Individual treatment effects of sodium-glucose co-transporter-2 inhibitors on the risk of chronic kidney disease in patients with type 2 diabetes: A counterfactual prediction model based on real-world data.

AIM: To estimate individual treatment effects (ITEs) of sodium-glucose co-transporter-2 inhibitors (SGLT2is) on lowering the risk of developing chronic kidney disease (CKD) in patients with type 2 diabetes (T2D) and to identify those most probable to benefit from treatment. METHODS: This study followed a T2D cohort from Ramathibodi Hospital, Thailand, from 2015 to 2022. A counterfactual model was constructed to predict factual and counterfactual risks of CKD if patients did/did not receive SGLT2is. ITEs were estimated by subtracting the factual risk from the counterfactual risk of CKD. RESULTS: There were 1619 and 15 879 patients included in the SGLT2i and non-SGLT2i groups, respectively. The estimated ITEs varied from -1.19% to -17.51% with a median of -4.49%, that is, 50% of patients had a 4.49% or greater lower CKD risk if they received an SGLT2i. Patients who gained the greatest benefit from SGLT2is were more probable to be male, aged at least 60 years, with a history of diabetes duration of at least 3 months, hypertension, peripheral arterial disease, diabetic retinopathy and low high-density lipoprotein cholesterol. CONCLUSIONS: Our prediction model provides individualized information that helps target T2D patients who may benefit more from SGLT2is. This could help clinical decision making and implementation of personalized medicine in clinical practice, especially in resource-limited settings.

Using LASSO Regression to Estimate the Population-Level Impact of Pneumococcal Conjugate Vaccines.

Pneumococcal conjugate vaccines (PCVs) protect against diseases caused by Streptococcus pneumoniae, such as meningitis, bacteremia, and pneumonia. It is challenging to estimate their population-level impact due to the lack of a perfect control population and the subtleness of signals when the endpoint-such as all-cause pneumonia-is nonspecific. Here we present a new approach for estimating the impact of PCVs: using least absolute shrinkage and selection operator (LASSO) regression to select variables in a synthetic control model to predict the counterfactual outcome for vaccine impact inference. We first used a simulation study based on hospitalization data from Mexico (2000-2013) to test the performance of LASSO and established methods, including the synthetic control model with Bayesian variable selection (SC). We found that LASSO achieved accurate and precise estimation, even in complex simulation scenarios where the association between the outcome and all control variables was noncausal. We then applied LASSO to real-world hospitalization data from Chile (2001-2012), Ecuador (2001-2012), Mexico (2000-2013), and the United States (1996-2005), and found that it yielded estimates of vaccine impact similar to SC. The LASSO method is accurate and easily implementable and can be applied to study the impact of PCVs and other vaccines.

Intracranial subsecond dopamine measurements during a "sure bet or gamble" decision-making task in patients with alcohol use disorder suggest diminished dopaminergic signals about relief.

OBJECTIVE: To the authors' knowledge, no data have been reported on dopamine fluctuations on subsecond timescales in humans with alcohol use disorder (AUD). In this study, dopamine release was monitored in 2 patients with and 2 without a history of AUD during a "sure bet or gamble" (SBORG) decision-making task to begin to characterize how subsecond dopamine responses to counterfactual information, related to psychological notions of regret and relief, in AUD may be altered. METHODS: Measurements of extracellular dopamine levels were made once every 100 msec using human voltammetric methods. Measurements were made in the caudate during deep brain stimulation electrode implantation surgeries (for treatment of movement disorders) in patients who did (AUD, n = 2) or did not (non-AUD, n = 2) have a history of AUD. Participants performed an SBORG decision-making task in which they made choices between sure bets and 50%-chance monetary gamble outcomes. RESULTS: Fast changes were found in dopamine levels that appear to be modulated by "what could have been" and by patients' AUD status. Positive counterfactual prediction errors (related to relief) differentiated patients with versus without a history of AUD. CONCLUSIONS: Dopaminergic encoding of counterfactual information appears to differ between patients with and without AUD. The current study has a major limitation of a limited sample size, but these data provide a rare insight into dopaminergic physiology during real-time decision-making in humans with an addiction disorder. The authors hope future work will expand the sample size and determine the generalizability of the current results.

Comparison of causal forest and regression-based approaches to evaluate treatment effect heterogeneity: an application for type 2 diabetes precision medicine.

OBJECTIVE: Precision medicine requires reliable identification of variation in patient-level outcomes with different available treatments, often termed treatment effect heterogeneity. We aimed to evaluate the comparative utility of individualized treatment selection strategies based on predicted individual-level treatment effects from a causal forest machine learning algorithm and a penalized regression model. METHODS: Cohort study characterizing individual-level glucose-lowering response (6 month reduction in HbA1c) in people with type 2 diabetes initiating SGLT2-inhibitor or DPP4-inhibitor therapy. Model development set comprised 1,428 participants in the CANTATA-D and CANTATA-D2 randomised clinical trials of SGLT2-inhibitors versus DPP4-inhibitors. For external validation, calibration of observed versus predicted differences in HbA1c in patient strata defined by size of predicted HbA1c benefit was evaluated in 18,741 patients in UK primary care (Clinical Practice Research Datalink). RESULTS: Heterogeneity in treatment effects was detected in clinical trial participants with both approaches (proportion predicted to have a benefit on SGLT2-inhibitor therapy over DPP4-inhibitor therapy: causal forest: 98.6%; penalized regression: 81.7%). In validation, calibration was good with penalized regression but sub-optimal with causal forest. A strata with an HbA1c benefit > 10 mmol/mol with SGLT2-inhibitors (3.7% of patients, observed benefit 11.0 mmol/mol [95%CI 8.0-14.0]) was identified using penalized regression but not causal forest, and a much larger strata with an HbA1c benefit 5-10 mmol with SGLT2-inhibitors was identified with penalized regression (regression: 20.9% of patients, observed benefit 7.8 mmol/mol (95%CI 6.7-8.9); causal forest 11.6%, observed benefit 8.7 mmol/mol (95%CI 7.4-10.1). CONCLUSIONS: Consistent with recent results for outcome prediction with clinical data, when evaluating treatment effect heterogeneity researchers should not rely on causal forest or other similar machine learning algorithms alone, and must compare outputs with standard regression, which in this evaluation was superior.

Predicting counterfactual risks under hypothetical treatment strategies: an application to HIV.

The accuracy of a prediction algorithm depends on contextual factors that may vary across deployment settings. To address this inherent limitation of prediction, we propose an approach to counterfactual prediction based on the g-formula to predict risk across populations that differ in their distribution of treatment strategies. We apply this to predict 5-year risk of mortality among persons receiving care for HIV in the U.S. Veterans Health Administration under different hypothetical treatment strategies. First, we implement a conventional approach to develop a prediction algorithm in the observed data and show how the algorithm may fail when transported to new populations with different treatment strategies. Second, we generate counterfactual data under different treatment strategies and use it to assess the robustness of the original algorithm's performance to these differences and to develop counterfactual prediction algorithms. We discuss how estimating counterfactual risks under a particular treatment strategy is more challenging than conventional prediction as it requires the same data, methods, and unverifiable assumptions as causal inference. However, this may be required when the alternative assumption of constant treatment patterns across deployment settings is unlikely to hold and new data is not yet available to retrain the algorithm.

Estimating the Individual Treatment Effect on Survival Time Based on Prior Knowledge and Counterfactual Prediction.

The estimation of the Individual Treatment Effect (ITE) on survival time is an important research topic in clinics-based causal inference. Various representation learning methods have been proposed to deal with its three key problems, i.e., reducing selection bias, handling censored survival data, and avoiding balancing non-confounders. However, none of them consider all three problems in a single method. In this study, by combining the Counterfactual Survival Analysis (CSA) model and Dragonnet from the literature, we first propose a CSA-Dragonnet to deal with the three problems simultaneously. Moreover, we found that conclusions from traditional Randomized Controlled Trials (RCTs) or Retrospective Cohort Studies (RCSs) can offer valuable bound information to the counterfactual learning of ITE, which has never been used by existing ITE estimation methods. Hence, we further propose a CSA-Dragonnet with Embedded Prior Knowledge (CDNEPK) by formulating a unified expression of the prior knowledge given by RCTs or RCSs, inserting counterfactual prediction nets into CSA-Dragonnet and defining loss items based on the bounds for the ITE extracted from prior knowledge. Semi-synthetic data experiments showed that CDNEPK has superior performance. Real-world experiments indicated that CDNEPK can offer meaningful treatment advice.

Time-series forecasting with deep learning: a survey.

Numerous deep learning architectures have been developed to accommodate the diversity of time-series datasets across different domains. In this article, we survey common encoder and decoder designs used in both one-step-ahead and multi-horizon time-series forecasting-describing how temporal information is incorporated into predictions by each model. Next, we highlight recent developments in hybrid deep learning models, which combine well-studied statistical models with neural network components to improve pure methods in either category. Lastly, we outline some ways in which deep learning can also facilitate decision support with time-series data. This article is part of the theme issue 'Machine learning for weather and climate modelling'.

Subsecond dopamine fluctuations in human striatum encode superposed error signals about actual and counterfactual reward.

In the mammalian brain, dopamine is a critical neuromodulator whose actions underlie learning, decision-making, and behavioral control. Degeneration of dopamine neurons causes Parkinson's disease, whereas dysregulation of dopamine signaling is believed to contribute to psychiatric conditions such as schizophrenia, addiction, and depression. Experiments in animal models suggest the hypothesis that dopamine release in human striatum encodes reward prediction errors (RPEs) (the difference between actual and expected outcomes) during ongoing decision-making. Blood oxygen level-dependent (BOLD) imaging experiments in humans support the idea that RPEs are tracked in the striatum; however, BOLD measurements cannot be used to infer the action of any one specific neurotransmitter. We monitored dopamine levels with subsecond temporal resolution in humans (n = 17) with Parkinson's disease while they executed a sequential decision-making task. Participants placed bets and experienced monetary gains or losses. Dopamine fluctuations in the striatum fail to encode RPEs, as anticipated by a large body of work in model organisms. Instead, subsecond dopamine fluctuations encode an integration of RPEs with counterfactual prediction errors, the latter defined by how much better or worse the experienced outcome could have been. How dopamine fluctuations combine the actual and counterfactual is unknown. One possibility is that this process is the normal behavior of reward processing dopamine neurons, which previously had not been tested by experiments in animal models. Alternatively, this superposition of error terms may result from an additional yet-to-be-identified subclass of dopamine neurons.

Propensity Weighted federated learning for treatment effect estimation in distributed imbalanced environments.

Estimating treatment effects from observational data in medicine using causal inference is a very relevant task due to the abundance of observational data and the ethical and cost implications of conducting randomized experiments or experimental interventions. However, how could we estimate the effect of a treatment in a hospital that has very restricted access to treatment? In this paper, we want to address the problem of distributed causal inference, where hospitals not only have different distributions of patients, but also different treatment assignment criteria. Furthermore, it is necessary to take into account that due to privacy restrictions, personal patient data cannot be shared between hospitals. To address this problem, we propose an adaptation of the federated learning algorithm FederatedAveraging to one of the most advanced models for the prediction of treatment effects based on neural networks, TEDVAE. Our algorithm adaptation takes into account the shift in the treatment distribution between hospitals and is therefore called Propensity WeightedFederatedAveraging (PW FedAvg). As the distributions of the assignment of treatments become more unbalanced between the nodes, the estimation of causal effects becomes more challenging. The experiments show that PW FedAvg manages to reduce errors in the estimation of individual causal effects when imbalances are large, compared to VanillaFedAvg and other federated learning-based causal inference algorithms based on the application of federated learning to linear parametric models, Gaussian Processes and Random Fourier Features.

Prolonged school closure during the pandemic time in successive waves of COVID-19- vulnerability of children to sexual abuses - A case study in Tamil Nadu, India.

Objectives: The Tamil Nadu government mandated several stay-at-home orders, with restrictions of varying intensities, to contain the first two waves of the COVID-19 pandemic. This research investigates how such orders impacted child sexual abuse (CSA) by using counterfactual prediction to compare CSA statistics with those of other crimes. After adjusting for mobility, we investigate the relationship between situational factors and recorded levels of cases registered under the Protection of Children from Sexual Offences Act (POCSO). The situational factors include the victims' living environment, their access to relief agencies, and the competence and responsiveness of the police. Methods: We adopt an auto-regressive neural network method to make a counterfactual forecast of CSA cases that represents a scenario without stay-at-home orders, relying on the eight-year daily count data of POCSO cases in Tamil Nadu. Using the insights from Google's COVID-19 Community Mobility Reports, we measure changes in mobility across various community spaces during the various phases of stay-at-home orders in both waves in 2020 and 2021. Results: The steep falls in POCSO cases during strict stay-at-home periods, compared with the counterfactual estimates, were -72% (Cliff's delta -0.99) and -36% (Cliff's delta -0.65) during the first and second waves, respectively. However, in the post-lockdown phases, there were sharp increases of 68% (Cliff's delta 0.65) and 36% (Cliff's delta 0.56) in CSA cases during the first and second waves, with concomitantly quicker reporting of case registration. Conclusions: Considering that the median delay in filing CSA complaints was above 30 days in the mild and post-intervention periods, the upsurge of cases in the more relaxed phases indicates increased occurrences of CSA during strict lockdowns. Overall, higher victimization numbers were observed during the prolonged lockdown-induced school closures. Our findings highlight the time gap between the incidents and their registration during the strict lockdown phases.

Personalized statin treatment plan using counterfactual approach with multi-objective optimization over benefits and risks.

Background: Statins are a class of drugs that lower cholesterol levels in the blood by inhibiting an enzyme called 3-hydroxy-3-methyl-glutaryl-coenzyme A (HMG-CoA) reductase. High cholesterol levels can lead to plaque buildup in the arteries, which can cause Atherosclerotic Cardiovascular Disease(ASCVD). Statins can reduce the risk of ASCVD events by about 25-35% but they might be associated with symptoms such as muscle pain, liver damage, or diabetes. As a result, this leads to a strong reason to discontinue statin therapy, which increases the risk of cardiovascular events and mortality and becomes a public-health problem.To solve this problem, in the previous work, we proposed a framework to produce a proactive strategy, called a personalized statin treatment plan (PSTP) to minimize the risks of statin-associated symptoms and therapy discontinuation when prescribing statin. In our previous PSTP framework, three limitations remain, and they can influence PSTP usability: (1) Not taking the counterfactual predictions and confounding bias into account. (2) The balance between multiple drug-prescribing objectives (especially trade-off objectives), such as tradeoff between benefits and risks. (3) Evaluating PSTP in retrospective data. Objectives: This manuscript aimed to provide solutions for the three abovementioned problems to improve PSTP robustness to produce a proactive strategy for statin prescription that can maximize the benefits (low-density lipoprotein cholesterol (LDL-C) reduction) and minimize risks (statin-associated symptoms and therapy discontinuation) at the same time. Methods: We applied overlapping weighting counterfactual survival risk prediction (CP), multiple objective optimization (MOO), and clinical trial simulation (CTS) which consists of Random Arms, Clinical Guideline arms, PSTP Arms, and Practical Arms to improve the PSTP framework and usability. Results: In addition to highly balanced covariates, in the CTS, the revised PSTP showed improvements in lowering the SAS risks overall compared to other arms across all time points by at most 7.5% to at least 1.0% (Fig. 8(a)). It also has the better flexibility of identifying the optimal Statin across all time points within one year. Conclusion: We demonstrated feasibility of robust and trustworthy counterfactual survival risk prediction model. In CTS, we also demonstrated the PSTP with Pareto optimization can personalize optimal balance between Statin benefits and risks.

Impact of COVID-19 pandemic on road safety in Tamil Nadu, India.

This study uses structured literature mapping to review worldwide trends in traffic safety following the phenomenon of the COVID-19 pandemic. Motivated by dissimilar findings globally and a lack of evidence from emerging nations which have been significantly more affected by road traffic crashes, the study examines the impact of the pandemic-induced lockdown on road traffic deaths and injuries in Tamil Nadu, India. Using a holistic approach, methods such as ARIMA, Holt-Winters, Bayesian Structural Time Series, and Generalized Additive Model are employed for counterfactual prediction, to draw a causal inference of lockdown on traffic safety. In line with global studies, a substantial reduction in traffic crashes, injuries, and fatalities during lockdowns has been found. However, the comparison of relative differences shows that the number of grievous injuries reduced more than minor injuries, crashes, or fatalities. Furthermore, these relative differences were sustained even when metrics returned to normalcy in the post-lockdown phases. Further spatial stratification at two levels (cities and districts) shows that the macroscopic state-level trends are also broadly seen in the sub-units. This validates the consistency of trends across rural-urban differences and shows that, despite variations in the degree of enforcement of the lockdown within Chennai city, contrary to expectation, increased police presence did not have a differential impact on road crashes.

Covariates adjustment questioned conclusions of predictive analyses: an illustration with the Kidney Donor Risk Index.

OBJECTIVES: We aimed to illustrate that considering covariates can lead to meaningful interpretation of the discriminative capacities of a prognostic marker. For this, we evaluated the ability of the Kidney Donor Risk Index (KDRI) to discriminate kidney graft failure risk. STUDY DESIGN AND SETTING: From 4114 French patients, we estimated the adjusted area under the time-dependent ROC curve by standardizing the marker and weighting the observations. By weighting the contributions, we also studied the impact of KDRI-based transplantations on the patient and graft survival. RESULTS: The covariate-adjusted AUC varied from 55% (95% confidence interval [CI]: 51-60%) for a prognostic up to 1 year post-transplantation to 56% (95% CI: 52-59%) up to 7 years. The Restricted Mean Survival Time (RMST) was 6.44 years for high-quality graft recipients (95% CI: 6.30-6.56) and would have been 6.31 years (95% CI: 6.13-6.46) if they had medium-quality transplants. The RMST was 5.10 years for low-quality graft recipients (95% CI: 4.90-5.31) and would have been 5.52 years (95% CI: 5.17-5.83) if they had medium-quality transplants. CONCLUSION: We demonstrated that the KDRI discriminative capacities were mainly explained by the recipient characteristics. We also showed that counterfactual estimations, often used in causal studies, are also interesting in predictive studies, especially regarding the new available methods.

A scoping review of causal methods enabling predictions under hypothetical interventions.

BACKGROUND: The methods with which prediction models are usually developed mean that neither the parameters nor the predictions should be interpreted causally. For many applications, this is perfectly acceptable. However, when prediction models are used to support decision making, there is often a need for predicting outcomes under hypothetical interventions. AIMS: We aimed to identify published methods for developing and validating prediction models that enable risk estimation of outcomes under hypothetical interventions, utilizing causal inference. We aimed to identify the main methodological approaches, their underlying assumptions, targeted estimands, and potential pitfalls and challenges with using the method. Finally, we aimed to highlight unresolved methodological challenges. METHODS: We systematically reviewed literature published by December 2019, considering papers in the health domain that used causal considerations to enable prediction models to be used for predictions under hypothetical interventions. We included both methodologies proposed in statistical/machine learning literature and methodologies used in applied studies. RESULTS: We identified 4919 papers through database searches and a further 115 papers through manual searches. Of these, 87 papers were retained for full-text screening, of which 13 were selected for inclusion. We found papers from both the statistical and the machine learning literature. Most of the identified methods for causal inference from observational data were based on marginal structural models and g-estimation. CONCLUSIONS: There exist two broad methodological approaches for allowing prediction under hypothetical intervention into clinical prediction models: (1) enriching prediction models derived from observational studies with estimated causal effects from clinical trials and meta-analyses and (2) estimating prediction models and causal effects directly from observational data. These methods require extending to dynamic treatment regimes, and consideration of multiple interventions to operationalise a clinical decision support system. Techniques for validating 'causal prediction models' are still in their infancy.