FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292458077> ?p ?o ?g. }

• W4292458077 endingPage "42" @default.
• W4292458077 startingPage "32" @default.
• W4292458077 abstract "Objectives Early detection is of crucial importance for prevention of type 2 diabetes and pre-diabetes. Diagnosis of these conditions relies on the oral glucose tolerance test and haemoglobin A1c estimation which are invasive and challenging for large-scale screening. We aimed to combine the non-invasive nature of ECG with the power of machine learning to detect diabetes and pre-diabetes. Methods Data for this study come from Diabetes in Sindhi Families in Nagpur study of ethnically endogenous Sindhi population from central India. Final dataset included clinical data from 1262 individuals and 10 461 time-aligned heartbeats recorded digitally. The dataset was split into a training set, a validation set and independent test set (8892, 523 and 1046 beats, respectively). The ECG recordings were processed with median filtering, band-pass filtering and standard scaling. Minority oversampling was undertaken to balance the training dataset before initiation of training. Extreme gradient boosting (XGBoost) was used to train the classifier that used the signal-processed ECG as input and predicted the membership to ‘no diabetes’, pre-diabetes or type 2 diabetes classes (defined according to American Diabetes Association criteria). Results Prevalence of type 2 diabetes and pre-diabetes was ~30% and ~14%, respectively. Training was smooth and quick (convergence achieved within 40 epochs). In the independent test set, the DiaBeats algorithm predicted the classes with 97.1% precision, 96.2% recall, 96.8% accuracy and 96.6% F1 score. The calibrated model had a low calibration error (0.06). The feature importance maps indicated that leads III, augmented Vector Left (aVL), V4, V5 and V6 were most contributory to the classification performance. The predictions matched the clinical expectations based on the biological mechanisms of cardiac involvement in diabetes. Conclusions Machine-learning-based DiaBeats algorithm using ECG signal data accurately predicted diabetes-related classes. This algorithm can help in early detection of diabetes and pre-diabetes after robust validation in external datasets." @default.
• W4292458077 created "2022-08-20" @default.
• W4292458077 creator A5000869778 @default.
• W4292458077 creator A5002704733 @default.
• W4292458077 creator A5006288501 @default.
• W4292458077 creator A5018883009 @default.
• W4292458077 creator A5020806539 @default.
• W4292458077 creator A5027572121 @default.
• W4292458077 creator A5046653381 @default.
• W4292458077 creator A5050022570 @default.
• W4292458077 creator A5053651259 @default.
• W4292458077 creator A5072765503 @default.
• W4292458077 creator A5085912221 @default.
• W4292458077 date "2022-08-09" @default.
• W4292458077 modified "2023-10-06" @default.
• W4292458077 title "Machine-learning algorithm to non-invasively detect diabetes and pre-diabetes from electrocardiogram" @default.
• W4292458077 cites W1520722002 @default.
• W4292458077 cites W1774410908 @default.
• W4292458077 cites W1873622949 @default.
• W4292458077 cites W2009787667 @default.
• W4292458077 cites W2019407738 @default.
• W4292458077 cites W2028097684 @default.
• W4292458077 cites W2035573339 @default.
• W4292458077 cites W2039486021 @default.
• W4292458077 cites W2054005523 @default.
• W4292458077 cites W2079791971 @default.
• W4292458077 cites W2089181170 @default.
• W4292458077 cites W2114439920 @default.
• W4292458077 cites W2116570678 @default.
• W4292458077 cites W2127401958 @default.
• W4292458077 cites W2145444893 @default.
• W4292458077 cites W2151591509 @default.
• W4292458077 cites W2230697532 @default.
• W4292458077 cites W2291955599 @default.
• W4292458077 cites W2313824304 @default.
• W4292458077 cites W2460530547 @default.
• W4292458077 cites W2621611914 @default.
• W4292458077 cites W2659296870 @default.
• W4292458077 cites W2792805849 @default.
• W4292458077 cites W2888208815 @default.
• W4292458077 cites W2919856689 @default.
• W4292458077 cites W2920905494 @default.
• W4292458077 cites W2939633281 @default.
• W4292458077 cites W2955588623 @default.
• W4292458077 cites W2967781381 @default.
• W4292458077 cites W2992319380 @default.
• W4292458077 cites W2995510292 @default.
• W4292458077 cites W3000630830 @default.
• W4292458077 cites W3006581614 @default.
• W4292458077 cites W3006607088 @default.
• W4292458077 cites W3007453563 @default.
• W4292458077 cites W3011285191 @default.
• W4292458077 cites W3021332602 @default.
• W4292458077 cites W3022323014 @default.
• W4292458077 cites W3026441235 @default.
• W4292458077 cites W3032874471 @default.
• W4292458077 cites W3035150061 @default.
• W4292458077 cites W3037319793 @default.
• W4292458077 cites W3048114973 @default.
• W4292458077 cites W3086253300 @default.
• W4292458077 cites W3091608574 @default.
• W4292458077 cites W3093384189 @default.
• W4292458077 cites W3099878876 @default.
• W4292458077 cites W3103145119 @default.
• W4292458077 cites W3164056298 @default.
• W4292458077 cites W4200511449 @default.
• W4292458077 cites W4206163452 @default.
• W4292458077 cites W4251966062 @default.
• W4292458077 doi "https://doi.org/10.1136/bmjinnov-2021-000759" @default.
• W4292458077 hasPublicationYear "2022" @default.
• W4292458077 type Work @default.
• W4292458077 citedByCount "5" @default.
• W4292458077 countsByYear W42924580772022 @default.
• W4292458077 countsByYear W42924580772023 @default.
• W4292458077 crossrefType "journal-article" @default.
• W4292458077 hasAuthorship W4292458077A5000869778 @default.
• W4292458077 hasAuthorship W4292458077A5002704733 @default.
• W4292458077 hasAuthorship W4292458077A5006288501 @default.
• W4292458077 hasAuthorship W4292458077A5018883009 @default.
• W4292458077 hasAuthorship W4292458077A5020806539 @default.
• W4292458077 hasAuthorship W4292458077A5027572121 @default.
• W4292458077 hasAuthorship W4292458077A5046653381 @default.
• W4292458077 hasAuthorship W4292458077A5050022570 @default.
• W4292458077 hasAuthorship W4292458077A5053651259 @default.
• W4292458077 hasAuthorship W4292458077A5072765503 @default.
• W4292458077 hasAuthorship W4292458077A5085912221 @default.
• W4292458077 hasBestOaLocation W42924580771 @default.
• W4292458077 hasConcept C11413529 @default.
• W4292458077 hasConcept C119857082 @default.
• W4292458077 hasConcept C134018914 @default.
• W4292458077 hasConcept C154945302 @default.
• W4292458077 hasConcept C169903167 @default.
• W4292458077 hasConcept C2777180221 @default.
• W4292458077 hasConcept C2908647359 @default.
• W4292458077 hasConcept C41008148 @default.
• W4292458077 hasConcept C555293320 @default.
• W4292458077 hasConcept C71924100 @default.
• W4292458077 hasConcept C99454951 @default.

• next