PubMed Health⌕ Search

Biomedical subjects

Stefano Forti

Publications and source records attributed to Stefano Forti.

11 recordsLinked to original sources
PubMed2005

Ontologies supporting continuity of care: the case of heart failure.

Heart failure can be the final stage of almost any type of cardiovascular diseases. Such diseases are the leading cause of recurrent hospital stay and mortality in developed countries, and an increasingly important cause of morbidity and mortality in developing countries. In consideration of the growing incidence of this syndrome, the Province of Trento (Northern Italy) supports a research project called e-Heart Failure. The aims of this project include the implementation of a web-based patient record management system which must allow all the professionals involved in the care process to provide a shared and continuous care. This paper emphasizes the role of ontologies in supporting the continuity of care. In a complex scenario where multiple agents co-operate in order to allow continuity of care, ontologies are the essential glue to ensure semantic consistency to data and knowledge shared by the different actors involved in the process, including patients and their families.

Continuity of Patient Care↗
PubMed2005

A real time Teleconsultation System for Sharing an Oncologic Web-based Electronic Medical Record.

This poster presents an innovative real-time Teleconsultation System for synchronized navigation of the pages of a web-based Oncological Electronic Medical Record, designed to provide clinicians a cooperative work tool supporting the oncologic patient management between different hospitals. The system embeds additional tools supporting the discussion: digital whiteboard, chat and a digital audio channel.

Computer Systems↗
PubMed2005

An interactive real-time visualization environment for patients with heart failure.

We present an interactive real-time visualization environment of time-ordered medical data aimed to support multidisciplinary disease management of patients with heart failure. Our prototype has been integrated into a working Electronic Patient Record implemented for the integrated management of heart failure patients. Since January 2005, the system has been evaluating in a clinical setting to assess its practical utility involving 30 General Practitioners, 7 Hospital Physicians and 50 Hospital and Community Nurses.

Computer Systems↗
PubMed2005

OncoQUAL: a clinical instrument panel for quality assessment in cancer care.

We present OncoQUAL, a clinical instrument panel for quality assessment in cancer care. OncoQUAL is fully integrated in an oncological electronic patient record (OEPR) and it enables oncologists to interactively retrieve clinical data for performing process and outcome-based measures of quality of care. The capability of incorporating accurate and timely 'internal' quality measurements into the daily work of clinicians is essential for moving towards a user-oriented approach to the improvement of quality of care processes.

Databases as Topic↗
PubMed2004

Clinical validation of an automated system for supporting the early diagnosis of melanoma.

BACKGROUND: Early diagnosis and surgical excision is the most effective treatment of melanoma. Well-trained dermatologists reach a high level of diagnostic accuracy with good sensitivity and specificity. Their performances increase using some technical aids as digital epiluminescence microscopy. Several studies describe the development of computerized systems whose aim is supporting dermatologists in the early diagnosis of melanoma. In many cases, the performances of those systems were comparable to those of dermatologists. However, this cannot tell us whether a system is able to support dermatologists. Actually, the computerized system might correctly recognize the same lesions that the dermatologist does, without providing them any useful advice and therefore being useless in recognizing early malignant lesions. PURPOSE: We present a novel approach to enhance dermatologists' performances in the diagnosis of early melanoma. We provide results of our evaluation of a computerized system combined with dermatologists. METHODS: A Multiple-Classifier system was developed on a set of 152 cases and combined to a group of eight dermatologists to support them by improving their sensitivity. RESULTS: The eight dermatologists have average sensitivity and specificity values of 0.83 and 0.66, respectively. The Multiple-Classifier system performs as well as the eight dermatologists (sensitivity range: 0.75-0.86; specificity range: 0.64-0.89). The combination with the dermatologists shows an average improvement of 11% (P=0.022) of dermatologists' sensitivity. CONCLUSION: Our results suggest that an automated system can be effective in supporting dermatologists because it recognizes different malignant melanomas with respect to the dermatologists.

Dermatology↗
PubMed2003

A multiple classifier system for early melanoma diagnosis.

Melanoma is the most dangerous skin cancer and early diagnosis is the key factor in its successful treatment. Well-trained dermatologists reach a diagnosis via visual inspection, and reach sensitivity and specificity levels of about 80%. Several computerised diagnostic systems were reported in the literature using different classification algorithms. In this paper, we will illustrate a novel approach by which a suitable combination of different classifiers is used in order to improve the diagnostic performances of single classifiers. We used three different kinds of classifiers, namely linear discriminant analysis (LDA), k-nearest neighbour (k-NN) and a decision tree, the inputs of which are 38 geometric and colorimetric features automatically extracted from digital images of skin lesions. Multiple classifiers were generated by combining the diagnostic outputs of single classifiers with appropriate voting schemata. This approach was evaluated on a set of 152 digital skin images. We compared the performances of multiple classifiers (2- and 3-classifier groups) between them and with respect to single ones (1-classifier group). We further compared the classifiers' performances with those of eight dermatologists. Classifiers' performances were measured in terms of distance from the ideal classifier. Compared with 1- and 2-classifier groups, performances of 3-classifier systems were significantly higher (P<0.0005 and P<0.001, respectively). No statistically significant differences were found between the 1- and 2-classifier groups (P=0.352). While the dermatologists group showed a level of performances significantly higher than the 1-classifier systems (P<0.020), no differences were found between the multiple classifier groups and the dermatologists groups, indicating comparable performances. This work suggests that a suitable combination of different kinds of classifiers can improve the performances of an automatic diagnostic system.

Algorithms↗
PubMed2003

Experience in designing and evaluating a Teleconsultation System supporting shared care of oncological patients.

This poster present our experience in designing, developing and deploying a Web-based Teleconsultation System based on a Patient Centered Oncological Electronic Medical Record (PEMR) specifically de-signed to provide clinicians a cooperative work tool supporting the oncological patient management. An evaluation phase in a clinical setting was performed when the system was deployed in the hospitals. A second evaluation phase after two year of utilization has been carrying on.

Humans↗
PubMed2003

A real application of a concept-based Electronic Medical Record.

We present a real implementation of a concept-based Electronic Medical Record for the management of heart failure disease. Our approach is based on GEHR archetypes represented in XML format for modelling clinical information. By using this technique it could be possible to build a interoperable future-proof clinical information system.

Heart Failure↗
PubMed2002

Digital storage of glass slides for quality assurance in histopathology and cytopathology.

Proficiency testing programmes for measuring screening skills in pathology are mainly conducted using conventional glass microscope slides. However, the availability of robotic microscopes allows an entire conventional slide to be digitized. Our experiments have shown that, using a widely available robotized microscope and a PC, the image of a single field may be acquired in 2 s on average, including stage movements, autofocus and storage. Digitizing an entire slide, a fully automated procedure, takes up to 8 h. If the image of each field is compressed at an appropriate quality level (a compression ratio of, say, 35:1) it requires about 40 kByte to be stored, resulting in a total storage requirement of about 600 MByte per slide. Thus one CD-ROM can be used to store one virtual slide, as well as a self-installing program to provide a microscope simulator facility. This allows pathologists to examine the virtual case from their computer in a similar manner to looking at a glass slide on a conventional microscope. This permits a new, computer-based approach to proficiency testing in histopathology and cytopathology. Use of virtual slides should encourage the diffusion of national quality assurance programmes, which at present suffer from certain organizational and logistical limitations.

Analog-Digital Conversion↗
PubMedDate not supplied

[Benzene exposure in Modena: historical trend and health risk assessment].

OBJECTIVE: The present paper estimates the 1980-2000 trend in exposure to benzene of the population living within the urban area of Modena. An assessment of leukaemia risk is also presented. DESIGN: The 2000 annual means of benzene atmospheric concentrations in 73 sites has been derived using a procedure which integrated data from fixed site stations and passive samplers: on this basis, an annual mean for the whole urban area has been calculated. The population exposure trend for the period 1980-2000 has been estimated using the information on traffic emission changes. The expected annual number of leukaemia cases attributable to benzene has been calculated by using two different approaches. SETTING: Residents in the urban area of Modena. MAIN OUTCOME MEASURES: Annual incidence of leukaemia attributable to benzene. RESULTS: In 2000, the mean urban concentration was about 7 microg/m3 and in average the population was exposed to about 9 microg/m3. In the eighties, the population exposure was 5 times higher than the 2000 value, with a maximum of 51 microg/m3 in 1988. The leukaemia risk assessment procedures gave a value of about 4 x 10(-1) with the method based on cumulative exposure and of about 4 x 10(-2) with the method based on weighted exposure. DISCUSSION AND CONCLUSION: This study is one of the few examples of evaluation of both the trend in benzene exposure for a population and assessment of leukaemia risk. Uncertainties in the assessment of health impact derive from inconsistencies in the underlyng methods.

Benzene↗