Mercedes Barrachina Fernández
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Mercedes Barrachina Fernández has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Carmen Sánchez Ávila
Universidad Politécnica de Madrid, Departamento de Matemática Aplicada a las TIC, Madrid, España
4 shared publications Carmen Calderón Patier
CEU University
3 shared publications- Marcos Moreno-Verdú
Brain, Action, And Skill Laboratory, Institute of Neurosciences, UCLouvain, Belgium
3 shared publications - Francisco José Sánchez-Cuesta
Brain Injury and Movement Disorders Neurorehabilitation Group (GINDAT), Institute of Life Sciences, Universidad Francisco de Vitoria, Pozuelo de Alarcón, Spain
2 shared publications - Maria-Carmen Garcia-Centeno
Department of Mathematics and Data Science Universidad San Pablo‐CEU, CEU Universities Madrid Spain
2 shared publications María del Carmen García Centeno
CEU University
2 shared publications
Latest Publications
- Open Access
- 30 August 2024
- Published by Universidad Politecnica de Madrid - University Library
Evaluación de un sistema de identificación de fluctuaciones (estado ON/OFF) en enfermos de Parkinson
Parkinson's disease (PD) is the second most common neurodegenerative disorder worldwide and its annual prevalence of new cases ranges between 5 and 35 per 100,000 inhabitants [1]. The manifestations of PD are diverse and include motor and non-motor symptoms. Non-motor symptoms can affect the neuropsychiatric, cardiovascular, autonomic, genitourinary, and other systems [2]. In general, non-motor symptoms are underestimated and not recognized when defining the treatment strategy [3]. Accurate detection of motor and non-motor symptoms is crucial for the diagnosis and monitoring of the disease, as well as for treatment adjustments [4]. However, examination of patients with PD is usually done clinically, which increases the likelihood of inaccuracy if performed by non-specialized physicians. Furthermore, although motor and non-motor symptoms typically improve in response to levodopa treatment, as the disease progresses, response to medication fluctuates throughout the day [3]. This determines that the detection and/or prediction of symptom fluctuations is essential to adequately adjust therapeutic management. However, detection of such fluctuations often depends on the patients ability to remember these periods over the past few days, which can lead to inaccuracies and/or underreporting [5]. Biosignals or medical signals have become a source of patient data, which provide information about how their different organs and systems are working, allowing the analysis of cellular, biochemical and molecular factors, among others, therefore providing information about diseases being already suffered by the patient and that could be suffered in the future. The treatment of these signals began more than 50 years ago, focusing the study on the electrocardiogram signal and since then, research on the extraction of characteristics from this and other signals has increased considerably. On the other hand, Artificial Intelligence (AI) is helping to develop multiple applications in different areas, including the diagnosis and treatment of diseases in medicine. This work focuses on beginning by studying one of the biosignals most related to the sympathetic system, the electrodermal signal, and understanding what its most relevant characteristics and frequent applications are. Subsequently, the main symptoms associated with Parkinson's, diagnostic criteria and different treatments are identified. The use of multiple biosignals has been investigated in Parkinson's patients; however, the use of skin conductance measurements has not been systematically reviewed, so a study will, first be carried out to analyze the devices used, the purpose of the study, the measurements evaluated and the processing and analysis methods applied to the signals. Currently there are different devices focused on identifying the characteristics of PD, which evaluate the motor symptoms and help in the management of the disease. The identification of symptom fluctuations is key to improve the patients life, therefore, this work has focused on the investigation of the use of sensors to identify ON/OFF states in patients with PD, and evaluate the application of ML techniques to differentiate between ON/OFF states. Once this theoretical analysis is concluded, different models will be proposed to model the ON/OFF states in Parkinson's patients, using models based on SVM and different configurations of neural networks. The last step of this study focuses on carrying out an exploratory analysis of the relationship between the electrodermal signal and the electroencephalogram signal also in Parkinson's patients, seeking to define correlations that could be used in future lines of research. Finally, the main conclusions of this research and some open lines as a continuation of this work are detailed. RESUMEN La enfermedad de Parkinson (EP) es el segundo trastorno neurodegenerativo más común en todo el mundo y su prevalencia anual de nuevos casos oscila entre 5 y 35 por 100.000 habitantes [1]. Las manifestaciones de la EP son diversas e incluyen síntomas motores y no motores. Los síntomas no motores pueden afectar los sistemas neuropsiquiátrico, cardiovascular, autónomo, genitourinario y otros [2]. En general, los síntomas no motores se subestiman y no se reconocen al definir la estrategia de tratamiento [3]. La detección precisa de los síntomas motores y no motores es crucial para el diagnóstico y seguimiento de la enfermedad, así como para los ajustes del tratamiento [4]. Sin embargo, la exploración de los pacientes con EP suele realizarse clínicamente, lo que aumenta la probabilidad de inexactitud si la realizan médicos no especializados. Además, a pesar de que los síntomas motores y no motores suelen mejorar en respuesta al tratamiento con levodopa, a medida que avanza la enfermedad, la respuesta a la medicación fluctúa durante el día [3]. Esto determina que la detección y/o predicción de las fluctuaciones de los síntomas es fundamental para ajustar adecuadamente el manejo terapéutico. Sin embargo, la detección de tales fluctuaciones suele depender de la capacidad del paciente para recordar estos períodos durante los últimos días, lo que puede dar lugar a imprecisiones y/o subregistro [5]. Las bioseñales o señales médicas se han convertido en una fuente de datos del paciente, facilitando, por tanto, información sobre las enfermedades que está sufriendo el paciente o que podría sufrir en un futuro. Por otro lado, la Inteligencia Artificial (IA) está ayudando a desarrollar múltiples aplicaciones en diferentes campos, entre ellas el diagnóstico y tratamiento de enfermedades en medicina. Este trabajo se centra en comenzar estudiando una de las bioseñales más relacionadas con el sistema simpático, la señal electrodermal y entender cuáles son...
- 30 August 2024
- Published by Universidad Politecnica de Madrid - University Library
Open AccessEvaluación de un sistema de identificación de fluctuaciones (estado ON/OFF) en enfermos de Parkinson
Parkinson's disease (PD) is the second most common neurodegenerative disorder worldwide and its annual prevalence of new cases ranges between 5 and 35 per 100,000 inhabitants [1]. The manifestations of PD are diverse and include motor and non-motor symptoms. Non-motor symptoms can affect the neuropsychiatric, cardiovascular, autonomic, genitourinary, and other systems [2]. In general, non-motor symptoms are underestimated and not recognized when defining the treatment strategy [3]. Accurate detection of motor and non-motor symptoms is crucial for the diagnosis and monitoring of the disease, as well as for treatment adjustments [4]. However, examination of patients with PD is usually done clinically, which increases the likelihood of inaccuracy if performed by non-specialized physicians. Furthermore, although motor and non-motor symptoms typically improve in response to levodopa treatment, as the disease progresses, response to medication fluctuates throughout the day [3]. This determines that the detection and/or prediction of symptom fluctuations is essential to adequately adjust therapeutic management. However, detection of such fluctuations often depends on the patients ability to remember these periods over the past few days, which can lead to inaccuracies and/or underreporting [5]. Biosignals or medical signals have become a source of patient data, which provide information about how their different organs and systems are working, allowing the analysis of cellular, biochemical and molecular factors, among others, therefore providing information about diseases being already suffered by the patient and that could be suffered in the future. The treatment of these signals began more than 50 years ago, focusing the study on the electrocardiogram signal and since then, research on the extraction of characteristics from this and other signals has increased considerably. On the other hand, Artificial Intelligence (AI) is helping to develop multiple applications in different areas, including the diagnosis and treatment of diseases in medicine. This work focuses on beginning by studying one of the biosignals most related to the sympathetic system, the electrodermal signal, and understanding what its most relevant characteristics and frequent applications are. Subsequently, the main symptoms associated with Parkinson's, diagnostic criteria and different treatments are identified. The use of multiple biosignals has been investigated in Parkinson's patients; however, the use of skin conductance measurements has not been systematically reviewed, so a study will, first be carried out to analyze the devices used, the purpose of the study, the measurements evaluated and the processing and analysis methods applied to the signals. Currently there are different devices focused on identifying the characteristics of PD, which evaluate the motor symptoms and help in the management of the disease. The identification of symptom fluctuations is key to improve the patients life, therefore, this work has focused on the investigation of the use of sensors to identify ON/OFF states in patients with PD, and evaluate the application of ML techniques to differentiate between ON/OFF states. Once this theoretical analysis is concluded, different models will be proposed to model the ON/OFF states in Parkinson's patients, using models based on SVM and different configurations of neural networks. The last step of this study focuses on carrying out an exploratory analysis of the relationship between the electrodermal signal and the electroencephalogram signal also in Parkinson's patients, seeking to define correlations that could be used in future lines of research. Finally, the main conclusions of this research and some open lines as a continuation of this work are detailed. RESUMEN La enfermedad de Parkinson (EP) es el segundo trastorno neurodegenerativo más común en todo el mundo y su prevalencia anual de nuevos casos oscila entre 5 y 35 por 100.000 habitantes [1]. Las manifestaciones de la EP son diversas e incluyen síntomas motores y no motores. Los síntomas no motores pueden afectar los sistemas neuropsiquiátrico, cardiovascular, autónomo, genitourinario y otros [2]. En general, los síntomas no motores se subestiman y no se reconocen al definir la estrategia de tratamiento [3]. La detección precisa de los síntomas motores y no motores es crucial para el diagnóstico y seguimiento de la enfermedad, así como para los ajustes del tratamiento [4]. Sin embargo, la exploración de los pacientes con EP suele realizarse clínicamente, lo que aumenta la probabilidad de inexactitud si la realizan médicos no especializados. Además, a pesar de que los síntomas motores y no motores suelen mejorar en respuesta al tratamiento con levodopa, a medida que avanza la enfermedad, la respuesta a la medicación fluctúa durante el día [3]. Esto determina que la detección y/o predicción de las fluctuaciones de los síntomas es fundamental para ajustar adecuadamente el manejo terapéutico. Sin embargo, la detección de tales fluctuaciones suele depender de la capacidad del paciente para recordar estos períodos durante los últimos días, lo que puede dar lugar a imprecisiones y/o subregistro [5]. Las bioseñales o señales médicas se han convertido en una fuente de datos del paciente, facilitando, por tanto, información sobre las enfermedades que está sufriendo el paciente o que podría sufrir en un futuro. Por otro lado, la Inteligencia Artificial (IA) está ayudando a desarrollar múltiples aplicaciones en diferentes campos, entre ellas el diagnóstico y tratamiento de enfermedades en medicina. Este trabajo se centra en comenzar estudiando una de las bioseñales más relacionadas con el sistema simpático, la señal electrodermal y entender cuáles son...
- Open Access
- 19 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 32 (15344320) , 2654-2664
AMBER: A Device for Hand Motor and Cognitive Rehabilitation—Development and Proof of Concept
Stroke survivors usually exhibit concurrent motor and cognitive impairment. Historically, rehabilitation strategies post-stroke occur separately in terms of motor and cognitive functions. However, recent studies show that hand motor interventions can have a positive impact on cognitive recovery. In this work, we introduce AMBER (portAble and Modular device for comprehensive Brain Evaluation and Rehabilitation), a new device developed for the evaluation and rehabilitation of both hand motor function and cognition simultaneously. AMBER is a simple, portable, ergonomic and cheap device based on Force Sensitive Resistors, in which every finger interaction is recorded to provide information about finger strength, processing speed, and memory status. This paper presents the requirements of the device and the design of the system. In addition, a pilot study was conducted with 36 healthy individuals using the evaluation module of the device to assess its psychometric properties, as test-retest reliability and measurement error. Its validity was also evaluated comparing its measurements with three different gold standards for strength, processing speed and memory. The device showed good test-retest reliability for strength (ICC =0.741-0.852), reaction time (ICC =0.715 – 0.900) and memory (ICC =0.556-0.885). These measures were correlated with their corresponding gold standards (r =0.780-890). AMBER shows great potential to impact hand rehabilitation, offering therapists a valid, reliable and versatile tool to comprehensively assess patients. With ongoing advancements and refinements, it has the opportunity to significantly impact rehabilitation practices and improve patient outcomes.
- 19 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 32 (15344320) , 2654-2664
Open AccessAMBER: A Device for Hand Motor and Cognitive Rehabilitation—Development and Proof of Concept
Stroke survivors usually exhibit concurrent motor and cognitive impairment. Historically, rehabilitation strategies post-stroke occur separately in terms of motor and cognitive functions. However, recent studies show that hand motor interventions can have a positive impact on cognitive recovery. In this work, we introduce AMBER (portAble and Modular device for comprehensive Brain Evaluation and Rehabilitation), a new device developed for the evaluation and rehabilitation of both hand motor function and cognition simultaneously. AMBER is a simple, portable, ergonomic and cheap device based on Force Sensitive Resistors, in which every finger interaction is recorded to provide information about finger strength, processing speed, and memory status. This paper presents the requirements of the device and the design of the system. In addition, a pilot study was conducted with 36 healthy individuals using the evaluation module of the device to assess its psychometric properties, as test-retest reliability and measurement error. Its validity was also evaluated comparing its measurements with three different gold standards for strength, processing speed and memory. The device showed good test-retest reliability for strength (ICC =0.741-0.852), reaction time (ICC =0.715 – 0.900) and memory (ICC =0.556-0.885). These measures were correlated with their corresponding gold standards (r =0.780-890). AMBER shows great potential to impact hand rehabilitation, offering therapists a valid, reliable and versatile tool to comprehensively assess patients. With ongoing advancements and refinements, it has the opportunity to significantly impact rehabilitation practices and improve patient outcomes.
- Open Access
- 29 November 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (23) , 4822
Advanced Analysis of Electrodermal Activity Measures to Detect the Onset of ON State in Parkinson’s Disease
Background: Electrodermal activity (EDA) serves as a prominent biosignal for assessing sympathetic activation across various scenarios. Prior research has suggested a connection between EDA and fluctuations in Parkinson’s disease (PD), but its precise utility in reliably detecting these fluctuations has remained unexplored. This study aims to evaluate the efficacy of both basic and advanced analyses of EDA changes in identifying the transition to the ON state following dopaminergic medication administration in individuals with PD. Methods: In this observational study, 19 individuals with PD were enrolled. EDA was continuously recorded using the Empatica E4 device, worn on the wrist, during the transition from the OFF state to the ON state following levodopa intake. The raw EDA signal underwent preprocessing and evaluation through three distinct approaches. A logistic regression model was constructed to assess the significance of variables predicting the ON/OFF state, and support vector machine (SVM) models along with various Neural Network (NN) configurations were developed for accurate state prediction. Results: Differences were identified between the ON and OFF states in both the time and frequency domains, as well as through the utilization of convex optimization techniques. SVM and NN models demonstrated highly promising results in effectively distinguishing between the OFF and ON states. Conclusions: Evaluating sympathetic activation changes via EDA measures holds substantial promise for detecting non-motor fluctuations in PD. The SVM algorithm, in particular, yields precise outcomes for predicting these non-motor fluctuation states.
- 29 November 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (23) , 4822
Open AccessAdvanced Analysis of Electrodermal Activity Measures to Detect the Onset of ON State in Parkinson’s Disease
Background: Electrodermal activity (EDA) serves as a prominent biosignal for assessing sympathetic activation across various scenarios. Prior research has suggested a connection between EDA and fluctuations in Parkinson’s disease (PD), but its precise utility in reliably detecting these fluctuations has remained unexplored. This study aims to evaluate the efficacy of both basic and advanced analyses of EDA changes in identifying the transition to the ON state following dopaminergic medication administration in individuals with PD. Methods: In this observational study, 19 individuals with PD were enrolled. EDA was continuously recorded using the Empatica E4 device, worn on the wrist, during the transition from the OFF state to the ON state following levodopa intake. The raw EDA signal underwent preprocessing and evaluation through three distinct approaches. A logistic regression model was constructed to assess the significance of variables predicting the ON/OFF state, and support vector machine (SVM) models along with various Neural Network (NN) configurations were developed for accurate state prediction. Results: Differences were identified between the ON and OFF states in both the time and frequency domains, as well as through the utilization of convex optimization techniques. SVM and NN models demonstrated highly promising results in effectively distinguishing between the OFF and ON states. Conclusions: Evaluating sympathetic activation changes via EDA measures holds substantial promise for detecting non-motor fluctuations in PD. The SVM algorithm, in particular, yields precise outcomes for predicting these non-motor fluctuation states.
- 6 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (22) , 26900-26909
Skin Conductance Assessment in Parkinson’s Disease: A Systematic Review
Multiple biosignals have been investigated in people with Parkinson’s disease (PD), but the use of skin conductance measures has not been systematically reviewed. Following the PRISMA standards, we electronically searched for studies investigating the use of skin conductance measures as a biomarker and clinical assessment in people with PD in three databases (2012-2022). The main purpose of the acquisition, the device to record it, as well as pre-processing and analysis methods were analyzed. Methodological quality was assessed using the STROBE checklist. Twenty-four studies with 940 participants were included. Eighteen acquired the electrodermal activity (EDA) and 6 the electrochemical skin conductance (ESC). These measures were used as a diagnostic tool and to assess autonomic and/or sudomotor disfunction, under-stand decision-making and learning processes and detect gait freezing or non-motor fluctuations. Fourteen devices recorded EDA and one ESC. Most studies did not pre-process the EDA/ESC signals or applied simple analyses. The EDA was analyzed only in the temporal domain in 23 studies. Analysis of the ESC signal was very limited. Moderate methodological quality was found. There is large heterogeneity not only on the devices to capture skin conductance but also on the signal processing methods. Clinical application of EDA/ESC could be of great value to detect non-motor fluctuations or to correlate with other observations, but the lack of normative values makes it difficult.
- 6 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (22) , 26900-26909
Skin Conductance Assessment in Parkinson’s Disease: A Systematic Review
Multiple biosignals have been investigated in people with Parkinson’s disease (PD), but the use of skin conductance measures has not been systematically reviewed. Following the PRISMA standards, we electronically searched for studies investigating the use of skin conductance measures as a biomarker and clinical assessment in people with PD in three databases (2012-2022). The main purpose of the acquisition, the device to record it, as well as pre-processing and analysis methods were analyzed. Methodological quality was assessed using the STROBE checklist. Twenty-four studies with 940 participants were included. Eighteen acquired the electrodermal activity (EDA) and 6 the electrochemical skin conductance (ESC). These measures were used as a diagnostic tool and to assess autonomic and/or sudomotor disfunction, under-stand decision-making and learning processes and detect gait freezing or non-motor fluctuations. Fourteen devices recorded EDA and one ESC. Most studies did not pre-process the EDA/ESC signals or applied simple analyses. The EDA was analyzed only in the temporal domain in 23 studies. Analysis of the ESC signal was very limited. Moderate methodological quality was found. There is large heterogeneity not only on the devices to capture skin conductance but also on the signal processing methods. Clinical application of EDA/ESC could be of great value to detect non-motor fluctuations or to correlate with other observations, but the lack of normative values makes it difficult.
- 27 August 2022
- Published by Springer Nature
- p. 143-151
Brazilian Entrepreneurship: Implications for ASEAN Countries
- 27 August 2022
- Published by Springer Nature
- p. 143-151
Brazilian Entrepreneurship: Implications for ASEAN Countries
- 17 June 2022
- Published by IGI Global Scientific Publishing
- p. 163-182
Machine Learning Techniques to Diagnose and Treat Cancer Disease
Cancer is one of the most common diseases nowadays, and it is a very heterogeneous disease that consists of several different subtypes. According to data from the World Health Organization (WHO), this disease caused death to approximately 10 million people during 2020, and in the same period, 19.3 million new cases were identified. Breast cancer is the most common cancer diagnosed for women, and lung cancer is the most detected cancer in men. Artificial intelligence has many different applications, and specifically, machine learning techniques are used for detecting and treating cancer. The methods associated with machine learning are computer algorithms that are considering different types of logic, and therefore, those types can be classified into supervised, unsupervised, reinforcement learning, self-supervised learning, active learning, etc. The main purpose of this work is to review and evaluate the different techniques associated to machine learning used by medical professionals but also by researchers with the main objectives of detecting and treating cancer. Request access from your librarian to read this chapter's full text.
- 17 June 2022
- Published by IGI Global Scientific Publishing
- p. 163-182
Machine Learning Techniques to Diagnose and Treat Cancer Disease
Cancer is one of the most common diseases nowadays, and it is a very heterogeneous disease that consists of several different subtypes. According to data from the World Health Organization (WHO), this disease caused death to approximately 10 million people during 2020, and in the same period, 19.3 million new cases were identified. Breast cancer is the most common cancer diagnosed for women, and lung cancer is the most detected cancer in men. Artificial intelligence has many different applications, and specifically, machine learning techniques are used for detecting and treating cancer. The methods associated with machine learning are computer algorithms that are considering different types of logic, and therefore, those types can be classified into supervised, unsupervised, reinforcement learning, self-supervised learning, active learning, etc. The main purpose of this work is to review and evaluate the different techniques associated to machine learning used by medical professionals but also by researchers with the main objectives of detecting and treating cancer. Request access from your librarian to read this chapter's full text.
- Open Access
- 1 January 2022
- Published by IGI Global Scientific Publishing in International Journal of Applied Behavioral Economics
- Vol. 11 (1) , 1-14
Comparative Analysis of Factors Influencing Informal Investors of Spain and the United States
Informal investors play a significant and critical role in the investment field. Apart from that, informal investors promote entrepreneurship as they are a funding source especially for small and micro entrepreneurs. The objective of this analysis is to identify the factors that characterize the informal investors in Spain and the United States. The basis for this analysis is the data from the website Global Entrepreneurship Monitor (GEM) from the period 2001-2015 at the global individual level for Spain and for United Sates. The purpose is to compare the existing differences between the factors that characterize an informal investor in different economic periods (pre-crisis, crisis, post-crisis) in two different entrepreneurial environments, Spain and United States, to identify measures or actions that can be implemented by the national and local organisms to promote informal investment and entrepreneurship.
- 1 January 2022
- Published by IGI Global Scientific Publishing in International Journal of Applied Behavioral Economics
- Vol. 11 (1) , 1-14
Open AccessComparative Analysis of Factors Influencing Informal Investors of Spain and the United States
Informal investors play a significant and critical role in the investment field. Apart from that, informal investors promote entrepreneurship as they are a funding source especially for small and micro entrepreneurs. The objective of this analysis is to identify the factors that characterize the informal investors in Spain and the United States. The basis for this analysis is the data from the website Global Entrepreneurship Monitor (GEM) from the period 2001-2015 at the global individual level for Spain and for United Sates. The purpose is to compare the existing differences between the factors that characterize an informal investor in different economic periods (pre-crisis, crisis, post-crisis) in two different entrepreneurial environments, Spain and United States, to identify measures or actions that can be implemented by the national and local organisms to promote informal investment and entrepreneurship.
- Open Access
- 31 October 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (21) , 12047
Women Sustainable Entrepreneurship: Review and Research Agenda
In various regions of the world, there is great concern about existing gender differences, which could affect opportunities for economic growth, and how to mitigate them. Entrepreneurship is of great importance to the economy and in a global society, and it is a hot topic for interested public decision makers due to its growing importance in economic activity—as it creates jobs, increases competitiveness and modernizes the economy. Sustainability is also a critical topic when designing the future economy, and combining female entrepreneurship with sustainability results in a very interesting topic to be evaluated when pursuing sustainable development. This paper tries to shed light on the relationship between female entrepreneurship and sustainability by analyzing 28 different papers from the Web of Science (WoS) database. Its main conclusion supports the idea that awareness of women is relevant to sustainability when starting a new company. However, further research is required due to the novelty of the topic and also the existing gaps in knowledge.
- 31 October 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (21) , 12047
Open AccessWomen Sustainable Entrepreneurship: Review and Research Agenda
In various regions of the world, there is great concern about existing gender differences, which could affect opportunities for economic growth, and how to mitigate them. Entrepreneurship is of great importance to the economy and in a global society, and it is a hot topic for interested public decision makers due to its growing importance in economic activity—as it creates jobs, increases competitiveness and modernizes the economy. Sustainability is also a critical topic when designing the future economy, and combining female entrepreneurship with sustainability results in a very interesting topic to be evaluated when pursuing sustainable development. This paper tries to shed light on the relationship between female entrepreneurship and sustainability by analyzing 28 different papers from the Web of Science (WoS) database. Its main conclusion supports the idea that awareness of women is relevant to sustainability when starting a new company. However, further research is required due to the novelty of the topic and also the existing gaps in knowledge.
- 26 September 2021
- Published by Springer Nature
- p. 47-60
Analysis of the European Women Entrepreneurship in STEM Fields
- 26 September 2021
- Published by Springer Nature
- p. 47-60
Analysis of the European Women Entrepreneurship in STEM Fields
- Open Access
Wearable Technology to Detect Motor Fluctuations in Parkinson’s Disease Patients: Current State and Challenges
Monitoring of motor symptom fluctuations in Parkinson’s disease (PD) patients is currently performed through the subjective self-assessment of patients. Clinicians require reliable information about a fluctuation’s occurrence to enable a precise treatment rescheduling and dosing adjustment. In this review, we analyzed the utilization of sensors for identifying motor fluctuations in PD patients and the application of machine learning techniques to detect fluctuations. The review process followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Ten studies were included between January 2010 and March 2021, and their main characteristics and results were assessed and documented. Five studies utilized daily activities to collect the data, four used concrete scenarios executing specific activities to gather the data, and only one utilized a combination of both situations. The accuracy for classification was 83.56–96.77%. In the studies evaluated, it was not possible to find a standard cleaning protocol for the signal captured, and there is significant heterogeneity in the models utilized and in the different features introduced in the models (using spatiotemporal characteristics, frequential characteristics, or both). The two most influential factors in the good performance of the classification problem are the type of features utilized and the type of model.
Open AccessWearable Technology to Detect Motor Fluctuations in Parkinson’s Disease Patients: Current State and Challenges
Monitoring of motor symptom fluctuations in Parkinson’s disease (PD) patients is currently performed through the subjective self-assessment of patients. Clinicians require reliable information about a fluctuation’s occurrence to enable a precise treatment rescheduling and dosing adjustment. In this review, we analyzed the utilization of sensors for identifying motor fluctuations in PD patients and the application of machine learning techniques to detect fluctuations. The review process followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Ten studies were included between January 2010 and March 2021, and their main characteristics and results were assessed and documented. Five studies utilized daily activities to collect the data, four used concrete scenarios executing specific activities to gather the data, and only one utilized a combination of both situations. The accuracy for classification was 83.56–96.77%. In the studies evaluated, it was not possible to find a standard cleaning protocol for the signal captured, and there is significant heterogeneity in the models utilized and in the different features introduced in the models (using spatiotemporal characteristics, frequential characteristics, or both). The two most influential factors in the good performance of the classification problem are the type of features utilized and the type of model.