Different decision tree induction strategies for a medical decision problem

Burduk, Robert; Woźniak, Michał

doi:10.2478/s11536-011-0142-x

Cited by 10 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine learning (ML) methods are an attractive solution for such a task as they offer fast and precise intelligent analysis of multidimensional data. Such algorithms are widely used for clinical decision support [17] and are applied by authors to the tasks as the hypertension diagnosis [18], drug discovery [19], nephropathy detection among new-borns [20], or abdominal pain diagnosis [31].…”

Section: Introductionmentioning

confidence: 99%

Automatic diagnosis of primary headaches by machine learning methods

Krawczyk

Simić

et al. 2013

Open Medicine

View full text Add to dashboard Cite

AbstractPrimary headaches are common disease of the modern society and it has high negative impact on the productivity and the life quality of the affected person. Unfortunately, the precise diagnosis of the headache type is hard and usually imprecise, thus methods of headache diagnosis are still the focus of intense research. The paper introduces the problem of the primary headache diagnosis and presents its current taxonomy. The considered problem is simplified into the three class classification task which is solved using advanced machine learning techniques. Experiments, carried out on the large dataset collected by authors, confirmed that computer decision support systems can achieve high recognition accuracy and therefore be a useful tool in an everyday physician practice. This is the starting point for the future research on automation of the primary headache diagnosis.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic diagnosis of primary headaches by machine learning methods

Krawczyk

Simić

et al. 2013

Open Medicine

View full text Add to dashboard Cite

show abstract

“…The tenth comes from the Surgical Clinic Wroclaw Medical Academy and describes the acute abdominal pain diagnosis problem. A set of all the available features was used for all data sets, however, for the acute abdominal pain data set the selection of features has been made in accordance with the suggestions from another work on the topic [20,21]. [22].…”

Section: Methodsmentioning

confidence: 99%

Construction of Sequential Classifier Using Confusion Matrix

Burduk

Trajdos

2013

Computer Information Systems and Industrial Management

Self Cite

View full text Add to dashboard Cite

Part 7: AlgorithmsInternational audienceThis paper presents the problem of building the decision scheme in the multistage pattern recognition task. This task can be presented using a decision tree. This decision tree is built in the learning phase of classification. This paper proposes a split criterion based on the analysis of the confusion matrix. Specifically, we propose the division associated with an incorrect classification. The obtained results were verified on the data sets form UCI Machine Learning Repository and one real-life data set of the computer-aided medical diagnosis

show abstract

“…Algoritma decision tree yang banyak digunakan dalam teknik data mining antara lain ID3, C4.5, dan Random Forest [5]. Aplikasi penggunaan algoritma decision tree antara lain dilakukan oleh Robert Burduk [6] dalam dunia medis untuk diagnosa penyakit perut bagian atas. Moon, Sung Seek [7] menggunakan algoritma decision tree dalam melakukan klasifikasi untuk menemukan relasi antara jumlah rokok yang dikonsumsi per hari dengan umur mulai merokok, tingkat pendidikan, dan stress psikologis.…”

Section: B Decision Treeunclassified

Prediksi Kelulusan Peserta Uji Kompetensi Profesi Menggunakan Algoritma C4.5

Wirasto

Negara

2021

IKOMTI

View full text Add to dashboard Cite

Uji Kompetensi Mahasiswa Program Profesi Dokter Gigi (UKMP2DG) merupakan exit exam bagi para mahasiswa yang telah selesai menempuh pendidikan profesi dokter gigi. Meski peserta yang tidak lulus UKMP2DG dapat mengulang ujian di periode-periode berikutnya, para retaker ini dihadapkan pada batasan masa studi maksimal sebelum dinyatakan drop out. Selain itu semakin lama jeda antara penyelesaian studi dan waktu ujian dikhawatirkan berpengaruh pada penguasaan terhadap ilmu yang telah dipelajari. Penelitian ini bertujuan membangun model yang dapat digunakan untuk memprediksi kelulusan calon peserta UKMP2DG melalui data-data pendukung. Penerapan algoritma C4.5 menghasilkan model dengan tingkat akurasi 81,40%, presisi 82,84% dan recall sebesar 95,82%. Hasil penelitian ini dapat dimanfaatkan oleh Institusi Pendidikan Dokter Gigi (IPDG) untuk mengambil langkah-langkah khusus dalam mempersiapkan calon peserta yang diprediksi akan tidak lulus dalam ujian yang akan ditempuh.

show abstract

Different decision tree induction strategies for a medical decision problem

Cited by 10 publications

References 29 publications

Automatic diagnosis of primary headaches by machine learning methods

Automatic diagnosis of primary headaches by machine learning methods

Construction of Sequential Classifier Using Confusion Matrix

Prediksi Kelulusan Peserta Uji Kompetensi Profesi Menggunakan Algoritma C4.5

Contact Info

Product

Resources

About