Childhood acute lymphoblastic leukemia survival and spatial analysis of socio-environmental risks in Mexico

Background

Acute lymphoblastic leukemia (ALL) etiology remains largely unknown; incidence patterns by age, sex, and geographical distribution suggest a potential environmental role.

Aim

To identify ALL clusters from four contrasting urban areas of Mexico and to characterize the sources of environmental carcinogens.

Methods

Hospital-based ALL cases (n = 443) diagnosed in children <19 years old from the Metropolitan Zones of Merida and San Luis Potosi, the State of Mexico, and Tijuana were analyzed (2015-2020). ALL cases were coded according to the International Classification of Diseases for Oncology. ALL clusters were identified by Kernel Density, and excess risk was estimated. Data of particulate matter ≤2.5 µm (PM2.5) concentrations measured by community-monitoring stations were analyzed. Geocoded datasets of benzene, polycyclic aromatic hydrocarbons, and PM2.5 sources were analyzed to characterize patterns of exposure in ALL clusters.

Results

The survival rate for ALL ranged from 61.5% to 78.6%. Seven ALL clusters with excess risk (RR 1.4-2.3, p < 0.05) were identified. The carcinogen sources included artisanal brick kilns, gas stations, cement works, carpentry, paint, and chemical manufacturing establishments. PM2.5 levels ranged from 15 µg/m3 to 37 µg/m3 among study areas.

Conclusion

ALL clusters were identified at the community level; the excess risk could be explained by small-scale carcinogen sources. The levels of PM2.5 in outdoor air ranged from 3 to 6 times above the World Health Organization (WHO) air quality guidelines. Healthcare providers must raise awareness of the increased risk of ALL in children living near sources of environmental carcinogens; cancer control and prevention strategies must be steered from a multi-sectoral and multi-action perspective to protect children's health.

Machine learning based study for the classification of Type 2 diabetes mellitus subtypes

PURPOSE

Data-driven diabetes research has increased its interest in exploring the heterogeneity of the disease, aiming to support in the development of more specific prognoses and treatments within the so-called precision medicine. Recently, one of these studies found five diabetes subgroups with varying risks of complications and treatment responses. Here, we tackle the development and assessment of different models for classifying Type 2 Diabetes (T2DM) subtypes through machine learning approaches, with the aim of providing a performance comparison and new insights on the matter.

METHODS

We developed a three-stage methodology starting with the preprocessing of public databases NHANES (USA) and ENSANUT (Mexico) to construct a dataset with N = 10,077 adult diabetes patient records. We used N = 2,768 records for training/validation of models and left the remaining (N = 7,309) for testing. In the second stage, groups of observations -each one representing a T2DM subtype- were identified. We tested different clustering techniques and strategies and validated them by using internal and external clustering indices; obtaining two annotated datasets Dset A and Dset B. In the third stage, we developed different classification models assaying four algorithms, seven input-data schemes, and two validation settings on each annotated dataset. We also tested the obtained models using a majority-vote approach for classifying unseen patient records in the hold-out dataset.

RESULTS

From the independently obtained bootstrap validation for Dset A and Dset B, mean accuracies across all seven data schemes were [Formula: see text] ([Formula: see text]) and [Formula: see text] ([Formula: see text]), respectively. Best accuracies were [Formula: see text] and [Formula: see text]. Both validation setting results were consistent. For the hold-out dataset, results were consonant with most of those obtained in the literature in terms of class proportions.

CONCLUSION

The development of machine learning systems for the classification of diabetes subtypes constitutes an important task to support physicians for fast and timely decision-making. We expect to deploy this methodology in a data analysis platform to conduct studies for identifying T2DM subtypes in patient records from hospitals.

A Blockchain and Fingerprinting Traceability Method for Digital Product Lifecycle Management

The rise of digitalization, sensory devices, cloud computing and internet of things (IoT) technologies enables the design of novel digital product lifecycle management (DPLM) applications for use cases such as manufacturing and delivery of digital products. The verification of the accomplishment/violations of agreements defined in digital contracts is a key task in digital business transactions. However, this verification represents a challenge when validating both the integrity of digital product content and the transactions performed during multiple stages of the DPLM. This paper presents a traceability method for DPLM based on the integration of online and offline verification mechanisms based on blockchain and fingerprinting, respectively. A blockchain lifecycle registration model is used for organizations to register the exchange of digital products in the cloud with partners and/or consumers throughout the DPLM stages as well as to verify the accomplishment of agreements at each DPLM stage. The fingerprinting scheme is used for offline verification of digital product integrity and to register the DPLM logs within digital products, which is useful in either dispute or violation of agreements scenarios. We built a DPLM service prototype based on this method, which was implemented as a cloud computing service. A case study based on the DPLM of audios was conducted to evaluate this prototype. The experimental evaluation revealed the ability of this method to be applied to DPLM in real scenarios in an efficient manner.

Exploiting lexical patterns for knowledge graph construction from unstructured text in Spanish

Knowledge graphs (KGs) are useful data structures for the integration, retrieval, dissemination, and inference of information in various information domains. One of the main challenges in building KGs is the extraction of named entities (nodes) and their relations (edges), particularly when processing unstructured text as it has no semantic descriptions. Generating KGs from texts written in Spanish represents a research challenge as the existing structures, models, and strategies designed for other languages are not compatible in this scenario. This paper proposes a method to design and construct KGs from unstructured text in Spanish. We defined lexical patterns to extract named entities and (non) taxonomic, equivalence, and composition relations. Next, named entities are linked and enriched with DBpedia resources through a strategy based on SPARQL queries. Finally, OWL properties are defined from the predicate relations for creating resource description framework (RDF) triples. We evaluated the performance of the proposed method to determine the degree of elements extracted from the input text and to assess their quality through standard information retrieval measures. The evaluation revealed the feasibility of the proposed method to extract RDF triples from datasets in general and computer science domains. Competitive results were observed by comparing our method regarding an existing approach from the literature.

Blockchain support for execution, monitoring and discovery of inter-organizational business processes

In an Inter-Organizational Business Process (IOBP), independent organizations (collaborators) exchange messages to perform business transactions. With process mining, the collaborators could know what they are actually doing from process execution data and take actions for improving the underlying business process. However, process mining assumes that the knowledge of the entire process is available, something that is difficult to achieve in IOBPs since process execution data generally is not shared among the collaborating entities due to regulations and confidentiality policies (exposure of customers' data or business secrets). Additionally, there is an inherently lack-of-trust problem in IOBP as the collaborators are mutually untrusted and executed IOBP can be subject to dispute on counterfeiting actions. Recently, Blockchain has been suggested for IOBP execution management to mitigate the lack-of-trust problem. Independently, some works have suggested the use of Blockchain to support process mining tasks. In this paper, we study and address the problem of IOBP mining whose management and execution is supported by Blockchain. As contribution, we present an approach that takes advantage of Blockchain capabilities to tackle, at the same time, the lack-of-trust problem (management and execution) and confident execution data collection for process mining (discovery and conformance) of IOBPs. We present a method that (i) ensures the business rules for the correct execution and monitoring of the IOBP by collaborators, (ii) creates the event log, with data cleaning integrated, at the time the IOBP executes, and (iii) produces useful event log in XES and CSV format for the discovery and conformance checking tasks in process mining. By a set of experiments on real IOBPs, we validate our method and evaluate its impact in the resulting discovered models (fitness and precision metrics). Results revealed the effectiveness of our method to cope with both the lack-of-trust problem in IOBPs at the time that contributes to collect the data for process mining. Our method was implemented as a software tool available to the community as open-source code.

A WoT-Based Method for Creating Digital Sentinel Twins of IoT Devices

The data produced by sensors of IoT devices are becoming keystones for organizations to conduct critical decision-making processes. However, delivering information to these processes in real-time represents two challenges for the organizations: the first one is achieving a constant dataflow from IoT to the cloud and the second one is enabling decision-making processes to retrieve data from dataflows in real-time. This paper presents a cloud-based Web of Things method for creating digital twins of IoT devices (named sentinels).The novelty of the proposed approach is that sentinels create an abstract window for decision-making processes to: (a) find data (e.g., properties, events, and data from sensors of IoT devices) or (b) invoke functions (e.g., actions and tasks) from physical devices (PD), as well as from virtual devices (VD). In this approach, the applications and services of decision-making processes deal with sentinels instead of managing complex details associated with the PDs, VDs, and cloud computing infrastructures. A prototype based on the proposed method was implemented to conduct a case study based on a blockchain system for verifying contract violation in sensors used in product transportation logistics. The evaluation showed the effectiveness of sentinels enabling organizations to attain data from IoT sensors and the dataflows used by decision-making processes to convert these data into useful information.