Self-Reported Health Outcomes in Metabolic Health YouTube Comments: Cross-Sectional Study and Rule-Based Natural Language Processing Framework Development and Validation Ricardo Ribeiro, Aneesh Zutshi Journal of Medical Internet Research, 2026 Background YouTube is increasingly used for healthcasting, the sharing of evidence-based dietary and lifestyle interventions by domain experts. In the metabolic health domain, channels focused on therapeutic carbohydrate restriction have accumulated audiences of millions. A distinctive feature is the comment section, where viewers share first-person accounts of health changes, constituting a unique source of real-world outcome data at scale. However, extracting structured health information from unstructured comments presents computational challenges. Objective This observational, cross-sectional study aims to develop and validate a precision-optimized computational framework for extracting self-reported health outcomes from healthcasting YouTube comments and to characterize the prevalence, distribution across health aspects, and channel-level variation of reported outcomes across a large-scale metabolic health corpus. Methods This study analyzed 43,111 unique YouTube comments from 110 videos across 11 therapeutic carbohydrate restriction-focused healthcasting channels (37,458 unique authors; data span November 2013 to January 2026; collected via YouTube data application programming interface version 3). The methodology comprised 3 construction phases and 5 validation studies. The construction phases were (1) exploratory corpus characterization, (2) iterative development of a 35-aspect hierarchical health outcome ontology, and (3) precision-optimized rule-based classification, validated through precision validation (stratified sample of n=500), recall estimation (n=510), external validation on 5 held-out channels (n=12,653 comments), large language model–assisted interrater reliability assessment, and transformer baseline comparison against Bidirectional Encoder Representations from Transformers (BERT) and Robustly Optimized BERT Pretraining Approach (ROBERTa) classifiers. A supplementary aspect–based sentiment analysis contextualized the positive-only design. Results The framework identified 1790 positive health outcome reports (1790/43,111, 4.15% prevalence), achieving 97.6% (488/500) precision (95% CI 95.7%-98.6%) and estimated 56.2% recall (95% CI 43.4%-67.9%). The reports described 6674 positive outcomes, distributed across 35 health aspects and 18 named disease conditions extending beyond weight loss: pain and inflammation reduction (1137/6674, 17%), type 2 diabetes improvement (977/6674, 14.6%), skin health (784/6674, 11.8%), and psychological well-being (731/6674, 11%). Over half (3355/6674, 50.3%) spanned multiple research objectives. Significant channel-level variation was observed (χ²10=927.5; P<.001), with positive outcome rates ranging from 1.32% to 10.40% (odds ratio 8.68, 95% CI 7.10-10.61). Transformer baselines achieved higher recall but lower precision, confirming their advantage for high-confidence corpus generation. A supplementary aspect-based sentiment analysis indicated a positive-to-negative ratio of approximately 4.6:1 (n=1003), with negative experiences (59/495, 11.9%) predominantly involving gastrointestinal and cardiovascular concerns. Conclusions This study presents, to our knowledge, the first validated, rule-based framework for extracting self-reported metabolic health outcomes from healthcasting YouTube comments at corpus scale. Unlike existing recall-oriented social media health classifiers, the precision-optimized design achieves the confidence threshold required for outcomes research without manual review. These findings demonstrate that expert-led health content comment sections constitute a scalable, complementary data source for monitoring real-world engagement with dietary interventions, with implications for public health surveillance, platform design, and health communication research.
EBDF: The enterprise blockchain design framework and its application to an e-Procurement ecosystem Tahereh Nodehi, Aneesh Zutshi, Antonio Grilo, Belma Rizvanovic Computers and Industrial Engineering, 2022 Blockchain technologies have seen a steady growth in interest from industries as the technology is gaining maturity. It is offering a novel way to establish trust amongst multiple stakeholders without relying or trusting centralised authorities. While its use as a decentralised store of value has been validated through the emergence of cryptocurrencies, its use case in industrial applications with multiple stakeholder ecosystems such as industrial supply chain management, is still at an early stage of design and experimentation where private blockchains are used as opposed to public blockchains. Many enterprise blockchain projects failed to gain traction after initial launches, due to inefficient design, lack of incentives to all stakeholders or simply because the use of blockchain was not really necessary in the first place. There has been a need for a framework that allows blockchain designers and researchers to evaluate scenarios when a blockchain solution is useful and design the key configurations for an enterprise blockchain solution. Literature on blockchain architectures are sparse and only applicable to specific use cases or functionalities. This paper proposes a comprehensive Enterprise Blockchain Design Framework (EBDF), that not only identifies the relevant use cases when a blockchain must be utilised, but also details all the characteristics and configurations for designing an enterprise blockchain ecosystem, applicable to multiple industries. To validate the EBDF, we apply the same to the Vortal e-Procurement ecosystem allowing for multiple platforms to interoperate with greater transparency and accountability over the proposed blockchain framework. In this use case, many vendors bid for procurement procedures, often for publicly managed funds where it is extremely vital that full transparency and accountability is ensured in the entire process. Ensuring that certain digital certification functions, such as timestamps are independent from e-Procurement platform owners has been a challenge. Blockchain technology has emerged as a promising solution for not only ensuring transparency and immutability of records, but also providing for interoperability across different platforms by acting as a trusted third-party. The applied framework is used to design a Hyperledger based blockchain solution with some of the key architectural elements that could fulfil these needs while presenting the advantages of such a solution.
The value proposition of blockchain technologies and its impact on Digital Platforms Aneesh Zutshi, Antonio Grilo, Tahereh Nodehi Computers and Industrial Engineering, 2021 Since the last few years there have been a massive spurt of Research on Blockchain Technologies and several attempts at incorporating them for a myriad of Business Applications. Blockchain Technologies promised to bring about decentralized Trust having the potential to disrupt digital ecosystems by providing alternatives to centralized storage and management of data. This has the potential to radically transform industries and services through new models of data storage, transparency, tracking, payment systems amongst other advantages. However, Blockchain Technology is designed to provide other Value Propositions beyond decentralized storage, such as innovative crypto economic and investment models and radical new forms of decentralized participative governance models that could lead to the evolution of new generation of Digital Platforms and multi stakeholder business interactions. In this paper, through a systematic literature review, we present a set of key Blockchain Value Propositions and a discussion on how it can complement to the evolution of Digital Platforms and the Collaborative Economy. We also argue that while some of the value propositions are easier to integrate with existing Digital Platforms, more disruptive value propositions such as Business Automation, Economic and Governance Models present greater challenges but could lead to not just innovation at the technological level, but also metamorphosis of the existing social, economic and governance models.
A blockchain based architecture for fulfilling the needs of an e-procurement platform Proceedings of the International Conference on Industrial Engineering and Operations Management, 2020
The Emergence of Digital Platforms: A Conceptual Platform Architecture and impact on Industrial Engineering Aneesh Zutshi, Antonio Grilo Computers and Industrial Engineering, 2019 The Digital Platform Business Model has caused massive disruption across multiple industries and services and led to optimising efficiencies, speeding up information sharing and dynamising of business processes. This new phenomenon has pushed businesses into redesigning their strategy, and enabled economies of scale for several smaller companies, through the evolution of Business Ecosystems based on Digital Platforms. In this paper, through a systematic analysis of numerous case scenarios, we present a conceptual understanding of the Digital Platform and explore its impact in the field of Industrial Engineering as well as its implications for society. We elaborate on the key actors and characteristics of a Digital Platform Ecosystem and identify its main Value Proposition. We also present a Digital Platform Architecture, that enables us to conceptually classify its various layers based on the functionality and domain knowledge. Finally, we elaborate on the impact of Digital Platforms on Industrial Engineering, and identify scenarios where different areas of Industrial Engineering can be applied to the different layers of our Digital Platform Architecture.
Caller-Agent Pairing in Call Centers Using Machine Learning Techniques with Imbalanced Data Negin Mehrbod, Antonio Grilo, Aneesh Zutshi 2018 IEEE International Conference on Engineering Technology and Innovation ICE Itmc 2018 Proceedings, 2018 Call centers as the frontline of companies have high interaction with customers. Therefore, the call center performance is very important in the issue of customer satisfaction. Successful communications between agents and customers, satisfy customers and increase the performance of contact center. Call centers managers try to use historical data to improve the service to their clients. Pairing caller with the best suited agent using historical data, helps companies to reduce their costs and improve customer satisfaction. In this work, we proposed a model which optimize call centers outcome with using machine learning techniques to route the caller to the based-suited agent. The result shows using historical data of call center to find an intelligent pairing of callers and agents can improve the performance.
Simulation and forecasting of digital pricing models for an e-procurement platform using an agent-based simulation model Aneesh Zutshi, Antonio Grilo, Tahereh Nodehi, Ahmad Mehrbod, Ricardo Jardim-Goncalves Journal of Simulation, 2018 Online businesses can be represented as a complex interaction of interconnected online users responding to the value proposition of an online company. We propose a Dynamic Agent-Based Modeling framework (DYNAMOD) that aims to explain these complex dynamics. This framework aids in the creation of simulation models that mimic the actual market behavior and perform business forecasting and decision support functions. Through a case study of the largest e-procurement provider in Portugal – Vortal.biz, we simulate their pricing model and analyze revenue impact by optimizing pricing using genetic algorithms. The objective of this research is to propose agent-based model as an effective method to forecast the impact of pricing decisions.
A conceptual framework of risk identification for scale up companies in transition period Proceedings of the International Conference on Industrial Engineering and Operations Management, 2018
Relationship between investors and European startup ecosystems builders Antonio Grilo, Andre Agueda, Aneesh Zutshi, Tahereh Nodehi 2017 International Conference on Engineering Technology and Innovation Engineering Technology and Innovation Management Beyond 2020 New Challenges New Approaches ICE Itmc 2017 Proceedings, 2017
A comparison between nordic and mediterranean start up ecosystems: Economic sectors, business and pricing models Proceedings of the International Conference on Industrial Engineering and Operations Management, 2017
How business startup accelerators envision their future Proceedings of the International Conference on Industrial Engineering and Operations Management, 2017
Digital marketing practices of start-up accelerators Proceedings of International Conference on Computers and Industrial Engineering CIE, 2017
Simulating digital businesses using an agent based modeling approach Aneesh Zutshi, Antonio Grilo, Ricardo Jardim-Gonçalves ICE B 2014 Proceedings of the 11th International Conference on E Business Part of Icete 2014 11th International Joint Conference on E Business and Telecommunications, 2014
