Faculty of Electrical Engineering and Information Technologies
Permanent URI for this communityhttps://repository.ukim.mk/handle/20.500.12188/10
Browse
12 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Bias in vital signs? Machine learning models can learn patients’ race or ethnicity from the values of vital signs alone(BMJ, 2025-07-10); ; ; ; Mullan, Irene DankwaObjectives To investigate whether machine learning (ML) algorithms can learn racial or ethnic information from the vital signs alone. Methods A retrospective cohort study of critically ill patients between 2014 and 2015 from the multicentre eICU-CRD critical care database involving 335 intensive care units in 208 US hospitals, containing 200 859 admissions. We extracted 10 763 critical care admissions of patients aged 18 and over, alive during the first 24 hours after admission, with recorded race or ethnicity as well as at least two measurements of heart rate, oxygen saturation, respiratory rate and blood pressure. Pairs of subgroups were matched based on age, gender, admission diagnosis and disease severity. XGBoost, Random Forest and Logistic Regression algorithms were used to predict recorded race or ethnicity based on the values of vital signs. Results Models derived from only four vital signs can predict patients’ recorded race or ethnicity with an area under the curve (AUC) of 0.74 (±0.030) between White and Black patients, AUC of 0.74 (±0.030) between Hispanic and Black patients and AUC of 0.67 (±0.072) between Hispanic and White patients, even when controlling for known factors. There were very small, but statistically significant differences between heart rate, oxygen saturation and blood pressure, but not respiration rate and invasively measured oxygen saturation. Discussion ML algorithms can extract racial or ethnicity information from vital signs alone across diverse patient populations, even when controlling for known biases such as pulse oximetry variations and comorbidities. The model correctly classified the race or ethnicity in two out of three patients, indicating that this outcome is not random. Conclusion Vital signs embed racial information that can be learnt by ML algorithms, posing a significant risk to equitable clinical decision-making. Mitigating measures might be challenging, considering the fundamental role of vital signs in clinical decision-making. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Survey of Bias in Healthcare: Pitfalls of Using Biased Datasets and Applications(Springer, Cham, 2023-07-09); ; Osmani, VenetArtificial intelligence (AI) is widely used in medical applications to support outcome prediction and treatment optimisation based on collected patient data. With the increasing use of AI in medical applications, there is a need to identify and address potential sources of bias that may lead to unfair decisions. There have been many reported cases of bias in healthcare professionals, medical equipment, medical datasets, and actively used medical applications. These cases have severely impacted the quality of patients’ healthcare, and despite awareness campaigns, bias has persisted or in certain cases even exacerbated. In this paper, we survey reported cases of different forms of bias in medical practice, medical technology, medical datasets, and medical applications, and analyse the impact these reports have in the access and quality of care provided for certain patient groups. In the end, we discuss possible pitfalls of using biased datasets and applications, and thus, provide the reasoning behind the need for robust and equitable medical technologies. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Network Traffic Analysis and Control by Application of Machine Learning(Springer, Cham, 2023-07-09) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Analysis of Early Cancer Diagnosis Using Machine Learning(Springer, Cham, 2024) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Mobile Edge Computing services with QoS support model for Next Generation Mobile Networks(FEEIT, Skopje, 2022) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Machine Learning Based Classification of IoT Traffic(Brno University of Technology, 2023-06); With the rapid expansion and widespread adoption of the Internet of Things (IoT), maintaining secure connections among active devices can be challenging. Since IoT devices are limited in power and storage, they cannot perform complex tasks, which makes them vulnerable to different types of attacks. Given the volume of data generated daily, detecting anomalous behavior can be demanding. However, machine learning (ML) algorithms have proven successful in extracting complex patterns from big data, which has led to active applications in IoT. In this paper, we perform a comprehensive analysis, including 4 ML algorithms and 3 neural networks (NNs), and propose a pipeline which analyzes the influence data reduction (loss) has on the performance of these algorithms. We use random undersampling as a data reduction technique, which simulates reduced network traffic data. The pipeline investigates several degrees of data loss. The results show that models trained on the original data distribution obtain accuracy that verges on 100%. XGBoost performs best from the classic ML algorithms. From the deep learning models, the 2-layered NN provides excellent results and has sufficient depth for practical application. On the other hand, when the models are trained on the undersampled data, there is a decrease in performance, most notably in the case of NNs. The most prominent change is seen in the 4-layered NN, where the model trained on the original dataset detects attacks with a success of 93.53%, whereas the model trained on the maximally reduced data has a success of only 39.39%. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Classifying Power Quality Disturbances in Noisy Conditions using Machine Learning(The Jozhef Stefan Institute, 2019-10) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Investigating Presence of Ethnoracial Bias in Clinical Data using Machine Learning(2021-09); ; Celi, Leo AnthonyAn important target for machine learning research is obtaining unbiased results, which require addressing bias that might be present in the data as well as the methodology. This is of utmost importance in medical applications of machine learning, where trained models should be unbiased so as to result in systems that are widely applicable, reliable and fair. Since bias can sometimes be introduced through the data itself, in this paper we investigate the presence of ethnoracial bias in patients’ clinical data. We focus primarily on vital signs and demographic information and classify patient ethnoraces in subsets of two from the three ethnoracial groups (African Americans, Caucasians, and Hispanics). Our results show that ethnorace can be identified in two out of three patients, setting the initial base for further investigation of the complex issue of ehtnoracial bias. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Mobile Edge Computing services with QoS support for beyond 5G Networks – Use Cases(2021-09) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Image Segmentation as an Instrument for Setting Attention Regions in Convolutional Neural Networks for Bias Detection Purposes(2023); Convolutional neural networks (CNNs) are constantly being used for medical image processing with increased application in publicly available datasets and are later being actively applied in medical practice. Therefore, since patient lives are at stake, it is important that the functionality of the neural network is beyond reproach. In this paper, due to dataset availability, we present two lung segmentation approaches using traditional image processing and deep learning methodologies; these approaches can later be used to focus a CNN for image segmentation and classification tasks, with implementations spanning everything from disease diagnosis to demographic and bias analysis. The aim of this paper is to provide a framework for segmentation in medical images of the chest cavity, as a way of applying attention regions and localizing sources of bias in images. Both of the proposed segmentation tools, the traditional image approach using computer tomography scans and the CNN applied to chest X-rays, provide excellent lung segmentation comparable to popular methods in the image processing sphere. This allows for an all-encompassing application of the developed methodology regardless of different image formats, therefore making it widely applicable in setting attention regions for CNNs.