Using data mining techniques to support breast cancer diagnosis

More than ever, there is an increase of the number of decision support methods and computer aided diagnostic systems applied to various areas of medicine. In breast cancer research, many works have been done in order to reduce false-positives when used as a double reading method. In this study, we aimed to present a set of data mining techniques that were applied to approach a decision support system in the area of breast cancer diagnosis. This method is geared to assist clinical practice in identifying mammographic findings such as microcalcifications, masses and even normal tissues, in order to avoid misdiagnosis. In this work a reliable database was used, with 410 images from about 115 patients, containing previous reviews performed by radiologists as microcalcifications, masses and also normal tissue findings. Throughout this work, two feature extraction techniques were used: the gray level co-occurrence matrix and the gray level run length matrix. For classification purposes, we considered various scenarios according to different distinct patterns of injuries and several classifiers in order to distinguish the best performance in each case described. The many classifiers used were Naïve Bayes, Support Vector Machines, k-nearest Neighbors and Decision Trees (J48 and Random Forests). The results in distinguishing mammographic findings revealed great percentages of PPV and very good accuracy values. Furthermore, it also presented other related results of classification of breast density and BI-RADS® scale. The best predictive method found for all tested groups was the Random Forest classifier, and the best performance has been achieved through the distinction of microcalcifications. The conclusions based on the several tested scenarios represent a new perspective in breast cancer diagnosis using data mining techniques.

O impacto do uso da tala nocturna na funcionalidade do indivíduo com síndrome do túnel carpiano

A síndrome do túnel carpiano (STC) é considerada a neuropatia compressiva mais comum na população. É causada pela compressão directa sobre o nervo mediano no interior do túnel carpiano, que origina parestesias, dor na mão e disfunção muscular. Como consequência destes sintomas, os indivíduos vêem comprometida a sua funcionalidade ao nível das ocupações e, por consequência, alterado o seu desempenho ocupacional. Este trabalho tem como objectivo principal verificar de que forma a utilização da tala nocturna influencia a funcionalidade do indivíduo com STC. Concomitantemente pretende-se definir em que medida alterações das forças de preensão palmar e de pinças se relaciona com o uso da tala. Por último, identificar quais as variáveis sócio - demográficas e as que caracterizam a patologia que estão relacionadas com o problema em estudo e aos valores obtidos com as escalas do Boston Carpal Tunnel Questionnaire (BQTC), nos indivíduos dos grupos controlo e experimental. A amostra é constituída por 22 indivíduos no grupo controlo e 24 no grupo experimental, com diagnóstico de STC ligeiro e moderado. Foram aplicados o BCTQ, o dinamómetro e o pinch meter de Jamar. Os resultados deste estudo mostram uma diminuição significativa da sintomatologia da STC, após a aplicação da tala, nos momentos de reavaliação e follow up, (p=0,000 e p=0,004), assim como um aumento significativo da funcionalidade nos dois momentos (p=0,000 e p=0,004). Deste estudo conclui-se que a utilização da tala nocturna beneficia os indivíduos com STC ligeiro e moderado.

Comparação entre os valores de Procalcitonina e Proteína C reactiva em adultos com doença hemato-oncológica

Os pacientes com doença hemato-oncológica submetidos a quimioterapia possuem maior propensão para infecções bacterianas. O seu diagnóstico pode ser efectuado recorrendo-se aos marcadores biológicos: procalcitonina (PCT) e proteína C reactiva (PCR). Neste estudo, observaram-se diferenças estatisticamente significativas na concentração de PCT nos diferentes grupos de infecção, o que não se verificou na concentração de PCR. Observou-se ainda uma fraca correlação entre estes marcadores nos grupos de infecção. Apenas os valores de PCT estão directamente relacionados com a gravidade da infecção, evidenciando-o como um bom marcador de diagnóstico, mais eficaz do que a PCR.

CardioML: integrating personal cardiac information for ubiquous diagnosis and analysis

The latest medical diagnosis devices enable the performance of e-diagnosis making the access to these services easier, faster and available in remote areas. However this imposes new communications and data interchange challenges. In this paper a new XML based format for storing cardiac signals and related information is presented. The proposed structure encompasses data acquisition devices, patient information, data description, pathological diagnosis and waveform annotation. When compared with similar purpose formats several advantages arise. Besides the full integrated data model it may also be noted the available geographical references for e-diagnosis, the multi stream data description, the ability to handle several simultaneous devices, the possibility of independent waveform annotation and a HL7 compliant structure for common contents. These features represent an enhanced integration with existent systems and an improved flexibility for cardiac data representation.

An Exercise Program Improves Health-Related Quality of Life of Workers

Low back problems are associated with decreased quality of life. Specific exercises can improve quality of life, resulting in better professional performance and functionality. The purpose of this study was to evaluate the effect of following a 21-month exercise program on the quality of life of warehouse workers. The population included 557 male warehouse workers from a food distribution company in Oporto, Portugal. Upon application of the selection criteria, 249 workers were deemed eligible, which were randomized into two groups (125 in the intervention group and 124 in the control group). Then, subjects were asked to volunteer for the study, the sample being formed by 229 workers (112 in the intervention group and 117 in the control group). All subjects completed the SF-36 questionnaire prior to beginning the program and on the 11th and 21st months following it. The exercises were executed in the company facilities once a day for 8 min. Data were analyzed using SPSS® 17.0 for Windows®. After 11 months of following the exercise program, there was an increase in all scores for the experimental group, with statistically significant differences in the dimensions physical functioning (0.019), bodily pain (0.010), general health (0.004), and rolephysical (0.037). The results obtained at the end of the study (21 months) showed significant improvements in the dimensions physical functioning (p = 0.002), rolephysical (p = 0.007), bodily pain (p = 0.001), social functioning (p = 0.015), role-emotional (p = 0.011), and mental health (p = 0.001). In the control group all dimensions showed a decrease in mean scores. It can be concluded that the implementation of a low back specific exercise program has changed positively the quality of life of warehouse workers.

Immediate effects of Tuina techniques on working-related musculoskeletal disorder of professional orchestra musicians

BACKGROUND: Musicians are a prone group to suffer from working-related musculoskeletal disorder (WRMD). Conventional solutions to control musculoskeletal pain include pharmacological treatment and rehabilitation programs but their efficiency is sometimes disappointing. OBJECTIVE: The aim of this research is to study the immediate effects of Tuina techniques on WRMD of professional orchestra musicians from the north of Portugal. DESIGN, SETTING, PARTICIPANTS AND INTERVENTIONS: We performed a prospective, controlled, single-blinded, randomized study. Professional orchestra musicians with a diagnosis of WRMD were randomly distributed into the experimental group (n=39) and the control group (n=30). During an individual interview, Chinese diagnosis took place and treatment points were chosen. Real acupoints were treated by Tuina techniques into the experimental group and non-specific skin points were treated into the control group. Pain was measured by verbal numerical scale before and immediately after intervention. RESULTS: After one treatment session, pain was reduced in 91.8% of the cases for the experimental group and 7.9% for the control group. CONCLUSION: Although results showed that Tuina techniques are effectively reducing WRMD in professional orchestra musicians of the north of Portugal, further investigations with stronger measurements, double-blinding designs and bigger simple sizes are needed.