Applying Data Mining and Machine Learning Algorithms to predict symptom development in Parkinson's disease

Journal Title: Annales Academiae Medicae Silesiensis - Year 2014, Vol 68, Issue 5

Abstract

The standard treatment of PD symptoms depends on the experience of a particular neurologist, UPDRS and Hoehn and Yahr scale measurements in order to estimate the stage of PD, the patient’s reports and patient’s responses to medications. All these estimations are to a great extent subjective and determine different treatments in different centers. The purpose of this work was to develop an approach that may more precisely and objectively estimate a patient’s symptoms and in consequence optimize individual PD treatment. We have presented several examples of different methods that make measurements in PD more precise. However, greater precision and objectivity were only the first steps. In addition, all (standard and new) data must be evaluated in an intelligible way in order to better estimate PD symptoms and their developments. We have used data mining and machine learning approaches to mimic the “golden” neurologist’s reasoning.

Authors and Affiliations

Andrzej Przybyszewski

Keywords

Related Articles

-643C/T polymorphism of RANKL gene and its association with osteoporosis in postmenopausal women

INTRODUCTION RANKL is a key cytokine involved in osteoclast differentiation from its precursors, activation and survival of osteoclasts themselves. Because RANKL binds with RANK, the presence of RANK on target cells is a...

12-month assessment of increase in total kidney volume in children and young adults with autosomal dominant polycystic kidney disease – a pilot study

INTRODUCTION: Autosomal dominant polycystic kidney disease (ADPKD) is the most common type of monogenic kidney disease. It is the cause of ESRD in 5–10% of adult patients who undergo renal replacement therapy. Owing to t...

Atypical form of microscopic colitis in 56-year-old patient presenting with long-lasting watery diarrhea

Microscopic colitis (MC) is a common cause of unexplainable, chronic diarrhea. The disease is characterized by the presence of clinical symptoms, a normal colonoscopy and typical histopathological changes upon microscopi...

Socio-economic burden of cardiovascular diseases in Poland and Central Europe

Cardiovascular diseases cause over 4 million deaths each year in the societies of fifty-three countries of the World Health Organization’s European region. Over 1.9 million deaths occur in European Union countries. In 20...

Application of radiotherapy and stereotactic radiosurgery in treatment of patients with brain gliosarcoma – preliminary results

AIM The aim of the work is to evaluate the results of the treatment of gliosarcoma according to the applied therapeutic methods. MATERIAL AND METHODS 43 patients (15 women and 28 men) aged 21 to 80 years were treated for...

Download PDF file
  • EP ID EP266944
  • DOI -
  • Views 110
  • Downloads 0

How To Cite

Andrzej Przybyszewski (2014). Applying Data Mining and Machine Learning Algorithms to predict symptom development in Parkinson's disease. Annales Academiae Medicae Silesiensis, 68(5), 332-349. https://europub.co.uk/articles/-A-266944