Hang Lou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hang Lou has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Bo Wang
Center for Precision Psychiatry, Massachusetts General Hospital, Boston, MA, United States
1 shared publication - Edward Palmer
Bloomsbury Institute of Intensive Care Medicine, University College London, London, UK
1 shared publication - Hao Ni
University College London
1 shared publication - Hao Ni
Chongqing University of Posts and Telecommunications
1 shared publication - James Foster
Department of Mathematical Sciences University of Bath UK
1 shared publication - James Morrill
Mathematical Institute, University of Oxford, Oxford, UK
1 shared publication
Latest Publications
- Open Access
- 22 January 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-10
Subtle variation in sepsis-III definitions markedly influences predictive performance within and across methods
Early detection of sepsis is key to ensure timely clinical intervention. Since very few end-to-end pipelines are publicly available, fair comparisons between methodologies are difficult if not impossible. Progress is further limited by discrepancies in the reconstruction of sepsis onset time. This retrospective cohort study highlights the variation in performance of predictive models under three subtly different interpretations of sepsis onset from the sepsis-III definition and compares this against inter-model differences. The models are chosen to cover tree-based, deep learning, and survival analysis methods. Using the MIMIC-III database, between 867 and 2178 intensive care unit admissions with sepsis were identified, depending on the onset definition. We show that model performance can be more sensitive to differences in the definition of sepsis onset than to the model itself. Given a fixed sepsis definition, the best performing method had a gain of 1–5% in the area under the receiver operating characteristic (AUROC). However, the choice of onset time can cause a greater effect, with variation of 0–6% in AUROC. We illustrate that misleading conclusions can be drawn if models are compared without consideration of the sepsis definition used which emphasizes the need for a standardized definition for sepsis onset.
- 22 January 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-10
Open AccessSubtle variation in sepsis-III definitions markedly influences predictive performance within and across methods
Early detection of sepsis is key to ensure timely clinical intervention. Since very few end-to-end pipelines are publicly available, fair comparisons between methodologies are difficult if not impossible. Progress is further limited by discrepancies in the reconstruction of sepsis onset time. This retrospective cohort study highlights the variation in performance of predictive models under three subtly different interpretations of sepsis onset from the sepsis-III definition and compares this against inter-model differences. The models are chosen to cover tree-based, deep learning, and survival analysis methods. Using the MIMIC-III database, between 867 and 2178 intensive care unit admissions with sepsis were identified, depending on the onset definition. We show that model performance can be more sensitive to differences in the definition of sepsis onset than to the model itself. Given a fixed sepsis definition, the best performing method had a gain of 1–5% in the area under the receiver operating characteristic (AUROC). However, the choice of onset time can cause a greater effect, with variation of 0–6% in AUROC. We illustrate that misleading conclusions can be drawn if models are compared without consideration of the sepsis definition used which emphasizes the need for a standardized definition for sepsis onset.
- Open Access
Path Development Network with Finite-dimensional Lie Group Representation
The path signature, a mathematically principled and universal feature of sequential data, leads to a performance boost of deep learning-based models in various sequential data tasks as a complimentary feature. However, it suffers from the curse of dimensionality when the path dimension is high. To tackle this problem, we propose a novel, trainable path development layer, which exploits representations of sequential data with the help of finite-dimensional matrix Lie groups. We also design the backpropagation algorithm of the development layer via an optimisation method on manifolds known as trivialisation. Numerical experiments demonstrate that the path development consistently and significantly outperforms, in terms of accuracy and dimensionality, signature features on several empirical datasets. Moreover, stacking the LSTM with the development layer with a suitable matrix Lie group is empirically proven to alleviate the gradient issues of LSTMs and the resulting hybrid model achieves the state-of-the-art performance.
Open AccessPath Development Network with Finite-dimensional Lie Group Representation
The path signature, a mathematically principled and universal feature of sequential data, leads to a performance boost of deep learning-based models in various sequential data tasks as a complimentary feature. However, it suffers from the curse of dimensionality when the path dimension is high. To tackle this problem, we propose a novel, trainable path development layer, which exploits representations of sequential data with the help of finite-dimensional matrix Lie groups. We also design the backpropagation algorithm of the development layer via an optimisation method on manifolds known as trivialisation. Numerical experiments demonstrate that the path development consistently and significantly outperforms, in terms of accuracy and dimensionality, signature features on several empirical datasets. Moreover, stacking the LSTM with the development layer with a suitable matrix Lie group is empirically proven to alleviate the gradient issues of LSTMs and the resulting hybrid model achieves the state-of-the-art performance.