Dealing with time-dependent exposures and confounding when defining and estimating attributable fractions-Revisiting estimands and estimators.

The population-attributable fraction (PAF) is commonly interpreted as the proportion of events that can be ascribed to a certain exposure in a certain population. Its estimation is sensitive to common forms of time-dependent bias in the face of a time-dependent exposure. Predominant estimation approaches based on multistate modeling fail to fully eliminate such bias and, as a result, do not permit a causal interpretation, even in the absence of confounding. While recently proposed multistate modeling approaches can successfully eliminate residual time-dependent bias, and moreover succeed to adjust for time-dependent confounding by means of inverse probability of censoring weighting, inadequate application, and misinterpretation prevails in the medical literature. In this paper, we therefore revisit recent work on previously proposed PAF estimands and estimators in settings with time-dependent exposures and competing events and extend this work in several ways. First, we critically revisit the interpretation and applied terminology of these estimands. Second, we further formalize the assumptions under which a causally interpretable PAF estimand can be identified and provide analogous weighting-based representations of the identifying functionals of other proposed estimands. This representation aims to enhance the applied statistician's understanding of different sources of bias that may arise when the aim is to obtain a valid estimate of a causally interpretable PAF. To illustrate and compare these representations, we present a real-life application to observational data from the Ghent University Hospital ICUs to estimate the fraction of ICU deaths attributable to hospital-acquired infections.

On optimal timing of antenatal corticosteroids: time to reformulate the question.

Administration of antenatal corticosteroids (ACS) for accelerating foetal lung maturation in threatened preterm birth is one of the cornerstones of prevention of neonatal mortality and morbidity. To identify the optimal timing of ACS administration, most studies have compared subgroups based on treatment-to-delivery intervals. Such subgroup analysis of the first placebo-controlled randomised controlled trial indicated that a one to seven day interval between ACS administration and birth resulted in the lowest rates of neonatal respiratory distress syndrome. This efficacy window was largely confirmed by a series of subgroup analyses of subsequent trials and observational studies and strongly influenced obstetric management. However, these subgroup analyses suffer from a methodological flaw that often seems to be overlooked and potentially has important consequences for drawing valid conclusions. In this commentary, we point out that studies comparing treatment outcomes between subgroups that are retrospectively identified at birth (i.e. after randomisation) may not only be plagued by post-randomisation confounding bias but, more importantly, may not adequately inform decision making before birth, when the projected duration of the interval is still unknown. We suggest two more formal interpretations of these subgroup analyses, using a counterfactual framework for causal inference, and demonstrate that each of these interpretations can be linked to a different hypothetical trial. However, given the infeasibility of these trials, we argue that none of these rescue interpretations are helpful for clinical decision making. As a result, guidelines based on these subgroup analyses may have led to suboptimal clinical practice. As an alternative to these flawed subgroup analyses, we suggest a more principled approach that clearly formulates the question about optimal timing of ACS treatment in terms of the protocol of a future randomised study. Even if this 'target trial' would never be conducted, its protocol may still provide important guidance to avoid repeating common design flaws when conducting observational 'real world' studies using statistical methods for causal inference.

The population-attributable fraction for time-to-event data.

BACKGROUND: Even though the population-attributable fraction (PAF) is a well-established metric, it is often incorrectly estimated or interpreted not only in clinical application, but also in statistical research articles. The risk of bias is especially high in more complex time-to-event data settings. METHODS: We explain how the PAF can be defined, identified and estimated in time-to-event settings with competing risks and time-dependent exposures. By using multi-state methodology and inverse probability weighting, we demonstrate how to reduce or completely avoid severe types of biases including competing risks bias, immortal time bias and confounding due to both baseline and time-varying patient characteristics. RESULTS: The method is exemplarily applied to a real data set. Moreover, we estimate the number of deaths that were attributable to ventilator-associated pneumonia in France in the year 2016. The example demonstrates how, under certain simplifying assumptions, PAF estimates can be extrapolated to a target population of interest. CONCLUSIONS: Defining and estimating the PAF in advanced time-to-event settings within a framework that unifies causal and multi-state modelling enables to tackle common sources of bias and allows straightforward implementation with standard software packages.

Organization, feasibility and patient appreciation of a follow-up consultation in surgical critically ill patients with favorable baseline quality of life and prolonged ICU-stay: a pilot study.

OBJECTIVES: Intensive care unit (ICU) survivors are often left with impairments in physical, mental and cognitive functioning (Post-Intensive Care Syndrome (PICS)). We evaluated the organization, the feasibility for caregivers and patients and the patients' appreciation of a post-ICU consultation aiming to detect these PICS-symptoms. METHODS: A single-center prospective observational pilot study was conducted during an 18 month-period in the surgical ICU of a tertiary care hospital. Consecutive adult patients with an ICU-stay of ≥8 days and a favorable baseline quality of life (utility index ≥0.6 on EQ-5D-3 L) were eligible for inclusion. A post-ICU follow-up consultation consisting of a structured interview was scheduled 3 months after hospital discharge. Characteristics of the consultation (CG) and no consultation group (NCG) were compared. P-values <0.05 were considered significant. RESULTS: Of 133 eligible patients, 85 (64%) consented for the study and 42 (49%) attended the consultation. A total of 148 phone calls were made to schedule the consultations. Consultations took a median of 68 (61-74) minutes. Compared to CG-patients, NCG-patients were more often discharged to a care facility (P = 0.003) and had more problems with mobility (P = 0.014), self-care (P < 0.001) and usual activities (P = 0.005) after 3 months. At least one PICS-related problem was documented in all patients in the CG and NCG. Thirty-four CG-patients (81%) appreciated the initiative. CONCLUSION: Organizing an ICU-follow-up consultation was difficult and feasibility was low, but most attending patients appreciated the initiative. Better developed structures for ICU-follow-up are needed in view of the high number of PICS-related problems documented.

Timing of dialysis in acute kidney injury using routinely collected data and dynamic treatment regimes.

BACKGROUND AND OBJECTIVES: Defining the optimal moment to start renal replacement therapy (RRT) in acute kidney injury (AKI) remains challenging. Multiple randomized controlled trials (RCTs) addressed this question whilst using absolute criteria such as pH or serum potassium. However, there is a need for identification of the most optimal cut-offs of these criteria. We conducted a causal analysis on routinely collected data (RCD) to compare the impact of different pre-specified dynamic treatment regimes (DTRs) for RRT initiation based on time-updated levels of potassium, pH, and urinary output on 30-day ICU mortality. DESIGN, SETTING, PARTICIPANTS, AND MEASUREMENTS: Patients in the ICU of Ghent University Hospital were included at the time they met KDIGO-AKI-stage ≥ 2. We applied inverse-probability-of-censoring-weighted Aalen-Johansen estimators to evaluate 30-day survival under 81 DTRs prescribing RRT initiation under different thresholds of potassium, pH, or persisting oliguria. RESULTS: Out of 13,403 eligible patients (60.8 ± 16.8 years, SOFA 7.0 ± 4.1), 5622 (63.4 ± 15.3 years, SOFA 8.2 ± 4.2) met KDIGO-AKI-stage ≥ 2. The DTR that delayed RRT until potassium ≥ 7 mmol/l, persisting oliguria for 24-36 h, and/or pH < 7.0 (non-oliguric) or < 7.2 (oliguric) despite maximal conservative treatment resulted in a reduced 30-day ICU mortality (from 12.7% [95% CI 11.9-13.6%] under current standard of care to 10.5% [95% CI 9.5-11.7%]; risk difference 2.2% [95% CI 1.3-3.8%]) with no increase in patients starting RRT (from 471 [95% CI 430-511] to 475 [95% CI 342-572]). The fivefold cross-validation benchmark for the optimal DTR resulted in 30-day ICU mortality of 10.7%. CONCLUSIONS: Our causal analysis of RCD to compare RRT initiation at different thresholds of refractory low pH, high potassium, and persisting oliguria identified a DTR that resulted in a decrease in 30-day ICU mortality without increase in number of RRTs. Our results suggest that the current criteria to start RRT as implemented in most RCTs may be suboptimal. However, as our analysis is hypothesis generating, this optimal DTR should ideally be validated in a multicentric RCT.

Explainability in medicine in an era of AI-based clinical decision support systems.

The combination of "Big Data" and Artificial Intelligence (AI) is frequently promoted as having the potential to deliver valuable health benefits when applied to medical decision-making. However, the responsible adoption of AI-based clinical decision support systems faces several challenges at both the individual and societal level. One of the features that has given rise to particular concern is the issue of explainability, since, if the way an algorithm arrived at a particular output is not known (or knowable) to a physician, this may lead to multiple challenges, including an inability to evaluate the merits of the output. This "opacity" problem has led to questions about whether physicians are justified in relying on the algorithmic output, with some scholars insisting on the centrality of explainability, while others see no reason to require of AI that which is not required of physicians. We consider that there is merit in both views but find that greater nuance is necessary in order to elucidate the underlying function of explainability in clinical practice and, therefore, its relevance in the context of AI for clinical use. In this paper, we explore explainability by examining what it requires in clinical medicine and draw a distinction between the function of explainability for the current patient versus the future patient. This distinction has implications for what explainability requires in the short and long term. We highlight the role of transparency in explainability, and identify semantic transparency as fundamental to the issue of explainability itself. We argue that, in day-to-day clinical practice, accuracy is sufficient as an "epistemic warrant" for clinical decision-making, and that the most compelling reason for requiring explainability in the sense of scientific or causal explanation is the potential for improving future care by building a more robust model of the world. We identify the goal of clinical decision-making as being to deliver the best possible outcome as often as possible, and find-that accuracy is sufficient justification for intervention for today's patient, as long as efforts to uncover scientific explanations continue to improve healthcare for future patients.

Digital pills for the remote monitoring of medication intake: a stakeholder analysis and assessment of marketing approval and patent granting policies.

This article explores whether 'digital pills' that track medication intake should be used to enhance adherence. We concentrate on psychiatric conditions since these pose unique challenges. We analyze two public policies that potentially encourage the development of systems for remote monitoring of intake, namely the granting of patents and marketing authorization, and identify key stakeholders and their main interests so as to discuss whether these policies provide disproportionate benefits to some. The stakeholders identified are patients, system providers, drug manufacturers, insurers or healthcare systems, physicians, data users, and society at large. We discuss relevant industry reports, regulatory data, patent documents, and academic literature, and argue that there is concern that the drivers for these tracking systems are revenue and the monitoring of 'compliance' rather than 'adherence'. While accepting that the use of these systems can be justified in some circumstances, in our view these systems pose risks to patient autonomy, Shared Decision-Making, and privacy. We also find that policies on granting patents and marketing authorization overly favor the commercial actors and put patients' interests at risk. Accordingly, we propose that additional safeguards are required.

On estimation and cross-validation of dynamic treatment regimes with competing risks.

The optimal moment to start renal replacement therapy in a patient with acute kidney injury (AKI) remains a challenging problem in intensive care nephrology. Multiple randomized controlled trials have tried to answer this question, but these contrast only a limited number of treatment initiation strategies. In view of this, we use routinely collected observational data from the Ghent University Hospital intensive care units (ICUs) to investigate different prespecified timing strategies for renal replacement therapy initiation based on time-updated levels of serum potassium, pH, and fluid balance in critically ill patients with AKI with the aim to minimize 30-day ICU mortality. For this purpose, we apply statistical techniques for evaluating the impact of specific dynamic treatment regimes in the presence of ICU discharge as a competing event. We discuss two approaches, a nonparametric one - using an inverse probability weighted Aalen-Johansen estimator - and a semiparametric one - using dynamic-regime marginal structural models. Furthermore, we suggest an easy to implement cross-validation technique to assess the out-of-sample performance of the optimal dynamic treatment regime. Our work illustrates the potential of data-driven medical decision support based on routinely collected observational data.

An exploration of expectations and perceptions of practicing physicians on the implementation of computerized clinical decision support systems using a Qsort approach.

BACKGROUND: There is increasing interest in incorporating clinical decision support (CDS) into electronic healthcare records (EHR). Successful implementation of CDS systems depends on acceptance of them by healthcare workers. We used a mix of quantitative and qualitative methods starting from Qsort methodology to explore expectations and perceptions of practicing physicians on the use of CDS incorporated in EHR. METHODS: The study was performed in a large tertiary care academic hospital. We used a mixed approach with a Q-sort based classification of pre-defined reactions to clinical case vignettes combined with a thinking-aloud approach, taking into account COREQ recommendations The open source software of Ken-Q Analysis version 1.0.6. was used for the quantitative analysis, using principal components and a Varimax rotation. For the qualitative analysis, a thematic analysis based on the four main themes was performed based on the audiotapes and field notes. RESULTS: Thirty physicians were interviewed (7 in training, 8 junior staff and 15 senior staff; 16 females). Nearly all respondents were strongly averse towards interruptive messages, especially when these also were obstructive. Obstructive interruption was considered to be acceptable only when it increases safety, is adjustable to user expertise level and/or allows deviations when the end-user explains why a deviation is desirable in the case at issue. Transparency was deemed an essential feature, which seems to boil down to providing sufficient clarification on the factors underlying the recommendations of the CDS, so that these can be compared against the physicians' existing knowledge, beliefs and convictions. CONCLUSION: Avoidance of disruptive workflows and transparency of the underlying decision processes are important points to consider when developing CDS systems incorporated in EHR.

Neonatal magnesium levels are safe after maternal MgSO4 administration: a comparison between unexposed preterm neonates and neonates exposed for fetal neuroprotection or maternal eclampsia prevention-a cohort study.

To objective of this study was to compare neonatal magnesemia in the first 15 days of neonatal life between three groups: a control group not exposed to MgSO4, a neuroprotection group, and an eclampsia prevention group, and to explore its associations with child outcomes. A retrospective single-centre cohort study was performed in a tertiary care setting. Infants admitted at the neonatal intensive care unit born between 24 and 32 weeks' gestation, regardless of etiology of preterm birth, were included. The mean outcome measure was neonatal magnesemia (mmol/L). Linear mixed regression of neonatal magnesemia on exposure group and day of life was done. Generalised estimating equation models of child outcomes on neonatal magnesemia according to exposure group and day of life were made. The analyses showed that in neonatal magnesemia is significantly higher in the preeclampsia group compared to the control and neuroprotection groups. On the day of birth, this is irrespective of maternal magnesemia (preeclampsia vs control groups), and the maternal total dose or duration of MgSO4 administration (preeclampsia vs neuroprotection group). No differences were found in short-term composite outcome between the three groups. CONCLUSION: We found mean differences in neonatal magnesemia between children not exposed to MgSO4 antenatally, children exposed for fetal neuroprotection, and children exposed for maternal eclampsia prevention. A 4-g loading and 1-g/h maintenance doses, for fetal neuroprotection and eclampsia prevention, appear to be safe on the short term for the neonate. WHAT IS KNOWN: • Magnesium sulphate is a valuable medicine in obstetrics. The main indications are prevention of eclampsia and fetal neuroprotection. The most used dosage is a 4- or 6-g loading dose and a 1- or 2-g per h maintenance dose. It reduces neuromotor disabilities in extreme-to-moderate preterm born children. WHAT IS NEW: • Maternal concentrations are supraphysiological and the maternal total dose can be high. Concentrations in neonates appear to remain in safe ranges. A dosage of 4-g loading and 1 g/h seems safe for the preterm neonate on the short term.

"Many roads lead to Rome and the Artificial Intelligence only shows me one road": an interview study on physician attitudes regarding the implementation of computerised clinical decision support systems.

Research regarding the drivers of acceptance of clinical decision support systems (CDSS) by physicians is still rather limited. The literature that does exist, however, tends to focus on problems regarding the user-friendliness of CDSS. We have performed a thematic analysis of 24 interviews with physicians concerning specific clinical case vignettes, in order to explore their underlying opinions and attitudes regarding the introduction of CDSS in clinical practice, to allow a more in-depth analysis of factors underlying (non-)acceptance of CDSS. We identified three general themes from the results. First, 'the perceived role of the AI', including items referring to the tasks that may properly be assigned to the CDSS according to the respondents. Second, 'the perceived role of the physician', referring to the aspects of clinical practice that were seen as being fundamentally 'human' or non-automatable. Third, 'concerns regarding AI', including items referring to more general issues that were raised by the respondents regarding the introduction of CDSS in general and/or in clinical medicine in particular. Apart from the overall concerns expressed by the respondents regarding user-friendliness, we will explain how our results indicate that our respondents were primarily occupied by distinguishing between parts of their job that should be automated and aspects that should be kept in human hands. We refer to this distinction as 'the division of clinical labor.' This division is not based on knowledge regarding AI or medicine, but rather on which parts of a physician's job were seen by the respondents as being central to who they are as physicians and as human beings. Often the respondents' view that certain core parts of their job ought to be shielded from automation was closely linked to claims concerning the uniqueness of medicine as a domain. Finally, although almost all respondents claimed that they highly value their final responsibility, a closer investigation of this concept suggests that their view of 'final responsibility' was not that demanding after all.

The web-based application "QUiPP v.2" for the prediction of preterm birth in symptomatic women is not yet ready for worldwide clinical use: ten reflections on development, validation and use.

PURPOSE: In this correspondence, we highlight general and domain-specific caveats in the development and validation of prediction models. METHODS: Development and use of the "QUiPP" application, a tool for preterm birth prediction which is supported by the United Kingdom National Health Service, is scrutinised and commented on. RESULTS: We highlight and elaborate ten points which may be perceived to be unclear or potentially misleading. CONCLUSION: While the QUiPP application has high potential, it lacks transparency (on certain aspects related to model development) and proper validation. This precludes transportability to settings with other treatment policies and to other countries where the app has been made publicly available.

Relevance of the antenatal corticosteroids-to-delivery interval in the prevention of neonatal respiratory distress syndrome through the eyes of causal inference: a review and target trial.

PURPOSE: To critically analyse the literature on the antenatal corticosteroids (ACS)-to-birth interval from a causal point of view and to present a solution to the problem of bias caused by post hoc analysis. METHODS: Due to the post hoc nature of the ACS-to-birth interval, a randomised controlled trial (RCT) of ACS versus placebo is not able to examine the importance of the interval. When an RCT is not feasible, for whatsoever reason, a target trial can be set up and an attempt can be made to answer the causal question of interest using observational data. An attempt was made to set up a target trial which could enable to examine the causal effect of the ACS-to-birth interval on neonatal outcomes. An analysis of current literature on the ACS-to-birth interval was done. RESULTS: The majority of studies aimed to examine the causal effect of the interval, but their study design only permitted to find associations between the interval and neonatal outcomes. Barriers for setting up a target trial are highlighted. CONCLUSION: Evidence on the superiority of any ACS-to-birth interval is lacking and the question can only be addressed causally and become clinically relevant if baseline randomisation to ACS-to-birth intervals is made possible.

IgE-mediated gastroallergic anisakiasis with eosinophilic oesophagitis: a case report.

BACKGROUND: Anisakiasis is an emerging zoonosis caused by the fish parasitic nematode Anisakis infecting the gastrointestinal tract. CASE PRESENTATION: We describe a case of a 58-year-old woman diagnosed with gastro-allergic anisakiasis, in which the patient developed an acute food-induced IgE-mediated hypersensitivity reaction as well as concurrent gastro-intestinal manifestations after consumption of raw fish. The patient presented with epigastric pain, anaphylaxis and acute dysphagia caused by eosinophilic oesophagitis. DISCUSSION: Anisakis allergy should be considered as causative agent in patients presenting with acute urticarial rash, anaphylaxis and/or abdominal manifestations, especially when symptoms occur after consumption of seafood. Moreover, eosinophilic oesophagitis may be a rare but important complication of Anisakis infection. Endoscopic evaluation with esophageal biopsies should therefore be considered if suggestive symptoms are present. Patients with confirmed gastroallergic anisakiasis are advised to properly freeze or cook fish prior to consumption, although caution is advised, since heat-stable allergen proteins have been described. An adrenaline auto-injector should be prescribed.

Characteristics of Sepsis-2 septic shock patients failing to satisfy the Sepsis-3 septic shock definition: an analysis of real-time collected data.

BACKGROUND: Baseline characteristics and disease severity of patients with septic shock according to the new Sepsis-3 definition may differ from patients that only comply with the Sepsis-2 definition. We conducted a retrospective cohort study on the ICU of a Belgian tertiary care facility to seek out differences between these two patient groups and to identify variables associated with no longer satisfying the latest definition of septic shock. RESULTS: Of 1198 patients with septic shock according to the Sepsis-2 consensus definition, 233 (19.4%) did not have septic shock according to the Sepsis-3 shock definition. These patients more often had medical admission reasons and a respiratory infection as cause for the septic shock. They less often had surgery on admission and were less likely to have chronic liver disease (5.6% vs 16.2%, absolute difference 10.6% (95% CI 6.4-14.1%). Patients with septic shock only according to the old definition had significant lower APACHE II and SOFA scores and lower hospital mortality (31.6% vs 55.3%, p < 0.001). In a multivariate analysis, following variables were associated with Sepsis-2 shock patients no longer being defined as such by the Sepsis-3 definition: respiratory infection (OR 1.485 (95% CI 1.56-2.089), p = 0.023), a medical admission reason (OR 1.977 (95% CI 1.396-2.800) and chronic liver disease (OR 0.345 (95% CI 0.181-0.660), p < 0.001). CONCLUSIONS: One in five patients with septic shock according to the Sepsis-2 consensus definition is no longer considered as such when the Sepsis-3 shock criteria are applied. A medical admission reason, a respiratory infection and absence of chronic liver disease are independently associated with no longer being identified as having septic shock by the Sepsis-3 criteria.

The importance of the urinary output criterion for the detection and prognostic meaning of AKI.

Most reports on AKI claim to use KDIGO guidelines but fail to include the urinary output (UO) criterion in their definition of AKI. We postulated that ignoring UO alters the incidence of AKI, may delay diagnosis of AKI, and leads to underestimation of the association between AKI and ICU mortality. Using routinely collected data of adult patients admitted to an intensive care unit (ICU), we retrospectively classified patients according to whether and when they would be diagnosed with KDIGO AKI stage ≥ 2 based on baseline serum creatinine (Screa) and/or urinary output (UO) criterion. As outcomes, we assessed incidence of AKI and association with ICU mortality. In 13,403 ICU admissions (62.2% male, 60.8 ± 16.8 years, SOFA 7.0 ± 4.1), incidence of KDIGO AKI stage ≥ 2 was 13.2% when based only the SCrea criterion, 34.3% when based only the UO criterion, and 38.7% when based on both criteria. By ignoring the UO criterion, 66% of AKI cases were missed and 13% had a delayed diagnosis. The cause-specific hazard ratios of ICU mortality associated with KDIGO AKI stage ≥ 2 diagnosis based on only the SCrea criterion, only the UO criterion and based on both criteria were 2.11 (95% CI 1.85-2.42), 3.21 (2.79-3.69) and 2.85 (95% CI 2.43-3.34), respectively. Ignoring UO in the diagnosis of KDIGO AKI stage ≥ 2 decreases sensitivity, may lead to delayed diagnosis and results in underestimation of KDIGO AKI stage ≥ 2 associated mortality.

The concept of justifiable healthcare and how big data can help us to achieve it.

Over the last decades, the face of health care has changed dramatically, with big improvements in what is technically feasible. However, there are indicators that the current approach to evaluating evidence in health care is not holistic and hence in the long run, health care will not be sustainable. New conceptual and normative frameworks for the evaluation of health care need to be developed and investigated. The current paper presents a novel framework of justifiable health care and explores how the use of artificial intelligence and big data can contribute to achieving the goals of this framework.

Overly optimistic prediction results on imbalanced data: a case study of flaws and benefits when applying over-sampling.

Information extracted from electrohysterography recordings could potentially prove to be an interesting additional source of information to estimate the risk on preterm birth. Recently, a large number of studies have reported near-perfect results to distinguish between recordings of patients that will deliver term or preterm using a public resource, called the Term/Preterm Electrohysterogram database. However, we argue that these results are overly optimistic due to a methodological flaw being made. In this work, we focus on one specific type of methodological flaw: applying over-sampling before partitioning the data into mutually exclusive training and testing sets. We show how this causes the results to be biased using two artificial datasets and reproduce results of studies in which this flaw was identified. Moreover, we evaluate the actual impact of over-sampling on predictive performance, when applied prior to data partitioning, using the same methodologies of related studies, to provide a realistic view of these methodologies' generalization capabilities. We make our research reproducible by providing all the code under an open license.