AB+K- Use of Information Technologies for the Rational Prescription of Antimicrobials in Intensive Care Medicine

  • Principal Investigator: António Megre Sarmento

Adaptive Learning Systems II

Análise Automatizada do Cardiotocograma na Gravidez Gemelar: Desenvolvimento e Avaliação

Anemia por Deficiência de Ferro e Terapêutica com Ferro: Efeitos nos Testes de Desenvolvimento na Criança

ARTTS – Assistive Real-Time Technology in Singing

Project description: Singing is perhaps the most expressive and effective modality for humans to communicate emotions, feelings, ideas, knowledge and artistic attitude. Singing is endogenous to every culture or society and it has always played a key role on the way cultural identity is shaped and transmitted across generations.
While in practice all human individuals develop an appreciation for music and singing, a significant fraction of the world population is strongly committed to educate its singing skills either motivated by personal or professional artistic realization.

It is quite a paradox however that on the transition between the XX and XXI centuries, a period in technological history known as “information age”, characterized by the ubiquity of the computer and inspired by the concept of “ambience intelligence”; the pedagogy of singing, the assessment of the quality of singing and the preventive vocal usage are poorly assisted by computers. For example, it is quite revealing that while Wakefield discusses the role of subjectivity in the communication and appreciation of singing, and concludes that the proprioceptive feedback is insufficient [Wak03], a study on the use in singing training of real-time visual feedback technology shows that it has a clear positive impact in improving singing abilities [HopO6].

This project proposal addresses those issues in an ambitious way by gathering together institutions, professionals and researchers from three complementary areas: singing pedagogy, engineering/signal processing, and medical/Laryngology. The common purpose is to articulate knowledge and know-how from the different disciplines in order to design, implement and validate innovative technologies and methodologies that are useful to singing students, teachers or professionals, namely:

  1. new technology-assisted pedagogic methodologies,
  2. real-time visual feedback of relevant quality parameters of the singing voice, and
  3. real-time monitoring and assessment of the singing voice with the purpose to prevent voice disorders.

In order to address these challenges seven tasks have been planned that include the following specific goals:

  • to promote a deep and structured knowledge concerning the voice production system, the correlation between subjective quality parameters of the singing voice (e.g., breathiness, clarity, vibrato, singer’s formant) and objective acoustic features (e.g., jitter, shimmer, harmonics to noise ratio, harmonic irregularity and extension, closing/open coefficient of the glottal pulse), the correlation between objective acoustic features and voice disorders in singing,
  • the design, realization and validation of biofeedback technologies in singing as well as technology-assisted teaching/learning methodologies,
  • the design, realization and optimization of technologies allowing the transcription of singing to musical score and including editing capabilities,
  • the robust estimation of the glottal pulse in real-time from running singing and not only from sustained vowels as it is the rule with currently existing technology with the purpose to extract information concerning the quality of the phonation or the abnormal operation of the vocal folds,
  • the design, realization and validation of technologies for the real-time assessment of the singing voice in order to monitor vocal stress, to detect risks of voice over-use and to prevent voice disorders.

The expertise and professional experience of the team that has been gathered around this project proposal not only covers the different axis of the problem, namely singing pedagogy, engineering and laryngology, but also contributes with quite relevant research results from other research projects or on-going PhD work. For example the Principal Investigator (PI) has conducted or coordinated research for more than 20 years, notably in the areas of audio coding/compression [Fer99, Fer08], acoustic signal processing [Fer06] and accurate voice/audio interpretation and transcription [Fer01, Fer02, Fer07, Fer08_2]. The PI has also been the principal promoter between 2004 and 2008 of a spin-off company in the areas of acoustic vocal assessment, biofeedback in stuttering treatment and visual feedback of the melodic line in singing. Currently the PI supervises three PhD students in the areas of new acoustic features in speech and singing, correlation between acoustic features and voice perceptual parameters, and singing to synthetic voice transcription. This team will contribute significantly to the project, namely with databases of normal and pathological voices and of singing. Project partners from the Faculty of Medicine of the University of Porto, from the School of Arts, Sound and Image of the Portuguese Catholic University and from the Performing Arts College of the Polytechnic Institute of Porto bring invaluable expertise to the project respectively in the areas of laryngology and vocal assessment (e.g., interactive systems in music, and singing teaching practice and methodologies.

Avaliação do Sistema de Análise Automática do Cardiotocograma Sisporto: Estudo Clínico, Prospectivo e Multicêntrico

CAGE – Computer Assisted Gastroenterology Examination

Project description: The main goal of the CAGE project is to explore Computer Vision and Human Computer Interaction methodologies in order to improve a clinician’s ability to diagnose Cancer quickly when facing a variety of Gastroenterology imaging modalities. While the goal of developing and deploying a full system for both clinical training and computer assisted decision is clearly too ambitious for a single project, our aims for this proposal are two-fold:

  • Research computer vision algorithms that can extract clinical information from the visual data itself.
  • Study adequate interaction mechanisms for integrating this type of technology into real gastroenterology environments.

We are motivated by the fact that cancer is a leading cause of death worldwide. From a total of 58 million deaths worldwide in 2005, cancer accounts for 7.6 million (or 13%) of all deaths [WHO08]. Gastric (or stomach) cancer is the second most lethal cancer in the World and that with highest mortality in the digestive tract among the Portuguese population. Every year approximately 1,000,000 new cases of gastric cancer are diagnosed worldwide [ACS08]. The follow-up of patients with lesions such as atrophy, intestinal metaplasia or dysplasia may lead into gastric cancer early diagnosis. If a cancer is detected early the prognosis is highly improved, motivating the development of systems that can support such detection or train clinicians to perform this task more efficiently.

Gastroenterology Imaging is today an essential tool for clinicians to detect cancer effectively. It is a rapidly evolving technological area with novel imaging devices such as Capsule, Narrowband Imaging or High-Definition Endoscopy. However, these technologies typically have a high time-price, even for an experienced clinician. The clear need for automation or semi-automation explains the increased relevance of the topic amongst Computer Vision scientists. In fact, doctors intuitively use visual features (colour and texture) in these procedures to diagnose several diseases. The medical community is aware that computer-assisted diagnosis will help and support a medical diagnosis preventing some errors and improving the health quality of their patients. Additionally, there are cases where clinical specialists are not available in the area, and therefore computer systems could provide a diagnosis to support the doctor’s work. Finally, these systems could also teach new non-experienced medical doctors, in several areas of medicine.

State of the art in computer vision research already includes several high-quality publications for Gastroenterology such as topographic segmentation for capsule endoscopy [Coim06A] or event detection [ViIaO6]. However, some literature also shows that conventional research in more traditional scenarios such as multimedia archives does not translate well to in-body imaging scenarios given that these pose difficult challenges such as poor focus and illumination properties, reduced colour spaces, absence of geometrical structures, severe lens distortion, etc. [Coim06B]. In the CAGE project we will address issues such as rotation and scale invariant texture descriptors, illumination corrected colour descriptors, or visual and clinical data fusion for statistical pattern recognition.

On the other hand we are interested in understanding how these algorithms will translate into useful tools inside a Gastroenterology exam room. Which information shall we provide the clinician? How shall we display it? How will he interact with the system? Using vocal commands or gestures? The answers to these and other similar questions are essential for obtaining a clinical tool rather than a high-tech toy. Human Computer Interaction methodologies will be used during the CAGE project to ensure that we understand the best way that the user can access and benefit from this additional layer of information.

In order to accomplish these objectives we have assembled a multidisciplinary team of specialists, all of which have experience in research involving engineers, computer scientists and clinicians. This includes experts in Gastroenterology and medical technology validation (Dr. Mário Dinis Ribeiro, CINTESIS/FMUP/IPO­Porto), Computer Vision and Human Computer Interaction (Dr. Miguel Coimbra, IT/FCUP, project’s Principal Investigator – PI), and two PhD students (in Computer Vision).

The PI is a young Professor who has returned to Portugal after his PhD in London and has 9 years of experience in Computer Vision, 5 of which in Medical Imaging research. Dr. Miguel Coimbra leads a team of PhD and Msc students, has numerous publications on the field, leads one financed project and has participated as a researcher in 4 financed projects involving clinical partners. Finally, we have obtained the commitment of collaboration of a medical institution (IPO­Porto), which will be an essential data provider and consultant.

CALLAS – Calculi and Languages for Sensor Networks

Caracterização endoscópia e histopatológica de lesões associadas a cancro gástrico

  • Proj. nº 204/2011

Chronic diseases of the airways: contents and tools for productive interactions between empowered patients and proactive professionals

Project description: The shift in the paradigm of healthcare delivery increasingly recognizes the participation of the patient in his own care. Beside the need for continuing medical education (CME), the importance given to patient education is increasing [Warsi 2004]. The models of delivery of care for chronic diseases emphasize on the patient’s participation in their own care and engaging them in decision-making [Kravitz 2001]. The Chronic Care Model defends the promotion of informed, empowered patients and families and prepared, proactive practice teams obtaining more productive interactions that lead to improved outcomes and reduced costs [Bodenheim 2002a, Bodenheim 2D02b]. In this way, education of both patients and physicians is the foundation for shared decision-making and self-management.
This explains the pertinence of a call for projects in the production and delivery of health information for both patients/general public and physicians/health students.

The Internet and related technologies represent a useful way to provide more contents (not only health information but also instruments for self-management) while reaching broader audiences.
Our proposal fits entirely in this call. We propose to develop contents and tools to be aggregated in a web platform. The contents, covering several aspects of the diseases, will be created in several formats. For each article, 3 versions will be developed, oriented to physicians/students, patients/public and audiences with limited literacy. Tools will be developed to promote shared medical decision, support disease assessment and monitoring. It is important to emphasize that we will apply standard web 2.0 technologies allowing users to be both consumers and producers of health information. Together with state- contents produced through strict procedures and continuous supervision, the input of the community will be encouraged. In this way we embrace the calls’ objective to distribute reliable, high-quality health material but also to establish links between groups and among groups, fostering productive relations. Additionally we will promote online courses and self-evaluation tests in order to foster CME.

The research team has backgrounds in Allergy & Asthma, Pulmonary Medicine, Psychiatry and Primary care Medicine and expertise in patient education, behavioural change, e-health, production of online health contents, patient centred care and training of health professionals. Members of the team have, in the past, produced information contents and interactive online tool for both patients and doctors, in different settings, mainly in the area of asthma care.

Asthma and chronic obstructive pulmonary disease (COPD) are the areas where the team has the most experience. It is important to emphasize that COPD was among the 5 leading causes of death in the world in 2001 and is foreseen to be 5th in terms of burden of disease (measured in % of total disability-adjusted life years) in 2020 [Lopez 2006, Murray 1997]. In fact, respiratory disease burden is superior to that of diabetes or HIV/AIDS. The World Health Organization recognized the impact of chronic respiratory diseases by the creation of the Global Alliance against Chronic Respiratory Diseases (GARD) [WHO 2008]. Portugal shares this view and, additionally to the dispositions in the National Health Plan, our country has dedicated National Programmes for Asthma Control and for the Prevention and Control of COPD.
In this view, we intend to implement our knowledge and previous work in asthma and COPD but also expand the scope of our interventions, creating a broad set of contents and tools for chronic diseases of the airways, comprehending asthma, COPD, rhinitis and rhinossinusitis, interstitial lung diseases and cystic fibrosis. Finally, we would like to praise the possibility to embrace this project, acknowledging the fact that it is an area of research where little is done and opportunities are sparse.

Comparative evaluation of Health Related Quality of Life and Functional Outcome, after Pediatric Intensive Care

CSI – Segurança Criptográfica de Instâncias Individuais

Development and assessment of optimal risk scores for outcomes in paediatric intensive care

DigiScope – DIGItally enhanced stethoscope for clinical usage

Project description: In the ears of an experienced physician, a stethoscope yields important clinical information which can help an initial assessment of a patient’s clinical condition and guide the subsequent need for more specialized exams. This is particularly true in chest Medicine, i.e. Cardiology and Pneumology, which is the reason why the stethoscope still maintains a key position in Medicine in the modern era. Auscultation, however, is a hard skill to master. The heart sounds are of low frequency and the intervals between events are in the order of milliseconds, requiring significant practice for a human ear to distinguish the subtle changes between a normal and a pathological heart sound. The use of a digitally enhanced stethoscope, adequate for training physicians to improve their basic skills in diagnosing and treating heart conditions, or as a stronger tool for world-wide screening of specific heart pathologies are but some examples of how state of the art technology can be used horizontally to benefit people at different economic, political or geographical levels. This motivates the key objective of the DigiScope project: develop the prototype of a digitally enhanced stethoscope, capable of automatically extracting clinical features from the collected data, as well as providing a clinical second opinion on specific heart pathologies.

A market inspection shows some commercial versions of electronic stethoscopes with different filtering options, but none provides computer assisted clinical data extraction. In addition, we found several isolated computer auscultation analysis systems referred in the literature, as described in one of our published articles [HedayO9]. Our review showed very promising  work in audio feature extraction using signal processing methodologies (e.g. S1 and S2 segmentation [Liang97]; A2 and P2 segmentation [Xu00]), and much poorer results for heart pathology detection. Furthermore, almost all research did not enforce either rigorous and extensive clinical data collection or a vital clinical validation step, both essential for understanding the viability of digitally enhanced stethoscopes in routine clinical practice.

As this proposal will detail, building a DigiScope involves not only signal processing (clinical feature extraction) and datamining (pathology detection using audio features and patient record information) but successfully accomplishing this objective requires two other key tasks: our ability to not only collect heart audio signals, but to extract patient record information by communicating directly and efficiently with typically heterogeneous and complex hospital information systems; build a framework of supporting hospitals and Cardiologists both for providing access to the large amounts of data required by the signal processing and data mining tasks, and for a rigorous clinical validation step of the developed technology. Our research team includes experts in all these four tasks such as Dr. Ricardo Correia (8 years of experience in medical information systems), Dr. Miguel Coimbra (9 years of experience in signal and image processing, 5 of which in medical signal research), Dr. Inês Dutra (8 years of experience in data mining), Dr. Almeida (5 years of experience in Cardiology) and Dr. Sandra Mattos (22 years of experience in Cardiology). Our ‘silver bullet’ is thus an experienced multi­disciplinary team, which includes experts in all fields identified as vital for the success of DigiScope, most of which have had previous experience in multi-disciplinary (medical and engineering) research projects.

Our strategy lies in accomplishing a set of core objectives for the described four tasks that will guarantee the development of a hospital integrated, clinically validated digitally enhanced stethoscope. Although this is by itself ground-breaking, we will then have a set of ambitious high-risk, advanced objectives that will also guarantee the scientific novelty of this project. As such, we do not only expect to produce a final prototype but also a reasonable number of publications in high-impact journals and conferences, as well as what will probably be the largest clinically annotated database on audio signal processing for cardiology.

Early detection of cancer using serum biomarkers based on aberrant post-translational modifications of O-glycoproteins, O-PTM-Biomarkers

Electricity load forecasting supported by prediction explanation and prediction reliability estimates

Estudo Epidemiológico da Pressão Arterial e outros Factores de Risco Cardio-vasculares em Famílias Portuguesas

Factores clínicos e económicos na evolução da utilização de recursos num hospital central: análise de registos de internamento na década de 90

HR-QoD – Quality of data (outliers, inconsistencies and errors) in hospital inpatient databases: methods and implications for data modeling, cleansing and analysis

Humanização e Qualidade nos Serviços de Saúde: Inquérito à Satisfação dos Utentes de um Centro de Saúde

ICAR – Control and Burden of Asthma and Rhinitis

Project description: Accurate data on the burden of chronic diseases is needed to set up evidence-based health policies. Asthma and rhinitis are highly prevalent respiratory diseases, causing substantial social and personal burden. Asthma and rhinitis are intrinsically related to each other. Frequently, they are co­morbidities in the same patient and the outcomes of one disease are influenced by the status of the other. However, the degree of this influence is poorly known.

During 2010, we’ve conducted two cross-sectional, telephone national surveys that assessed the prevalence (Portuguese Asthma Prevalence Survey PAPS) and the control (Portuguese Asthma Control Survey PACS) of asthma and rhinitis. Before these surveys there was no country-wide data on prevalence or about the control of asthma in Portugal. The PACS was commissioned by the Portuguese Health Directorate within the Portuguese program for the control of asthma. Of the 6003 interviews completed in PAPS, 559 participants with self-reported current asthma, 648 with self-reported current rhinitis without asthma and 753 individuals without respiratory symptoms were interviewed in PACS. The main questionnaires used were the GAZLEN survey and in CARAT (Control of Allergic Rhinitis and Asthma Test). The GAZLEN survey has been used in many European countries in the last few years.
However, no study has validated this instrument. CARAT was developed and validated by our group and was recently proposed as a first tool to implement ARIA guidelines in primary care. In spite of thorough evaluated in patients from secondary care, it has not been assessed in patients from the general population.

We propose an additional study that will apply a comprehensive set of diagnostic tests and clinical assessment to a sub-sample of participants in the PACS study. The effect of asthma, rhinitis and their control on personal and social burden will be studied comparing patients with current asthma and/or rhinitis and individuals with no respiratory symptoms. The aims of this project are: 1) to validate the survey instruments used PAPS and PACS, with clinical and objective tests and 2) to compare the disease burden of different groups of participants assessing the effect of i) the diseases and ii) its control. It will be an observational cross-sectional study which will include 750 individuals of all ages, divided in 4 groups: 1) Patients with a self-reported diagnosis of asthma alone (n=150), 2) Patients with a self-reported diagnosis of rhinitis alone (n=150), 3) Patients with a self-reported diagnosis of asthma and rhinitis (n=150) and 4) Patients with no history of respiratory symptoms or diseases (n=300). Sample size calculations were based on the comparison of quality of life measured by WHOQOL-BREF in patients with different diagnosis. Data collection includes anthropometric measurements, lung function & inflammation tests, allergy tests, a structured clinical interview and standardized questionnaires. Research assistants performing the evaluations will be blinded to the subject classification in PAPS and PACS and to the results of the questionnaires administered, namely the GA2LEN survey instrument and CARAT` The data collection will be organized with the local Public Health delegate and will take place as close as possible to the participants’ communities at a local health unit or in the surrounding area, in order to minimize dropouts.

This study will provide novel data on the burden of high-prevalence diseases, in light of the presence of asthma or rhinitis alone or together and of the control status of the diseases. This data will contribute to better estimates of the effects of health policies aiming to improve disease control and will aid the development of new policies addressing asthma and rhinitis together.

INTERCARE – Sistema Integrado de Cuidados Médicos Aplicado à Cardiotocografia e à Electrocardiografia

Knowledge Discovery from Ubiquitous Data Streams

OFELIA – Open Federated Environments Leveraging Identity and Authorization

Project description: The explosive growth of the Internet is accelerating the need to move and translate essential real world societal infrastructures to the virtual world. These invisible threads are keeping and enabling digital societies populated by digital identities that need to be managed and secured in an effective way. As a consequence, Identity management as a whole plays a fundamental role in securing access to an increasing set of systems and applications in everyday services and associated communications.

More recently, the tendency has been to concentrate on identity models conceived to facilitate user centric identity management, in concert with a digital society more focused on increasing the individual reliable management of civil liberties, like privacy and freedom.

Individuals must be given the tools to be able to easily secure and exercise for themselves their basic privacy rights. They need to be able to define how much about them is publicly known on the Internet and by whom. With the continuing growth of the number of online services, users end up having their identities scattered across multiple systems throughout Internet.  It is thus important to develop systems and processes that can help manage and control the access, and even the discloser and finality of these resources.

Federated Identity is the means by which web applications can offer users cross-domain single (SSO), which lets them authenticate once and thereafter gain access to protected resources and web sites elsewhere within the same federation domain. Federated identity management is a set of technologies and processes that let computer systems dynamically distribute identity information and delegate identity tasks across security domains [MERD08]. However attractive its benefits, federated identity imposes costs as well, entailing new and increased security and privacy risks because it shares valuable information across domains using loosely coupled network protocols [OID08]. Such risks require mitigation, which can range from preventing message replay to collecting user consent for data sharing in both online and offline scenarios.

Open ID is a decentralized system protocol ‘for user centric identification and digital identity management in the Internet. It is a “single sign on” (SSO) system, thus it eliminates the need for multiple user names and passwords across different security domains, i.e in the Open ID universe relying parties. A replying party, sometimes designated has “service provider”, is the site that wants to verify the end-user´s identifier (RDRD06). Open ID allows users to add as much attributes as they believe that best describes them and assume profiles, also called Personas.

Under this context we have developed the EOID server and associated Firefox plugin. EOID is a user friendly and more secure solution regarding identity management. It implements the OpenID 2.0 protocol combined with java smart card technology for strong authentication in the form of the new Portuguese Citizen´s Card. We have also developed a plugin for the Firefox browser in order to provide the user with the sponsorship of SAPO ISP within the 2008 summerbits initiative. 

With OFELIA, we are proposing the study, conceptualization and implementation of new ideas and extensions for federated identity management and federated authorization mechanisms by using and levering the work we have already developed for EOID (FRFADCM09). On identity management we want to explore the idea of having sensitive identity attributes directly stored on a user’s personal mobile secured wallet. This wallet could be a smart card, a PDA or even a personal mobile phone. We want to develop new extensions for the OpenID protocol that will allow for the secure communication of especially sensitive identification attributes from user a personal wallet, through the identity server, to an authorized relying party requesting them.

These attributes reside on user personal devices and can only be disclosed at the user discretion. To make this service even more user empowering and applicable under more rigorous contexts, like clinical health records, we want to further explore new ideas in the use of “valet key” authorization mechanisms for the issue and user-centric management of temporal automatic access authorization for strongly identified entities on a federation of trusted identity providers. This user centred model imposes new requirements to authentication and we also want to explore the use of biometrics in federated environments to secure the issue of valet authorization keys in contexts where the use of other authentication mechanisms like smart cards or passwords are not so appropriate, e.g on clinical settings where a doctor needs to quickly prove that he has the right to use a “valet key” that gives him access to a patients clinical record.

Outcome after severe trauma: implications for the clinical approach

Project description: Trauma is a pandemic and a health care problem all over the world. It is the main cause of death in young adults. Portugal is the leader among European countries concerning mortality after trauma. The real dimension of the problem is not well known in Portugal because of scarce data.

The first and main objective of this study is to get new knowledge on the epidemiology and other characteristics of trauma in Portugal as well as about severity and consequences in terms of mortality and morbidity. If our knowledge on mortality is limited, data on morbidity are scare. Data from Portuguese trauma system might help in the understanding of mortality and morbidity after trauma.

The first important trauma registry was the Major Trauma Outcome Study (MTOS) that started in 1975 in the United States of America. The major Trauma Outcome Study cohort has been widely used as a benchmark for comparing outcomes in patients with trauma using the TRISS methodology. It can be used to identify unexpected outcomes in populations and in individual patients.
In Europe the trauma Audit & Research Network (TARN) is a group of hospitals from all over England, Wales and even other countries in Europe. The Trauma Network (previously known as European MTOS) has been operating for the past 14 years and is a located at the University of Manchester, United Kingdom (UK). In other words TARN is concentrating the trauma data collected from all hospitals in the UK, analyzing it and producing epidemiological, clinical and audit reports.

Using its vast experience in data collection and analysis, TARN took the initiative to start a European Registry (Euro TARN) initiative consists of a regular participation of a 14 countries and support from many others who have come together to develop an effective system to review the standards of trauma care across Europe and develop an effective method for future data collection. Portugal by the participation of some elements of this team takes part in this registry.

Mortality is the worst consequence of trauma but not the only problem for those injured people. As technology improves, more people who suffer severe injury can survive. And even the less severe forms of trauma can result in significant problems that may persist, or even arise only after the injury. These individuals are often young, and otherwise healthy. Apart from different types of physical disabilities persistent cognitive, behavioural or mood disturbances can significantly affect short and long term outcomes. Patients may appear physically recovered, but problems reintegrating into family, work, or school can quickly become apparent contributing to a decrease in the quality life.

Education and appropriate interventions and referrals must be initiated as early as possible. Too often, these patients receive excellent acute care and initial rehabilitation, but then are lost to follow-up- The loop of care must be closed. A significant number of these patients can achieve good function, but will require continuous and possibly lifelong access to various components of an interdisciplinary team. This ensures maximized quality of life, and is one of the most efficient and cost-effective solution in the long run. This process should start at the initial contact with the patient and family. It should involve close collaboration between the family, patient, emergency physician, intensivist, surgeons, psychiatrists, rehabilitation medicine and other therapists, rehabilitation facilities, the workplace and community groups.

The follow-up consultation developed for this project will do the clinic at 6 months after trauma. The main objectives will be to assess and diagnose problems in the patient as well as to serve as a base for data collection and research on late outcomes. Several tests will be done with that objective namely: Mini Mental State; PTSS14; Zung inventory; BDI; Glasgow Outcome Scale – Extended and EQ-5D

OPTIM – Optimizing Information Systems for healthcare: improving Graphical User Interface and Storage Management through Machine Learning techniques on user logs data

Project description: The identification of clinically relevant information should enable an improvement in user interface design and in data management. However, it is difficult to identify what information is important in daily clinical care, and what is used only occasionally. In the healthcare domain, and especially in critical and acute care, the age of data is one of the factors often used to assess data relevance, making new information more relevant to the current search. Some authors have categorized “old data” as data at least three days old. In a pilot study, the authors of this proposal have examined for how long clinical documents are used by health professionals in a hospital environment, and how this is associated with document content and the context of information request. Our results show that some clinical reports are still used after one year regardless of the context in which they were created, although significant differences exist in reports created in distinct encounter types. We concluded that the usage of past patient data (data from previous hospital encounters) varied significantly according to the setting of healthcare and document content, which contradicts the definition of data used in previous studies.

In this project we propose to study how to estimate the relevance of healthcare information in a particular setting, aiming to use this to create adaptive user interfaces and smart high capacity data storage systems.
This project is divided into the following seven tasks: (1) collecting and preparing log data from hospital Information Systems (IS) usage; (2) studying the factors associated with the relevance of patient data; (3) defining algorithms that estimate the relevance in a particular situation for an interval of time; (4) characterizing the information visualization habits of health professionals using process mining techniques process mining techniques; (5,6) implementing two prototypes (an adaptive user interface and smart clinical data storage) and (7)evaluating the prototypes in different healthcare institutions. A diagram of the overall plan with tasks and data flows has been attached to this description.

The allocation of the task leaders follows (only indexed publications on ISI, Scopus or Medline were considered):

  • Tasks 1, 3, 5 and 6, Ricardo Correia, 34 years old, computer scientist, PhD in the integration of hospital IS, 21 publications, whose current interest is studying patient information
  • Task 2, Altamiro Costa-Pereira, 49 years old, Medical Doctor (MD), PhD in epidemiology and public health, more than 100 publications, with current interest in medical informatics.
  • Task 4. Luis Lapão, 40 years old, Physics Engineer, PhD in Medical Informatics, 5 publications, with current interest in IT Governance, Health processes and healthcare networks complexity.
  • Task 7, Jeremy Wyatt, 55 years old, MD, PhD in Medical Informatics, elected Fellow of the American College of Medical Informatics, has more than 100 indexed scientific publications and an h index of 24, with current interest in the evaluation of clinical information systems.

To our knowledge, the use of machine learning techniques to support graphical user interfaces and management storage systems is novel. The application of these methods to healthcare Information Systems will be an important contribution to science and is likely to be incorporated into commercial products in the future. The results of this research are also likely to have an important impact on the quality of healthcare by further increasing the usability and intelligence of existing Information Systems.

Perturbações Alimentares: Avaliação da Incidência, Factores de Risco e Programa de Intervenção Terapêutica

PIRO – The PIRO sepsis concept: implementation and validation of a new classification in sepsis

Project description: The definitions for SEPSIS, SEVERE SEPSIS and SEPTIC SHOCK of the last consensus conference do not allow precise characterization and staging of patients with this condition.
The PIRO concept was proposed with the 2001 SCCM/ESICM/ACCP/ATS/SIS International Sepsis Definitions Conference. The development of the Q PIRO classification scheme allows the stratification of SEPSIS patients on the basis of their (P) Predisposing conditions, the nature of the (I) Insult (in case of sepsis, infection), the nature and magnitude of the host (R) Response, and the degree of concomitant (O) Organ dysfunction.
It aroused as a template for further investigation and as a work in progress to be adopted. Its elaboration requires evaluation of sepsis in order to define the variables that predict the outcome. Until now no clear PIRO models were implemented and validated.

To develop and validate a clinically useful PIRO staging system that stratifies SEPSIS, SEVERE SEPSIS, and SEPTIC SHOCK patients by the baseline risk of an adverse outcome and the potential to respond to therapy.
Creation of a clinical decision tool that predicts outcome and potential to respond to therapy.

A 17 Intensive Care Units multicentric database of variables was created regarding to SEPSIS, SEVERE SEPSIS, and SEPTIC SHOCK variables, considered to have clinical Significance. Modelling of database/data-mining is to be performed in order to find variables with clinical relevance and establish statistics significance and to create a clinical decision tool that predicts outcome in terms of mortality and quality of life and potential to respond to therapy, Further data collection will be held to complement the existent database, allowing validation of data and decision tool.

Despite the definitions for sepsis, severe sepsis, and septic shock, these terms do not allow under the current scientific knowledge precise characterization and staging of patients with these conditions, neither a prediction of the outcome.

The analogy of the system to be developed is the TNM system, developed by Pierre Denoix in 1946, that classifies malignant tumours.
A well characterized system that allows staging and prediction of outcome would largely be of benefit both for the clinician, making clinical decision on these critical patients easier and objectively supported, and for the patient as the odds would less depend on personal beliefs rather on science basis.

Prospective multicentric study on postoperative pain in Portugal

RECIMA – Registo de Cardiopatia Isquémica da Madeira: um Instrumento para a Avaliação de Morbilidade e Mortalidade Coronárias

Registo Oncológico Pediátrico do HSJ – Análise de Sobrevida e Correlação Anátomo-Clínica

Regression methods for multiple outcomes in health research

Project description: In Health research it is typical to formalize the research question in terms of a single, unidimensional outcome. Even when the problem is intrinsically multidimensional, resulting on the collection of multiple outcomes, the most common strategy involves summarizing the outcomes into a single score using some pooling strategy or, alternatively, analyzing each outcome separately using univariate methods [1-4]. These approaches are practical, both from the point of view of comprehension/interpretation of the results and simplification of the analysis.

However, in many situations it is not possible to simplify the research question to a one-dimensional outcome (e.g. [5-8]) and the separate analysis of each outcome does not consider the problem as whole, Even in the context of clinical trials, where the topic of multiple outcomes received some attention due to the increasing number of trials with multiple endpoints, the main discussion has focused on adjustments to the significance level for multiple testing due to the individual analysis of the endpoints  The MRS study described in the “Research Plan section” is a prime example where interest lies on studying the association of several factors with 12 outcomes: 4 metabolite ratios in 3 brain regions. If the multivariate structure of the data is ignored, and each outcome is analyzed separately, we may lose the global understanding of the relationships between the factors and the outcomes.

Despite the existence of multivariate methods that can be used for the analysis of multiple outcomes, the reality is that these methods are hardly found in applied research and do not apply to many settings. For example, the multivariate regression analysis of non-commensurate outcomes (outcomes measured on different scales or mixed type of outcomes such as continuous and binary outcomes) still lacks a complete theoretical framework. The development of appropriate methodology for model selection in the multivariate setting is also seriously lacking.

In this project we propose to develop a general framework for the analysis of Health related data involving multiple outcomes, including the general situation of non-commensurate outcomes and model selection. It would be unrealistic to anticipate that we will solve the entire problem of handling multiple outcomes (for example, we do not consider longitudinal or clustered data) but we believe that we will be able to establish the foundation for other methodological extensions. In any case, we foresee that such methodology could be applied to a variety of examples, in many areas of Health research. In particular, the project is motivated, in part, by a real data example: the MRS study of long term brain damage in HIV patients, carried out by the HIV Neuroimaging Consortium at multiple sites in USA.

The three Biostatisticians involved in this proposal got to know each other at the Harvard School of Public Health during their PhD studies. However, their interest in this topic grew independently, mainly motivated by real data problems in their practice of collaborative research. Their individual methodological research interests and expertise provide an excellent combination for the success of this project. Armando Teixeira Pinto has been working on multivariate methods for non-commensurate outcomes [see references 1 and 2 of the “Past publications”], Eric Tchetgen Tchetgen is interested in robust and efficient estimation [see references 3 and 5 of the “Past publications”] and Jaroslaw Harezlak has been studying model selection methods [see references 4 and 5 of the “Past publications”].

Although this is a fairly technical and quantitative project, its results have an important and direct implication in problems related to Epidemiology, Public Health, Health Technology Assessment and Health Services Research that fully justify the submission of this project

Resposta do Sistema Hipotálamo – Hipofisário à Dor e à Acumpultura – Estudo Neuroendócrino, Experimental e Clínico

SAHIB – Enhancing multi-institutional health data availability through multi-agent systems

Project description: As its main goal, this project aims to contribute to the improvement of health data availability at the point of care.
One of the challenges facing healthcare organizations is giving all healthcare professionals complete, transparent and real-time access to patient data. However patients tend to visit multiple health institutions (e.g. hospitals, health centers or private clinics) during their lifetime, leaving a trail of scattered data.

This scenario makes integration of healthcare Information Systems (IS) essential to support the shared care of patients using health services at local, regional and international levels. Nevertheless, consistently combining data from such heterogeneous sources takes a great deal of effort because each institutional IS usually differs in several aspects, such as data models, terminology and semantics, functionalities and data presentation.

Furthermore, the different actors in healthcare make up a complex network where information is exchanged in different formats (eg. digital, paper, oral) aiming at delivering quality healthcare while maintaining patient privacy and satisfying legal requirements. However, agent-oriented modeling may provide a straightforward approach to system design, including component definition and system interaction. Heterogeneous environments may impose various requirements on the design, which can mean handled by different types of agent models. The use of multi-agent technologies has already allowed the successful integration of a large amount of heterogeneous clinical data in our own single hospital system.

The question to be investigated in this project is how to build applications that find, retrieve and deliver patient information to the point-of-care in a secure and timely fashion, even though it is distributed across multiple healthcare institutions, while safeguarding the different agendas and constraints of the different actors. In a regional or nationwide scale scenario where a multitude of IS coexist there is still a lack of efficient supporting architectures to provide clinical information at the point-of­-care.

The methods of this project includes the (1) characterization of main actors, their data needs and data flows; (2) the creation of an agents model that may assist the previously studied healthcare actors; the definition and implementation the agent functions, namely: (3) activation, (4) search, (5) communication with other systems, (6) information transport and (7) security; and (8) evaluating a prototype.
The description of the task leaders is here described (only indexed publications on ISI, Scopus or Medline were considered):

  • Task 1, Altamiro Costa­ Pereira, 49 years old, Medical Doctor (MD), PhD in epidemiology and public health, more than 100 publications, with current interest in medical informatics.
  • Task 2, John McGrory, 39 years old, Informatics Engineer, PhD in using Agents in Healthcare, 9 publications.
  • Tasks 3, 4 and 5, Ricardo Correia, 34 years old, computer scientist, PhD in the integration of hospital IS, 21 publications, current interest in studying the use of multi-agents systems in healthcare.
  • Tasks 6 and 7, Sergi Robles, Engineer in Computer Science, PhD in Mobile Agent Systems and Security, more than 60 publications, current interest in the application of agents to the healthcare domain.
  • Task 8, Jeremy Wyatt, 55 years old, MD, PhD in Medical Informatics, elected fellow of the American College of Medical Informatics, has more than 100 indexed scientific publications and an h index of 24, with current Interest in the evaluation of clinical information systems.

Other team members include: Pedro Marques, 34 years old, Computer Scientist, MSc in Computer Networks, currently doing a PhD in the use of agents in healthcare; Ana Margarida, 32 years old, Computer Scientist, MSc in Security, currently doing a PhD in securing IS in healthcare; and Filipa Almeida, 31 years old, MD, currently taking the cardiology specialty and with an interest in medical informatics.

The scientific contributions of this project are (1) a model of clinical information flow among the different actors that will provide a more clear view on how and what data is exchanged now and how and what ideally should be exchanged, and (2) a multi-agent model intended to pursuit each actor objectives regarding their information needs.The technological contributions of this project are (1) an ÑAPI that will facilitate new healthcare applications using multi-agent systems to be created, and (2) a prototype that aims at data availability improvement (finding and retrieving) with security (fault: tolerance and confidentiality).
In the case of a positive evaluation, other possible contribution of this project may be an improved acceptance of multi-agent.

Sisporto – Avaliação Multicêntrica do Sistema de Análise Automática do Cardiotocograma