The <i>F</i>-measure for Research Priority

Rousseau, Ronald

doi:10.2478/jdis-2018-0001

Cited by 21 publications

(16 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Precision is the number of correctly classified cases among all cases diagnosed by the algorithm. Additionally, the F-measure [27] was calculated as a combination of precision and sensitivity and as a combination of several thresholds of sensitivity and specificity, respectively.…”

Section: Methodsmentioning

confidence: 99%

Development and validation of a classification algorithm to diagnose and differentiate spontaneous episodic vertigo syndromes: results from the DizzyReg patient registry

et al. 2020

View full text Add to dashboard Cite

Background Spontaneous episodic vertigo syndromes, namely vestibular migraine (VM) and Menière's disease (MD), are difficult to differentiate, even for an experienced clinician. In the presence of complex diagnostic information, automated systems can support human decision making. Recent developments in machine learning might facilitate bedside diagnosis of VM and MD. Methods Data of this study originate from the prospective patient registry of the German Centre for Vertigo and Balance Disorders, a specialized tertiary treatment center at the University Hospital Munich. The classification task was to differentiate cases of VM, MD from other vestibular disease entities. Deep Neural Networks (DNN) and Boosted Decision Trees (BDT) were used for classification. Results A total of 1357 patients were included (mean age 52.9, SD 15.9, 54.7% female), 9.9% with MD and 15.6% with VM. DNN models yielded an accuracy of 98.4 ± 0.5%, a precision of 96.3 ± 3.9%, and a sensitivity of 85.4 ± 3.9% for VM, and an accuracy of 98.0 ± 1.0%, a precision of 90.4 ± 6.2% and a sensitivity of 89.9 ± 4.6% for MD. BDT yielded an accuracy of 84.5 ± 0.5%, precision of 51.8 ± 6.1%, sensitivity of 16.9 ± 1.7% for VM, and an accuracy of 93.3 ± 0.7%, precision 76.0 ± 6.7%, sensitivity 41.7 ± 2.9% for MD. Conclusion The correct diagnosis of spontaneous episodic vestibular syndromes is challenging in clinical practice. Modern machine learning methods might be the basis for developing systems that assist practitioners and clinicians in their daily treatment decisions.

show abstract

Section: Methodsmentioning

confidence: 99%

Development and validation of a classification algorithm to diagnose and differentiate spontaneous episodic vertigo syndromes: results from the DizzyReg patient registry

et al. 2020

View full text Add to dashboard Cite

show abstract

“…South Africa’s performance in nanotechnology was compared with that of BRICS countries using the nanotechnology activity index. The activity index (AI) is defined as the ratio of the country’s share in the publication output in the field to the country’s share in the world’s publication outputs in all fields (Rousseau 2018 ). The world activity index is considered to be one (1); hence, the AI for country X over period P can be approximated by equation ( 1 ) below.…”

Section: Resultsmentioning

confidence: 99%

A nanotechnology-foresight perspective of South Africa

2021

View full text Add to dashboard Cite

This paper presents a foresight perspective of nanotechnology in South Africa based on a 20-year period scientometric analysis of the country’s nanotechnology publications on the Web of Science (WoS) Core Collection. Firstly, publication trends are reported; then, possible socio-economic relevant sectors arising from this information are determined. Lastly, indicators that can be used in foresight exercises to evaluate the potential nanotechnology research areas in South Africa are examined. The 20-year review is also compared with the recent past year, 2019, to identify any changing trends. South Africa’s nanotechnology publications per year grew exponentially from 68 papers in 2000 to 1672 in 2019, an increase of 2459%. The total share of nanotech publications increased from 1.4% in 2000 to 6.6% in 2019, thus a 0.52% increase per year. Compared with Brazil, Russia, India and China, the BRICS countries, South Africa has the lowest nanotechnology productivity with an activity index of 0.68. Over the last 5 years, South Africa nanotech publications had a Hirsch-index of 94 and an average citations rate of 12.76 per paper. Universities are the most prominent publishers, and there are very few publications from the private sector, which can negatively impact the commercialisation of nanotechnology research. The top 10 most prolific researchers, author or co-author over 20% of the nanotechnology papers are reported. A mixture of old and new top researchers’ names suggests succession planning in the system as the years progress. The emergence of computer science as one of the top 20 subjects publishing in nanotech in 2019 and a high level of researcher collaboration suggests possible convergence of nanotech, information technology and artificial intelligence in South Africa. The strategic socio-economic-focused nanotechnology research areas identified for South Africa include material science, photoluminance and optics, medicine, catalysis, electronics, energy, biotech, magnetism, sensors, water and communicable diseases. The top collaborating countries, top researchers, top institutions and nanotechnology economic hubs are reported for each strategic research area. The level of innovation was evaluated using the nanotechnology value chain, and there is a meagre 3.5% of papers reporting on nano-enabled products.

show abstract

“…AUPRC is recommended for imbalanced data over the AUROC measure [26,27]. F-measure is a harmonic mean of precision and recall [28]. Lately, MCC measure was shown to be more advantageous over F-measure in the binary classification of imbalanced data [29].…”

Section: Model Scoringmentioning

confidence: 99%

Investigation of Machine Learning Models and Different Feature Sets for the Efficiency of Early Sepsis Prediction from Highly Unbalanced Data

Abromavičius¹,

Plonis²,

Tarasevičius³

et al. 2020

Preprint

View full text Add to dashboard Cite

The presented research faces the problem of early detection of sepsis for patients in the Intensive Care Unit. The PhysioNet/Computing in Cardiology Challenge 2019 facilitated the development of automated, open-source algorithms for the early detection of sepsis from clinical data. A labeled clinical records dataset for training and verification of the algorithms was provided by the challenge organizers. However, a relatively small number of records with sepsis, supported by Sepsis-3 clinical criteria, led to highly unbalanced dataset (only 2% records with sepsis label). A high number of unbalanced data records is a great challenge for machine learning model training and is not suitable for training classical classifiers. To address these issues, a number of various models were investigated. A solution including feature selection and data balancing techniques was proposed in this paper. In addition, several performance metrics were investigated. Results show, that for successful prediction, a particular model having few or more predictors based on the length of stay in the Intensive Care Unit should be applied.

show abstract

The F-measure for Research Priority

Cited by 21 publications

References 23 publications

Development and validation of a classification algorithm to diagnose and differentiate spontaneous episodic vertigo syndromes: results from the DizzyReg patient registry

Development and validation of a classification algorithm to diagnose and differentiate spontaneous episodic vertigo syndromes: results from the DizzyReg patient registry

A nanotechnology-foresight perspective of South Africa

Investigation of Machine Learning Models and Different Feature Sets for the Efficiency of Early Sepsis Prediction from Highly Unbalanced Data

Contact Info

Product

Resources

About