A causal Bayesian network model of disease progression mechanisms in chronic myeloid leukemia

LncRNA 51A: A promising diagnostic biomarker for assessing cognitive decline in occupationally exposed aluminum workers

OBJECTIVE

To assess the diagnostic utility of lncRNA 51 A in detecting cognitive decline among aluminum-exposed workers occupationally.

METHODS

921 male workers from an aluminum manufacturing facility underwent cognitive assessments, measurement of plasma aluminum levels and quantification of lncRNA 51 A levels. Receiver Operating Characteristic (ROC) curves were constructed to assess the diagnostic potential of lncRNA 51 A. Bayesian network model was utilized to predict the likelihood of cognitive decline among the study population.

RESULTS

Significant differences in lncRNA 51 A levels, plasma aluminum concentration and MMSE scores were observed between cognitive normal and decline groups. The lncRNA 51 A expression was negatively correlated with MMSE scores. The area under the curve (AUC) was 0.894, with 89.3 % sensitivity and 73.9 % specificity. The Bayesian network model indicated varying probabilities of cognitive decline based on lncRNA 51 A expression levels.

CONCLUSION

Plasma lncRNA 51 A shows potential as an excellent biomarker for cognitive decline diagnosis in aluminum-exposed workers.

Pathogenesis and management of accelerated and blast phases of chronic myeloid leukemia

The treatment of chronic myeloid leukemia (CML) with tyrosine kinase inhibitors (TKIs) has been a model for cancer therapy development. Though most patients with CML have a normal quality and duration of life with TKI therapy, some patients progress to accelerated phase (AP) and blast phase (BP), both of which have a relatively poor prognosis. The rates of progression have reduced significantly from over >20% in the pre-TKI era to <5% now, largely due to refinements in CML therapy and response monitoring. Significant insights have been gained into the mechanisms of disease transformation including the role of additional cytogenetic abnormalities, somatic mutations, and other genomic alterations present at diagnosis or evolving on therapy. This knowledge is helping to optimize TKI therapy, improve prognostication and inform the development of novel combination regimens in these patients. While patients with de novo CML-AP have outcomes almost similar to CML in chronic phase (CP), those transformed from previously treated CML-CP should receive second- or third- generation TKIs and be strongly considered for allogeneic stem cell transplantation (allo-SCT). Similarly, patients with transformed CML-BP have particularly dismal outcomes with a median survival usually less than one year. Combination regimens with a potent TKI such as ponatinib followed by allo-SCT can achieve long-term survival in some transformed BP patients. Regimens including venetoclax in myeloid BP or inotuzumab ozogamicin or blinatumomab in lymphoid BP might lead to deeper and longer responses, facilitating potentially curative allo-SCT for patients with CML-BP once CP is achieved. Newer agents and novel combination therapies are further expanding the therapeutic arsenal in advanced phase CML.

Exploring influencing factors of chronic obstructive pulmonary disease based on elastic net and Bayesian network

This study aimed to construct Bayesian networks (BNs) to analyze the network relationships between COPD and its influencing factors, and the strength of each factor's influence on COPD was reflected through network reasoning. Elastic Net and Max-Min Hill-Climbing (MMHC) algorithm were adopted to screen the variables on the surveillance data of COPD among residents in Shanxi Province, China from 2014 to 2015, and construct BNs respectively. 10 variables finally entered the model after screening by Elastic Net. The BNs constructed by MMHC showed that smoking status, household air pollution, family history, cough, air hunger or dyspnea were directly related to COPD, and Gender was indirectly linked to COPD through smoking status. Moreover, smoking status, household air pollution and family history were the parent nodes of COPD, and cough, air hunger or dyspnea represented the child nodes of COPD. In other words, smoking status, household air pollution and family history were related to the occurrence of COPD, and COPD would make patients’ cough, air hunger or dyspnea worse. Generally speaking, BNs could reveal the complex network linkages between COPD and its relevant factors well, making it more convenient to carry out targeted prevention and control of COPD.

A Clinical Decision Support Tool to Find the Best Initial Intravenous Cyclosporine Regimen in Pediatric Hematopoietic Stem Cell Transplantation

To optimize cyclosporine A (CsA) dosing regimen in pediatric patients undergoing hematopoietic stem cell transplantation (HSCT), we aimed to provide clinicians with a validated decision support tool for determining the most suitable first dose of intravenous CsA. We used a 10-year monocentric data set of pediatric patients undergoing HSCT. Discretization of all variables was performed according to literature or thanks to algorithms using Shannon entropy (from information theory) or equal width intervals. The first 8 years were used to build the Bayesian network model. This model underwent a 10-fold cross-validation, and then a prospective validation with data of the last 2 years. There were 3.3% and 4.1% of missing values in the training and the validation data set, respectively. After prospective validation, the Tree-Augmented Naïve Bayesian network shows interesting prediction performances with an average area under the receiver operating characteristic curve of 0.804, 32.8% of misclassified patients, a true-positive rate of 0.672, and a false-positive rate of 0.285. This validated model allows good predictions to propose an optimized and personalized initial CsA dose for pediatric patients undergoing HSCT. The clinical impact of its use should be further evaluated.

Recovery preparedness of global air transport influenced by COVID-19 pandemic: Policy intervention analysis

The outbreak of COVID-19 constitutes an unprecedented disruption globally, in which risk management framework is on top priority in many countries. Travel restriction and home/office quarantine are some frequently utilized non-pharmaceutical interventions, which bring the worst crisis of airline industry compared with other transport modes. Therefore, the post-recovery of global air transport is extremely important, which is full of uncertainty but rare to be studied. The explicit/implicit interacted factors generate difficulties in drawing insights into the complicated relationship and policy intervention assessment. In this paper, a Causal Bayesian Network (CBN) is utilized for the modelling of the post-recovery behaviour, in which parameters are synthesized from expert knowledge, open-source information and interviews from travellers. The tendency of public policy in reaction to COVID-19 is analyzed, whilst sensitivity analysis and forward/backward belief propagation analysis are conducted. Results show the feasibility and scalability of this model. On condition that no effective health intervention method (vaccine, medicine) will be available soon, it is predicted that nearly 120 days from May 22, 2020, would be spent for the number of commercial flights to recover back to 58.52%-60.39% on different interventions. This intervention analysis framework is of high potential in the decision making of recovery preparedness and risk management for building the new normal of global air transport.

Untangling the complexity of multimorbidity with machine learning

The prevalence of multimorbidity has been increasing in recent years, posing a major burden for health care delivery and service. Understanding its determinants and impact is proving to be a challenge yet it offers new opportunities for research to go beyond the study of diseases in isolation. In this paper, we review how the field of machine learning provides many tools for addressing research challenges in multimorbidity. We highlight recent advances in promising methods such as matrix factorisation, deep learning, and topological data analysis and how these can take multimorbidity research beyond cross-sectional, expert-driven or confirmatory approaches to gain a better understanding of evolving patterns of multimorbidity. We discuss the challenges and opportunities of machine learning to identify likely causal links between previously poorly understood disease associations while giving an estimate of the uncertainty on such associations. We finally summarise some of the challenges for wider clinical adoption of machine learning research tools and propose some solutions.