A systematic review of pharmacogenetic testing to guide antipsychotic treatment.

Pharmacogenomics could optimize antipsychotic treatment by preventing adverse drug reactions, improving treatment efficacy or relieving the cost burden on the healthcare system. Here we conducted a systematic review to investigate whether pharmacogenetic testing in individuals undergoing antipsychotic treatment influences clinical or economic outcomes. On 12 January 2024, we searched MEDLINE, EMBASE, PsycINFO and Cochrane Centrale Register of Controlled Trials. The results were summarized using a narrative approach and summary tables. In total, 13 studies were eligible for inclusion in the systematic review. The current evidence base is either in favor of pharmacogenetics-guided prescribing or showed no difference between pharmacogenetics and treatment as usual for clinical and economic outcomes. In the future, we require randomized controlled trials with sufficient sample sizes that provide recommendations for patients who take antipsychotics based on a broad, multigene panel, with consistent and comparable clinical outcomes.

Empirical meropenem versus piperacillin/tazobactam for adult patients with sepsis (EMPRESS) trial: Protocol.

BACKGROUND: Piperacillin/tazobactam may be associated with less favourable outcomes than carbapenems in patients with severe bacterial infections, but the certainty of evidence is low. METHODS: The Empirical Meropenem versus Piperacillin/Tazobactam for Adult Patients with Sepsis (EMPRESS) trial is an investigator-initiated, international, parallel-group, randomised, open-label, adaptive clinical trial with an integrated feasibility phase. We will randomise adult, critically ill patients with sepsis to empirical treatment with meropenem or piperacillin/tazobactam for up to 30 days. The primary outcome is 30-day all-cause mortality. The secondary outcomes are serious adverse reactions within 30 days; isolation precautions due to resistant bacteria within 30 days; days alive without life support and days alive and out of hospital within 30 and 90 days; 90- and 180-day all-cause mortality and 180-day health-related quality of life. EMPRESS will use Bayesian statistical models with weak to somewhat sceptical neutral priors. Adaptive analyses will be conducted after follow-up of the primary outcome for the first 400 participants concludes and after every 300 subsequent participants, with adaptive stopping for superiority/inferiority and practical equivalence (absolute risk difference <2.5%-points) and response-adaptive randomisation. The expected sample sizes in scenarios with no, small or large differences are 5189, 5859 and 2570 participants, with maximum 14,000 participants and ≥99% probability of conclusiveness across all scenarios. CONCLUSIONS: EMPRESS will compare the effects of empirical meropenem against piperacillin/tazobactam in adult, critically ill patients with sepsis. Due to the pragmatic, adaptive design with high probability of conclusiveness, the trial results are expected to directly inform clinical practice.

Effects of IV fluid restriction according to site-specific intensity of standard fluid treatment-protocol.

BACKGROUND: Variation in usual practice in fluid trials assessing lower versus higher volumes may affect overall comparisons. To address this, we will evaluate the effects of heterogeneity in treatment intensity in the Conservative versus Liberal Approach to Fluid Therapy of Septic Shock in Intensive Care trial. This will reflect the effects of differences in site-specific intensities of standard fluid treatment due to local practice preferences while considering participant characteristics. METHODS: We will assess the effects of heterogeneity in treatment intensity across one primary (all-cause mortality) and three secondary outcomes (serious adverse events or reactions, days alive without life support and days alive out of hospital) after 90 days. We will classify sites based on the site-specific intensity of standard fluid treatment, defined as the mean differences in observed versus predicted intravenous fluid volumes in the first 24 h in the standard-fluid group while accounting for differences in participant characteristics. Predictions will be made using a machine learning model including 22 baseline predictors using the extreme gradient boosting algorithm. Subsequently, sites will be grouped into fluid treatment intensity subgroups containing at least 100 participants each. Subgroups differences will be assessed using hierarchical Bayesian regression models with weakly informative priors. We will present the full posterior distributions of relative (risk ratios and ratios of means) and absolute differences (risk differences and mean differences) in each subgroup. DISCUSSION: This study will provide data on the effects of heterogeneity in treatment intensity while accounting for patient characteristics in critically ill adult patients with septic shock. REGISTRATIONS: The European Clinical Trials Database (EudraCT): 2018-000404-42, ClinicalTrials. gov: NCT03668236.

Effects of sceptical priors on the performance of adaptive clinical trials with binary outcomes.

It is unclear how sceptical priors impact adaptive trials. We assessed the influence of priors expressing a spectrum of scepticism on the performance of several Bayesian, multi-stage, adaptive clinical trial designs using binary outcomes under different clinical scenarios. Simulations were conducted using fixed stopping rules and stopping rules calibrated to keep type 1 error rates at approximately 5%. We assessed total sample sizes, event rates, event counts, probabilities of conclusiveness and selecting the best arm, root mean squared errors (RMSEs) of the estimated treatment effect in the selected arms, and ideal design percentages (IDPs; which combines arm selection probabilities, power, and consequences of selecting inferior arms), with RMSEs and IDPs estimated in conclusive trials only and after selecting the control arm in inconclusive trials. Using fixed stopping rules, increasingly sceptical priors led to larger sample sizes, more events, higher IDPs in simulations ending in superiority, and lower RMSEs, lower probabilities of conclusiveness/selecting the best arm, and lower IDPs when selecting controls in inconclusive simulations. With calibrated stopping rules, the effects of increased scepticism on sample sizes and event counts were attenuated, and increased scepticism increased the probabilities of conclusiveness/selecting the best arm and IDPs when selecting controls in inconclusive simulations without substantially increasing sample sizes. Results from trial designs with gentle adaptation and non-informative priors resembled those from designs with more aggressive adaptation using weakly-to-moderately sceptical priors. In conclusion, the use of somewhat sceptical priors in adaptive trial designs with binary outcomes seems reasonable when considering multiple performance metrics simultaneously.

Position Paper on the Reporting of Norepinephrine Formulations in Critical Care from the Society of Critical Care Medicine and European Society of Intensive Care Medicine Joint Task Force.

OBJECTIVES: To provide guidance on the reporting of norepinephrine formulation labeling, reporting in publications, and use in clinical practice. DESIGN: Review and task force position statements with necessary guidance. SETTING: A series of group conference calls were conducted from August 2023 to October 2023, along with a review of the available evidence and scope of the problem. SUBJECTS: A task force of multinational and multidisciplinary critical care experts assembled by the Society of Critical Care Medicine and the European Society of Intensive Care Medicine. INTERVENTIONS: The implications of a variation in norepinephrine labeled as conjugated salt (i.e., bitartrate or tartrate) or base drug in terms of effective concentration of norepinephrine were examined, and guidance was provided. MEASUREMENTS AND MAIN RESULTS: There were significant implications for clinical care, dose calculations for enrollment in clinical trials, and results of datasets reporting maximal norepinephrine equivalents. These differences were especially important in the setting of collaborative efforts across countries with reported differences. CONCLUSIONS: A joint task force position statement was created outlining the scope of norepinephrine-dose formulation variations, and implications for research, patient safety, and clinical care. The task force advocated for a uniform norepinephrine-base formulation for global use, and offered advice aimed at appropriate stakeholders.

Health-related quality of life trajectories in critical illness: Protocol for a Monte Carlo simulation study.

BACKGROUND: Health-related quality of life (HRQoL) is a patient-centred outcome increasingly used as a secondary outcome in critical care research. It may cover several important dimensions of clinical status in intensive care unit (ICU) patients that arguably elude other more easily quantified outcomes such as mortality. Poor associations with harder outcomes, conflicting data on HRQoL in critically ill compared to the background population, and paradoxical effects on HRQoL and mortality complicate the current operationalisation in critical care trials. This protocol outlines a simulation study that will gauge if the areas under the HRQoL trajectories could be a viable alternative. METHODS: We will gauge the behaviour of the proposed HRQoL operationalisation through Monte Carlo simulations, under clinical scenarios that reflect a broad critical care population eligible for inclusion in a large pragmatic trial. We will simulate 15,360 clinical scenarios based on a full factorial design with the following seven simulation parameters: number of patients per arm, relative mortality reduction in the interventional arm, acceleration of HRQoL improvement in the interventional arm, the relative improvement in final HRQoL in the interventional arm, dampening effect of mortality on HRQoL values at discharge from the ICU, proportion of so-called mortality benefiters in the interventional arm and mortality trajectory shape. For each clinical scenario, we will simulate 100,000 two-arm trials with 1:1 randomisation. HRQoL will be sampled fortnightly after ICU discharge. Outcomes will include HRQoL in survivors and all patients at the end of follow-up; mean areas under the HRQoL trajectories in both arms; and mean difference between areas under the HRQoL trajectories and single-sampled HRQoLs at the end of follow-up. DISCUSSION: In the outlined simulation study, we aim to assess whether the area under the HRQoL trajectory curve could be a candidate for reconciling the seemingly paradoxical effects on improved mortality and reduced HRQoL while remaining sensitive to early or accelerated improvement in patient outcomes. The resultant insights will inform subsequent methodological work on prudent collection and statistical analysis of such data from real critically ill patients.

Real-world causal evidence for planned predictive enrichment in critical care trials: A scoping review.

BACKGROUND: Randomised clinical trials in critical care are prone to inconclusiveness due, in part, to undue optimism about effect sizes and suboptimal accounting for heterogeneous treatment effects. Although causal evidence from rich real-world critical care can help overcome these challenges by informing predictive enrichment, no overview exists. METHODS: We conducted a scoping review, systematically searching 10 general and speciality journals for reports published on or after 1 January 2018, of randomised clinical trials enrolling adult critically ill patients. We collected trial metadata on 22 variables including recruitment period, intervention type and early stopping (including reasons) as well as data on the use of causal evidence from secondary data for planned predictive enrichment. RESULTS: We screened 9020 records and included 316 unique RCTs with a total of 268,563 randomised participants. One hundred seventy-three (55%) trials tested drug interventions, 101 (32%) management strategies and 42 (13%) devices. The median duration of enrolment was 2.2 (IQR: 1.3-3.4) years, and 83% of trials randomised less than 1000 participants. Thirty-six trials (11%) were restricted to COVID-19 patients. Of the 55 (17%) trials that stopped early, 23 (42%) used predefined rules; futility, slow enrolment and safety concerns were the commonest stopping reasons. None of the included RCTs had used causal evidence from secondary data for planned predictive enrichment. CONCLUSION: Work is needed to harness the rich multiverse of critical care data and establish its utility in critical care RCTs. Such work will likely need to leverage methodology from interventional and analytical epidemiology as well as data science.

Restrictive versus standard IV fluid therapy in adult ICU patients with septic shock-Bayesian analyses of the CLASSIC trial.

BACKGROUND: The CLASSIC trial assessed the effects of restrictive versus standard intravenous (IV) fluid therapy in adult intensive care unit (ICU) patients with septic shock. This pre-planned study provides a probabilistic interpretation and evaluates heterogeneity in treatment effects (HTE). METHODS: We analysed mortality, serious adverse events (SAEs), serious adverse reactions (SARs) and days alive without life-support within 90 days using Bayesian models with weakly informative priors. HTE on mortality was assessed according to five baseline variables: disease severity, vasopressor dose, lactate levels, creatinine values and IV fluid volumes given before randomisation. RESULTS: The absolute difference in mortality was 0.2%-points (95% credible interval: -5.0 to 5.4; 47% posterior probability of benefit [risk difference <0.0%-points]) with restrictive IV fluid. The posterior probabilities of benefits with restrictive IV fluid were 72% for SAEs, 52% for SARs and 61% for days alive without life-support. The posterior probabilities of no clinically important differences (absolute risk difference ≤2%-points) between the groups were 56% for mortality, 49% for SAEs, 90% for SARs and 38% for days alive without life-support. There was 97% probability of HTE for previous IV fluid volumes analysed continuously, that is, potentially relatively lower mortality of restrictive IV fluids with higher previous IV fluids. No substantial evidence of HTE was found in the other analyses. CONCLUSION: We could not rule out clinically important effects of restrictive IV fluid therapy on mortality, SAEs or days alive without life-support, but substantial effects on SARs were unlikely. IV fluids given before randomisation might interact with IV fluid strategy.

Effects of duration of follow-up and lag in data collection on the performance of adaptive clinical trials.

Different combined outcome-data lags (follow-up durations plus data-collection lags) may affect the performance of adaptive clinical trial designs. We assessed the influence of different outcome-data lags (0-105 days) on the performance of various multi-stage, adaptive trial designs (2/4 arms, with/without a common control, fixed/response-adaptive randomisation) with undesirable binary outcomes according to different inclusion rates (3.33/6.67/10 patients/day) under scenarios with no, small, and large differences. Simulations were conducted under a Bayesian framework, with constant stopping thresholds for superiority/inferiority calibrated to keep type-1 error rates at approximately 5%. We assessed multiple performance metrics, including mean sample sizes, event counts/probabilities, probabilities of conclusiveness, root mean squared errors (RMSEs) of the estimated effect in the selected arms, and RMSEs between the analyses at the time of stopping and the final analyses including data from all randomised patients. Performance metrics generally deteriorated when the proportions of randomised patients with available data were smaller due to longer outcome-data lags or faster inclusion, that is, mean sample sizes, event counts/probabilities, and RMSEs were larger, while the probabilities of conclusiveness were lower. Performance metric impairments with outcome-data lags ≤45 days were relatively smaller compared to those occurring with ≥60 days of lag. For most metrics, the effects of different outcome-data lags and lower proportions of randomised patients with available data were larger than those of different design choices, for example, the use of fixed versus response-adaptive randomisation. Increased outcome-data lag substantially affected the performance of adaptive trial designs. Trialists should consider the effects of outcome-data lags when planning adaptive trials.

Use of days alive without life support and similar count outcomes in randomised clinical trials - an overview and comparison of methodological choices and analysis methods.

BACKGROUND: Days alive without life support (DAWOLS) and similar outcomes that seek to summarise mortality and non-mortality experiences are increasingly used in critical care research. The use of these outcomes is challenged by different definitions and non-normal outcome distributions that complicate statistical analysis decisions. METHODS: We scrutinized the central methodological considerations when using DAWOLS and similar outcomes and provide a description and overview of the pros and cons of various statistical methods for analysis supplemented with a comparison of these methods using data from the COVID STEROID 2 randomised clinical trial. We focused on readily available regression models of increasing complexity (linear, hurdle-negative binomial, zero-one-inflated beta, and cumulative logistic regression models) that allow comparison of multiple treatment arms, adjustment for covariates and interaction terms to assess treatment effect heterogeneity. RESULTS: In general, the simpler models adequately estimated group means despite not fitting the data well enough to mimic the input data. The more complex models better fitted and thus better replicated the input data, although this came with increased complexity and uncertainty of estimates. While the more complex models can model separate components of the outcome distributions (i.e., the probability of having zero DAWOLS), this complexity means that the specification of interpretable priors in a Bayesian setting is difficult. Finally, we present multiple examples of how these outcomes may be visualised to aid assessment and interpretation. CONCLUSIONS: This summary of central methodological considerations when using, defining, and analysing DAWOLS and similar outcomes may help researchers choose the definition and analysis method that best fits their planned studies. TRIAL REGISTRATION: COVID STEROID 2 trial, ClinicalTrials.gov: NCT04509973, ctri.nic.in: CTRI/2020/10/028731.

Development of a dynamic prediction model for unplanned ICU admission and mortality in hospitalized patients.

Frequent assessment of the severity of illness for hospitalized patients is essential in clinical settings to prevent outcomes such as in-hospital mortality and unplanned admission to the intensive care unit (ICU). Classical severity scores have been developed typically using relatively few patient features. Recently, deep learning-based models demonstrated better individualized risk assessments compared to classic risk scores, thanks to the use of aggregated and more heterogeneous data sources for dynamic risk prediction. We investigated to what extent deep learning methods can capture patterns of longitudinal change in health status using time-stamped data from electronic health records. We developed a deep learning model based on embedded text from multiple data sources and recurrent neural networks to predict the risk of the composite outcome of unplanned ICU transfer and in-hospital death. The risk was assessed at regular intervals during the admission for different prediction windows. Input data included medical history, biochemical measurements, and clinical notes from a total of 852,620 patients admitted to non-intensive care units in 12 hospitals in Denmark's Capital Region and Region Zealand during 2011-2016 (with a total of 2,241,849 admissions). We subsequently explained the model using the Shapley algorithm, which provides the contribution of each feature to the model outcome. The best model used all data modalities with an assessment rate of 6 hours, a prediction window of 14 days and an area under the receiver operating characteristic curve of 0.898. The discrimination and calibration obtained with this model make it a viable clinical support tool to detect patients at higher risk of clinical deterioration, providing clinicians insights into both actionable and non-actionable patient features.

Association between days alive without life support/out of hospital and health-related quality of life.

BACKGROUND: Trials in critically ill patients increasingly focus on days alive without life support (DAWOLS) or days alive out of hospital (DAOOH) and health-related quality of life (HRQoL). DAWOLS and DAOOH convey more information than mortality and are simpler and faster to collect than HRQoL. However, whether these outcomes are associated with HRQoL is uncertain. We thus aimed to assess the associations between DAWOLS and DAOOH and long-term HRQoL. METHODS: Secondary analysis of the COVID STEROID 2 trial including adults with COVID-19 and severe hypoxaemia and the Handling Oxygenation Targets in the Intensive Care Unit (HOT-ICU) trial including adult intensive care unit patients with acute hypoxaemic respiratory failure. Associations between DAWOLS and DAOOH at day 28 and 90 and long-term HRQoL (after 6 or 12 months) using the EuroQol 5-dimension 5-level survey (EQ VAS and EQ-5D-5L index values) were assessed using flexible models and evaluated using measures of fit and prediction adequacy in both datasets (comprising internal performance and external validation), non-parametric correlation coefficients and graphical presentations. RESULTS: We found no strong associations between DAWOLS or DAOOH and HRQoL in survivors at HRQoL-follow-up (615 and 1476 patients, respectively). There was substantial variability in outcomes, and predictions from the best fitted models were poor both internally and externally in the other trial dataset, which also showed inadequate calibration. Moderate associations were found when including non-survivors, although predictions remained uncertain and calibration inadequate. CONCLUSION: DAWOLS and DAOOH were poorly associated with HRQoL in adult survivors of severe or critical illness included in the COVID STEROID 2 and HOT-ICU trials.

An overview of methodological considerations regarding adaptive stopping, arm dropping, and randomization in clinical trials.

BACKGROUND AND OBJECTIVES: Adaptive features may increase flexibility and efficiency of clinical trials, and improve participants' chances of being allocated to better interventions. Our objective is to provide thorough guidance on key methodological considerations for adaptive clinical trials. METHODS: We provide an overview of key methodological considerations for clinical trials employing adaptive stopping, adaptive arm dropping, and response-adaptive randomization. We cover pros and cons of different decisions and provide guidance on using simulation to compare different adaptive trial designs. We focus on Bayesian multi-arm adaptive trials, although the same general considerations apply to frequentist adaptive trials. RESULTS: We provide guidance on 1) interventions and possible common control, 2) outcome selection, follow-up duration and model choice, 3) timing of adaptive analyses, 4) decision rules for adaptive stopping and arm dropping, 5) randomization strategies, 6) performance metrics, their prioritization, and arm selection strategies, and 7) simulations, assessment of performance under different scenarios, and reporting. Finally, we provide an example using a newly developed R simulation engine that may be used to evaluate and compare different adaptive trial designs. CONCLUSION: This overview may help trialists design better and more transparent adaptive clinical trials and to adequately compare them before initiation.

Exploratory pharmacovigilance with machine learning in big patient data: A focused scoping review.

BACKGROUND: Machine learning can operationalize the rich and complex data in electronic patient records for exploratory pharmacovigilance endeavours. OBJECTIVE: The objective of this review is to identify applications of machine learning and big patient data in exploratory pharmacovigilance. METHODS: We searched PubMed and Embase and included original articles with an exploratory pharmacovigilance purpose, focusing on medicinal interventions and reporting the use of machine learning in electronic patient records with ≥1000 patients collected after market entry. FINDINGS: Of 2557 studies screened, seven were included. Those covered six countries and were published between 2015 and 2021. The most prominent machine learning methods were random forests, logistic regressions, and support vector machines. Two studies used artificial neural networks or naive Bayes classifiers. One study used formal concept analysis for association mining, and another used temporal difference learning. Five studies compared several methods against each other. The numbers of patients in most data sets were in the order of thousands; two studies used what can more reasonably be considered big data with >1 000 000 patients records. CONCLUSION: Despite years of great aspirations for combining machine learning and clinical data for exploratory pharmacovigilance, only few studies still seem to deliver somewhat on these expectations.

Is the CYP2D6 Genotype Associated with Antipsychotic-Induced Weight Gain?

Antipsychotic-induced weight gain (AIWG) is a serious adverse effect. Studies have linked genetically-predicted CYP2D6 metabolic capacity to AIWG. The evidence, however, is ambiguous. We performed multiple regression analyses examining the association between genetic-predicted CYP2D6 metabolic capacity and AIWG. Analyses were based on previously unpublished data from an RCT investigating the clinical utility of routine genotyping of CYP2D6 and CYP2C19 in patients with schizophrenia. A total of 211 patients, corresponding to 71% of the original study population, were included. Our analyses indicated an effect of genetically predicted CYP2D6 metabolic capacity on AIWG with significant weight gain in both CYP2D6 poor metabolizers (PMs) (4.00 kg (95% CI: 0.80; 7.21)) and ultrarapid metabolizers (UMs) (6.50 kg (95% CI: 1.03; 12.0)). This finding remained stable after adjustment for covariates (PMs: 4.26 kg (0.88; 7.64), UMs: 7.26 kg (1.24; 13.3)). In addition to the CYP2D6 metabolic capacity, both baseline body mass index (-0.24 (95% CI: -0.44; -0.03)) and chlorpromazine equivalents per day (0.0041 (95% CI: 0.0005; 0.0077)) were statistically significantly associated with weight change in the adjusted analysis. Our results support that the genetically predicted CYP2D6 metabolic capacity matters for AIWG.

Causal inference for planning randomised critical care trials: Protocol for a scoping review.

BACKGROUND: Randomised clinical trials in critical care are prone to inconclusiveness owing, in part, to undue optimism about effect sizes and suboptimal accounting for heterogeneous treatment effects. Planned predictive enrichment based on secondary critical care data (often very rich with respect to both data types and temporal granularity) and causal inference methods may help overcome these challenges, but no overview exists about their use to this end. METHODS: We will conduct a scoping review to assess the extent and nature of the use of causal inference from secondary data for planned predictive enrichment of randomised clinical trials in critical care. We will systematically search 10 general and specialty journals for reports published on or after 1 January 2018, of randomised clinical trials enrolling adult critically ill patients. We will collect trial metadata (e.g., recruitment period and phase) and, when available, information pertaining to the focus of the review (predictive enrichment based on causal inference estimates from secondary data): causal inference methods, estimation techniques and software used; types of patient populations; data provenance, types and models; and the availability of the data (public or not). The results will be reported in a descriptive manner. DISCUSSION: The outlined scoping review aims to assess the use of causal inference methods and secondary data for planned predictive enrichment in randomised critical care trials. This will help guide methodological improvements to increase the utility, and facilitate the use, of causal inference estimates when planning such trials in the future.

Discrete-time survival analysis in the critically ill: a deep learning approach using heterogeneous data.

Prediction of survival for patients in intensive care units (ICUs) has been subject to intense research. However, no models exist that embrace the multiverse of data in ICUs. It is an open question whether deep learning methods using automated data integration with minimal pre-processing of mixed data domains such as free text, medical history and high-frequency data can provide discrete-time survival estimates for individual ICU patients. We trained a deep learning model on data from patients admitted to ten ICUs in the Capital Region of Denmark and the Region of Southern Denmark between 2011 and 2018. Inspired by natural language processing we mapped the electronic patient record data to an embedded representation and fed the data to a recurrent neural network with a multi-label output layer representing the chance of survival at different follow-up times. We evaluated the performance using the time-dependent concordance index. In addition, we quantified and visualized the drivers of survival predictions using the SHAP methodology. We included 37,355 admissions of 29,417 patients in our study. Our deep learning models outperformed traditional Cox proportional-hazard models with concordance index in the ranges 0.72-0.73, 0.71-0.72, 0.71, and 0.69-0.70, for models applied at baseline 0, 24, 48, and 72 h, respectively. Deep learning models based on a combination of entity embeddings and survival modelling is a feasible approach to obtain individualized survival estimates in data-rich settings such as the ICU. The interpretable nature of the models enables us to understand the impact of the different data domains.

Language-agnostic pharmacovigilant text mining to elicit side effects from clinical notes and hospital medication records.

We sought to craft a drug safety signalling pipeline associating latent information in clinical free text with exposures to single drugs and drug pairs. Data arose from 12 secondary and tertiary public hospitals in two Danish regions, comprising approximately half the Danish population. Notes were operationalised with a fastText embedding, based on which we trained 10 270 neural-network models (one for each distinct single-drug/drug-pair exposure) predicting the risk of exposure given an embedding vector. We included 2 905 251 admissions between May 2008 and June 2016, with 13 740 564 distinct drug prescriptions; the median number of prescriptions was 5 (IQR: 3-9) and in 1 184 340 (41%) admissions patients used ≥5 drugs concomitantly. A total of 10 788 259 clinical notes were included, with 179 441 739 tokens retained after pruning. Of 345 single-drug signals reviewed, 28 (8.1%) represented possibly undescribed relationships; 186 (54%) signals were clinically meaningful. Sixteen (14%) of the 115 drug-pair signals were possible interactions, and two (1.7%) were known. In conclusion, we built a language-agnostic pipeline for mining associations between free-text information and medication exposure without manual curation, predicting not the likely outcome of a range of exposures but also the likely exposures for outcomes of interest. Our approach may help overcome limitations of text mining methods relying on curated data in English and can help leverage non-English free text for pharmacovigilance.

Using Machine Learning to Identify Patients at High Risk of Inappropriate Drug Dosing in Periods with Renal Dysfunction.

PURPOSE: Dosing of renally cleared drugs in patients with kidney failure often deviates from clinical guidelines, so we sought to elicit predictors of receiving inappropriate doses of renal risk drugs. PATIENTS AND METHODS: We combined data from the Danish National Patient Register and in-hospital data on drug administrations and estimated glomerular filtration rates for admissions between 1 October 2009 and 1 June 2016, from a pool of about 2.6 million persons. We trained artificial neural network and linear logistic ridge regression models to predict the risk of five outcomes (>0, ≥1, ≥2, ≥3 and ≥5 inappropriate doses daily) with index set 24 hours after admission. We used time-series validation for evaluating discrimination, calibration, clinical utility and explanations. RESULTS: Of 52,451 admissions included, 42,250 (81%) were used for model development. The median age was 77 years; 50% of admissions were of women. ≥5 drugs were used between admission start and index in 23,124 admissions (44%); the most common drug classes were analgesics, systemic antibacterials, diuretics, antithrombotics, and antacids. The neural network models had better discriminative power (all AUROCs between 0.77 and 0.81) and were better calibrated than their linear counterparts. The main prediction drivers were use of anti-inflammatory, antidiabetic and anti-Parkinson's drugs as well as having a diagnosis of chronic kidney failure. Sex and age affected predictions but slightly. CONCLUSION: Our models can flag patients at high risk of receiving at least one inappropriate dose daily in a controlled in-silico setting. A prospective clinical study may confirm that this holds in real-life settings and translates into benefits in hard endpoints.