental clinical utility in diagnostic assessment of children with ADHD when teacher and parent ratings were inconclusive. QbTest proved useful in titration of central stimulant treatment when parent ratings were inconclusive. Continuous performance tests were found to be clinically useful when rating scales were inconclusive.

A Bayesian hierarchical model for demand curve analysis

Drug self-administration experiments are a frequently used approach to assess the abuse liability and reinforcing property of a compound. It has been used to assess the abuse liabilities of various substances such as psychomotor stimulants and hallucinogens, food, nicotine, and alcohol. The demand curve generated from a self-administration study describes how demand of a drug or non-drug reinforcer varies as a function of price. With the approval of the 2009 Family Smoking Prevention and Tobacco Control Act, demand curve analysis provides crucial evidence to inform the US Food and Drug Administration's policy on tobacco regulation because it produces several important quantitative measurements to assess the reinforcing strength of nicotine. The conventional approach popularly used to analyze the demand curve data is individual-specific non-linear least square regression. The non-linear least square approach sets out to minimize the residual sum of squares for each subject in the dataset; however, this one-subject-at-a-time approach does not allow for the estimation of between- and within-subject variability in a unified model framework. In this paper, we review the existing approaches to analyze the demand curve data, non-linear least square regression, and the mixed effects regression and propose a new Bayesian hierarchical model. We conduct simulation analyses to compare the performance of these three approaches and illustrate the proposed approaches in a case study of nicotine self-administration in rats. We present simulation results and discuss the benefits of using the proposed approaches.

A Bayesian hierarchical model for demand curve analysis

Drug self-administration experiments are a frequently used approach to assessing the abuse liability and reinforcing property of a compound. It has been used to assess the abuse liabilities of various substances such as psychomotor stimulants and hallucinogens, food, nicotine, and alcohol. The demand curve generated from a self-administration study describes how demand of a drug or non-drug reinforcer varies as a function of price. With the approval of the 2009 Family Smoking Prevention and Tobacco Control Act, demand curve analysis provides crucial evidence to inform the US Food and Drug Administration's policy on tobacco regulation, because it produces several important quantitative measurements to assess the reinforcing strength of nicotine. The conventional approach popularly used to analyze the demand curve data is individual-specific non-linear least square regression. The non-linear least square approach sets out to minimize the residual sum of squares for each subject in the dataset; however, this one-subject-at-a-time approach does not allow for the estimation of between- and within-subject variability in a unified model framework. In this paper, we review the existing approaches to analyze the demand curve data, non-linear least square regression, and the mixed effects regression and propose a new Bayesian hierarchical model. We conduct simulation analyses to compare the performance of these three approaches and illustrate the proposed approaches in a case study of nicotine self-administration in rats. We present simulation results and discuss the benefits of using the proposed approaches.

Bayesian PTSD-Trajectory Analysis with Informed Priors Based on a Systematic Literature Search and Expert Elicitation

There is a recent increase in interest of Bayesian analysis. However, little effort has been made thus far to directly incorporate background knowledge via the prior distribution into the analyses. This process might be especially useful in the context of latent growth mixture modeling when one or more of the latent groups are expected to be relatively small due to what we refer to as limited data. We argue that the use of Bayesian statistics has great advantages in limited data situations, but only if background knowledge can be incorporated into the analysis via prior distributions. We highlight these advantages through a data set including patients with burn injuries and analyze trajectories of posttraumatic stress symptoms using the Bayesian framework following the steps of the WAMBS-checklist. In the included example, we illustrate how to obtain background information using previous literature based on a systematic literature search and by using expert knowledge. Finally, we show how to translate this knowledge into prior distributions and we illustrate the importance of conducting a prior sensitivity analysis. Although our example is from the trauma field, the techniques we illustrate can be applied to any field.

Appropriateness vs value: Echocardiography in primary care

BACKGROUND

Despite efforts targeting the growth of healthcare spending within the United States, the current increase in expenditures remains a widespread systemic issue. The overuse of healthcare testing has previously been identified as a modifiable contributing factor. One such test, echocardiography, has seen a continuous increase in its rate of use. This test is frequently ordered by primary-care physicians.

HYPOTHESIS

In the setting of a low likelihood of disease, echocardiography does not substantially change cardiac therapy, even if appropriately ordered.

METHODS

We randomly identified 500 patients who received an echocardiogram ordered by a primary-care physician between January 1, 2014, and December 31, 2014. Of these, 239 patient charts were reviewed and the following extracted: primary indication for the test, echocardiogram results, and changes in patient medical management. In addition, appropriateness of the test was assessed using the appropriate use criteria guidelines for echocardiography.

RESULTS

Nearly 97% of the studies within the ambulatory primary-care setting were appropriately ordered according to the appropriate use criteria. Among the 239 patients studied, only 52 had abnormalities and only 6 (2.5%) experienced a change in management that corresponded with the initial suspected diagnosis and echocardiographic findings.

CONCLUSIONS

To ensure the greatest value and optimize use of diagnostic testing, it may be necessary to develop a more comprehensive set of guidelines to assist clinicians to readily identify patient populations at low, moderate, and high risk for the presence of disease and provide educational interventions, including feedback regarding individual ordering behaviors.