Using machine learning to evaluate treatment effects in multiple-group interrupted time series analysis

FGFR1Pred: an artificial intelligence-based model for predicting fibroblast growth factor receptor 1 inhibitor

Fibroblast growth factor receptors (FGFRs) are a family of cell surface receptors that bind to fibroblast growth factor (FGF) and mediate various cellular functions (translocating proteins, tissue repair, cell proliferation, development, and differentiation) through complex signaling pathways. The FGFR1 growth receptor is essential in the pathogenesis of numerous malignancies, including but not limited to breast cancer, bladder cancer, hepatocellular carcinoma (HCC), and cholangiocarcinoma. The higher levels of FGFR1 expression on the surface of cancer cells cause overly active signaling, which leads to rapid cell proliferation, resulting in a high spread of cancer cells. The kinases that FGFR1 activates migrate across the cell nucleus, activating genes and kinase proteins necessary for the growth and survival of cancerous cells. Therefore, FGFR1 targeting shows therapeutic promise in some diseases, including cancer. Inhibitors of FGFR1s are being developed and studied for their potential to block aberrant FGFR1 signaling and inhibit cancer growth. Since the discovery of new FGFR1 inhibitors in the laboratory is difficult, expensive, time-consuming, and labor-intensive, only a small number of FGFR1 inhibitors have been approved by the FDA for use in the treatment of cancer. To accelerate drug discovery by efficiently exploring the vast chemical space, and identifying potential candidates with higher accuracy and reduced cost, we developed artificial intelligence (AI)-based prediction models for FGFR1 inhibitors using a dataset of 2356 chemical compounds. Four machine learning (ML) algorithms (SVM, RF, k-NN, and ANN) were used to train different prediction models based on molecular descriptors (1D and 2D, with and without molecular fingerprints). Among all trained models, the random forest (RF)-based prediction model achieved the highest accuracy on the training (98.9%), test (89.8%), and external test (90.3%) datasets. The developed inhibitor prediction model (FGFR1Pred) provides a valuable tool for identifying potential FGFR1 inhibitors, expediting the drug discovery process and ultimately facilitating the development of new therapeutics. The model is made available at https://github.com/PGlab-NIPER/FGFR1Pred.git.

Impacts of bariatric surgery in health outcomes and health care costs in Brazil: Interrupted time series analysis of multi-panel data

Background

The increasing burden of obesity generates significant socioeconomic impacts for individuals, populations, and national health systems worldwide. The literature on impacts and cost-effectiveness of obesity-related interventions for prevention and treatment of moderate to severe obesity indicate that bariatric surgery presents high costs associated with high effectiveness in improving health status referring to certain outcomes; however, there is a lack of robust evidence at an individual-level estimation of its impacts on multiple health outcomes related to obesity comorbidities.

Methods

The study encompasses a single-centre retrospective longitudinal analysis of patient-level data using micro-costing technique to estimate direct health care costs with cost-effectiveness for multiple health outcomes pre-and post-bariatric surgery. Data from 114 patients who had bariatric surgery at the Hospital of Clinics of the University of Sao Paulo during 2018 were investigated through interrupted time-series analysis with generalised estimating equations and marginal effects, including information on patients' characteristics, lifestyle, anthropometric measures, hemodynamic measures, biochemical exams, and utilisation of health care resources during screening (180 days before) and follow-up (180 days after) of bariatric surgery.

Results

The preliminary statistical analysis showed that health outcomes presented improvement, except cholesterol and VLDL, and overall direct health care costs increased after the intervention. However, interrupted time series analysis showed that the rise in health care costs is attributable to the high cost of bariatric surgery, followed by a statistically significant decrease in post-intervention health care costs. Changes in health outcomes were also statistically significant in general, except in cholesterol and LDL, leading to significant improvements in patients' health status after the intervention.

Conclusions

Trends multiple health outcomes showed statistically significant improvements in patients' health status post-intervention compared to trends pre-intervention, resulting in reduced direct health care costs and the burden of obesity.

Machine Learning in Causal Inference: Application in Pharmacovigilance

Monitoring adverse drug events or pharmacovigilance has been promoted by the World Health Organization to assure the safety of medicines through a timely and reliable information exchange regarding drug safety issues. We aim to discuss the application of machine learning methods as well as causal inference paradigms in pharmacovigilance. We first reviewed data sources for pharmacovigilance. Then, we examined traditional causal inference paradigms, their applications in pharmacovigilance, and how machine learning methods and causal inference paradigms were integrated to enhance the performance of traditional causal inference paradigms. Finally, we summarized issues with currently mainstream correlation-based machine learning models and how the machine learning community has tried to address these issues by incorporating causal inference paradigms. Our literature search revealed that most existing data sources and tasks for pharmacovigilance were not designed for causal inference. Additionally, pharmacovigilance was lagging in adopting machine learning-causal inference integrated models. We highlight several currently trending directions or gaps to integrate causal inference with machine learning in pharmacovigilance research. Finally, our literature search revealed that the adoption of causal paradigms can mitigate known issues with machine learning models. We foresee that the pharmacovigilance domain can benefit from the progress in the machine learning field.

A unified perspective on the adoption of online teaching in higher education during the COVID-19 pandemic

Purpose

The study aims to develop a theoretical model that highlights the determinants of the adoption of online teaching at the time of the outbreak of COVID-19. This study adopted a time-series analysis to understand the factors leading to the adoption of online teaching.

Design/methodology/approach

Empirical data were gathered from 222 university faculty members by using an online survey. In the first phase, data were collected from those faculty members who had no experience of conducting online classes but were supposed to adopt online teaching as a result of the COVID-19 pandemic and subsequent lockdown. After two weeks, a slightly modified questionnaire was forwarded to the same group of faculty members, who were conducting online classes to know their perception regarding the adoption and conduct of online teaching.

Findings

Both the proposed conceptual frameworks were investigated empirically through confirmatory factor analysis and structural equation modeling. Significant differences were found in the perceptions of faculty members regarding before and after conducting classes through online teaching.

Originality/value

This study contributes to the literature by presenting and validating a theory-driven framework that accentuates the factors influencing online teaching during the outbreak of a pandemic. This research further extends the unified theory of acceptance and use of technology by introducing and validating three new constructs, namely: facilitative leadership, regulatory support and project team capability. Based on the findings, practical insights are provided to universities to facilitate adoption, acceptance and use of online teaching during a health-care emergency leading to campus lockdowns or the imposition of restrictions on the physical movement of people.

Using randomization tests to assess treatment effects in multiple-group interrupted time series analysis

RATIONALE, AIMS, AND OBJECTIVES

Interrupted time series analysis (ITSA) is a popular evaluation methodology in which a single treatment unit's outcome is studied over time and the intervention is expected to "interrupt" the level and/or trend of the outcome, subsequent to its introduction. The internal validity of this analysis is strengthened considerably if the treated unit is contrasted with a comparable control group. However, multiple-group ITSA typically has small sample sizes, and parametric methods for multiple-group ITSA require strong assumptions that are unlikely to be met, possibly resulting in misleading P values. In this paper, randomization tests are introduced as a non-parametric, distribution-free option for computing exact P values.

METHOD

The effect of California's Proposition 99 (passed in 1988) for reducing cigarette sales is evaluated by comparing California (CA) to Montana (MT) and Idaho (ID)-the two best matched control states not exposed to any smoking reduction initiatives. Results from randomization tests are contrasted to those of interrupted time series analysis regression (ITSAREG)-a commonly used parametric approach for evaluating treatment effects in ITSA studies.

RESULTS

Both approaches found ID and MT to be comparable to CA on their preintervention time series, and both approaches equally found CA to have statistically lower cigarette sales in the postintervention period (P < 0.01).

CONCLUSIONS

In these data, randomization tests computed P values comparable with ITSAREG, bolstering confidence in the intervention effect. Routinely including randomization tests as a complement, or alternative, to parametric methods is therefore beneficial because randomization tests are free of assumptions regarding sample size and distribution and are extremely flexible in the choice of test statistic.