Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Mário Amorim Lopes
  • Cargo

    Investigador Sénior
  • Desde

    01 dezembro 2013
010
Publicações

2023

Predicting the future: introducing business analytics to endoscopy units

Autores
Pinho, R; Veloso, R; Estevinho, MM; Rodrigues, T; Almada Lobo, B; Amorim Lopes, M; Freitas, T;

Publicação
REVISTA ESPANOLA DE ENFERMEDADES DIGESTIVAS

Abstract
Background and aims: currently, most endoscopy software only provides limited statistics of past procedures, while none allows patterns to be extrapolated. To overcome this need, the authors applied business analytic models to pre-dict future demand and the need for endoscopists in a ter-tiary hospital Endoscopy Unit. Methods: a query to the endoscopy database was per-formed to retrieve demand from 2015 to 2021. The graphi-cal inspection allowed inferring of trends and seasonality, perceiving the impact of the COVID-19 pandemic, and se-lecting the best forecasting models. Considering COVID-19's impact in the second quarter of 2020, data for esoph-agogastroduodenoscopy (EGD) and colonoscopy was estimated using linear regression of historical data. The actual demand in the first two quarters of 2022 was used to validate the models. Results: during the study period, 53,886 procedures were requested. The best forecasting models were: a) simple sea-sonal exponential smoothing for EGD, colonoscopy and percutaneous endoscopic gastrostomy (PEG); b) double ex-ponential smoothing for capsule endoscopy and deep en-teroscopy; and c) simple exponential smoothing for endo-scopic retrograde cholangiopancreatography (ERCP) and endoscopic ultrasound (EUS). The mean average percent-age error ranged from 6.1 % (EGD) to 33.5 % (deep en - teroscopy). Overall, 8,788 procedures were predicted for 2022. The actual demand in the first two quarters of 2022 was within the predicted range. Considering the usual time allocation for each technique, 3.2 full-time equivalent en-doscopists (40 hours-dedication to endoscopy) will be re-quired to perform all procedures in 2022. Conclusions: the incorporation of business analytics into the endoscopy software and clinical practice may enhance resource allocation, improving patient-focused deci-sion-making and healthcare quality.

2023

A Biomedical Entity Extraction Pipeline for Oncology Health Records in Portuguese

Autores
Sousa, H; Pasquali, A; Jorge, A; Santos, CS; Lopes, MA;

Publicação
38TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2023

Abstract
Textual health records of cancer patients are usually protracted and highly unstructured, making it very time-consuming for health professionals to get a complete overview of the patient's therapeutic course. As such limitations can lead to suboptimal and/or inefficient treatment procedures, healthcare providers would greatly benefit from a system that effectively summarizes the information of those records. With the advent of deep neural models, this objective has been partially attained for English clinical texts, however, the research community still lacks an effective solution for languages with limited resources. In this paper, we present the approach we developed to extract procedures, drugs, and diseases from oncology health records written in European Portuguese. This project was conducted in collaboration with the Portuguese Institute for Oncology which, besides holding over 10 years of duly protected medical records, also provided oncologist expertise throughout the development of the project. Since there is no annotated corpus for biomedical entity extraction in Portuguese, we also present the strategy we followed in annotating the corpus for the development of the models. The final models, which combined a neural architecture with entity linking, achieved..1 scores of 88.6, 95.0, and 55.8 per cent in the mention extraction of procedures, drugs, and diseases, respectively.

2023

Design participativo e economia solidária: em busca de um co-design possível

Autores
Melezinski, HV; Costa, MF; Amorim, ML; Deina, WJ;

Publicação
Revista Tecnologia e Sociedade

Abstract
Reconhecendo as discussões em andamento no movimento da Economia Popular Solidáriano Brasil e tomando como base a pesquisa desenvolvida com a Rede de padariascomunitárias Fermento na Massa, este artigo conta sobre o retorno das atividades da Redepós Covid-19, a aproximação das pesquisadoras com a Rede e a troca que fizemos entreconhecimentos de design gráfico das pesquisadoras e as experiências como trabalhadorasda Economia Solidária. A partir disso buscamos discutir as relações entre a prática do designe a Economia Solidária, dialogando com os conceitos de design participativo e autogestãona prática da Economia Solidária buscamos refletir sobre as possibilidades de uma práticade um design mais solidário, co-produzido e buscando maior autonomia das trabalhadorasnos processos de comunicação e venda.

2023

Artificial intelligence and the future in health policy, planning and management

Autores
Lopes, MA; Martins, H; Correia, T;

Publicação
INTERNATIONAL JOURNAL OF HEALTH PLANNING AND MANAGEMENT

Abstract
[No abstract available]

2022

Fostering Customer Bargaining and E-Procurement Through a Decentralised Marketplace on the Blockchain

Autores
Martins, J; Parente, M; Amorim Lopes, M; Amaral, L; Figueira, G; Rocha, P; Amorim, P;

Publicação
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT

Abstract
Firms have available many forms of collaboration, including cooperatives or joint ventures, in this way leveraging their market power. Customers, however, are atomic agents with few mechanisms for collaborating, leading to an unbalanced buyer-supplier relationship and economic surpluses that shift to producers. Some group buying websites helped alleviate the problem by offering bulk discounts, but more advancements can be made with the emergence of technologies, such as the blockchain. In this article, we propose a customer-push e-marketplace built on top of Ethereum, where customers can aggregate their proposals, and suppliers try to outcompete each other in reverse auction bids to fulfil the order. Furthermore, smart contracts make it possible to automate many operational activities, such as payment escrows/release upon delivery confirmation, increasing the efficiency along the supply chain. The implementation of this network is expected to improve market efficiency by reducing transaction costs, time delays, and information asymmetry. Furthermore, concepts such as increased bargaining power and economies of scale, and their effects in buyer-supplier relationships, are also explored.

Teses
supervisionadas

2023

Using data science methods for forecasting and managing the inventory of community pharmacies

Autor
Gabriel Fraga Outeiro

Instituição
UP-FEUP

2023

Desenho e implementação de uma estratégia de pull-flow numa indústria de ciclismo

Autor
Raquel Maria Antunes Carvalho

Instituição
UP-FEUP

2023

Banking and Blockchain Adoption: Use Cases Analysis

Autor
Vitor Hugo Ferreira Roque

Instituição
UP-FEUP

2023

Unveiling the Gender Disparities in Sickness Benefits: A Comprehensive Analysis of Socioeconomic and Demographic Factors

Autor
João Nuno da Rocha Oliveira Gomes

Instituição
UP-FEUP

2023

Design, requirements gathering, set-up and implementation of a marketing automation platform

Autor
Ana Rita da Silva Oliveira

Instituição
UP-FEUP