Unifying Fourteen Post-Hoc Attribution Methods With Taylor Interactions.

Various attribution methods have been developed to explain deep neural networks (DNNs) by inferring the attribution/importance/contribution score of each input variable to the final output. However, existing attribution methods are often built upon different heuristics. There remains a lack of a unified theoretical understanding of why these methods are effective and how they are related. Furthermore, there is still no universally accepted criterion to compare whether one attribution method is preferable over another. In this paper, we resort to Taylor interactions and for the first time, we discover that fourteen existing attribution methods, which define attributions based on fully different heuristics, actually share the same core mechanism. Specifically, we prove that attribution scores of input variables estimated by the fourteen attribution methods can all be mathematically reformulated as a weighted allocation of two typical types of effects, i.e., independent effects of each input variable and interaction effects between input variables. The essential difference among these attribution methods lies in the weights of allocating different effects. Inspired by these insights, we propose three principles for fairly allocating the effects, which serve as new criteria to evaluate the faithfulness of attribution methods. In summary, this study can be considered as a new unified perspective to revisit fourteen attribution methods, which theoretically clarifies essential similarities and differences among these methods. Besides, the proposed new principles enable people to make a direct and fair comparison among different methods under the unified perspective.

Machine learning model to predict recurrent ulcer bleeding in patients with history of idiopathic gastroduodenal ulcer bleeding.

BACKGROUND: Patients with a history of Helicobacter pylori-negative idiopathic bleeding ulcers have an increased risk of recurring ulcer complications. AIM: To build a machine learning model to identify patients at high risk for recurrent ulcer bleeding. METHODS: Data from a retrospective cohort of 22 854 patients (training cohort) diagnosed with peptic ulcer disease in 2007-2016 were analysed to build a model (IPU-ML) to predict recurrent ulcer bleeding. We tested the IPU-ML in all patients with a diagnosis of gastrointestinal bleeding (n = 1265) in 2008-2015 from a different catchment population (independent validation cohort). Any co-morbid conditions which had occurred in >1% of study population were eligible as predictors. RESULTS: Recurrent ulcer bleeding developed in 4772 patients (19.5%) in the training cohort, during a median follow-up period of 2.7 years. IPU-ML model built on six parameters (age, baseline haemoglobin, and presence of gastric ulcer, gastrointestinal diseases, malignancies, and infections) identified patients with bleeding recurrence within 1 year with an area under the receiver operating characteristic curve (AUROC) of 0.648. When we set the IPU-ML cutoff value at 0.20, 27.5% of patients were classified as high risk for rebleeding with a sensitivity of 41.4%, specificity of 74.6%, and a negative predictive value of 91.1%. In the validation cohort, the IPU-ML identified patients with a recurrence ulcer bleeding within 1 year with an AUROC of 0.775, and 84.3% of overall accuracy. CONCLUSION: We developed a machine-learning model to identify those patients with a history of idiopathic gastroduodenal ulcer bleeding who are not at high risk for recurrent ulcer bleeding.

A Hybrid Residual Network and Long Short-Term Memory Method for Peptic Ulcer Bleeding Mortality Prediction.

The prediction of patient mortality, which can detect high-risk patients, is a significant yet challenging problem in medical informatics. Thanks to the wide adoption of electronic health records (EHRs), many data-driven methods have been proposed to forecast mortality. However, most existing methods do not consider correlations between static and dynamic data, which contain significant information about mutual influences between these data. In this paper, we utilize a deep Residual Network (ResNet) consisting of many convolution units, which can jointly analyze different variables, to capture correlation information in and between static and dynamic variables. Furthermore, the Long Short-Term Memory (LSTM) method is used to extract temporal dependencies information from dynamic data. Finally, a deep fusion method is used to integrate these different types of information to improve mortality prediction. Experiment results on Peptic Ulcer Bleeding (PUB) mortality prediction show that the proposed method outperforms existing methods and achieves an AUC (area under the receiver operating characteristic curve) score of 0.9353.

Mesoporous zinc ferrite: synthesis, characterization, and photocatalytic activity with H2O2/visible light.

Mesoporous ZnFe(2)O(4) (meso-ZnFe(2)O(4)) was synthesized by a hydrothermal process in which cetyltrimethylammonium bromide (CTAB) participates in the reaction to produce nanocrystals. Synthesized ZnFe(2)O(4) was characterized by energy dispersive spectroscopy (EDS), X-ray diffraction (XRD), Brunauer-Emmett-Teller (BET) surface area, scanning electronic microscopy (SEM), transmission electron microscopy (TEM), and diffuse reflectance spectra (DRS). The meso-ZnFe(2)O(4) was resulted from the agglomeration of nanoparticles with size of 5-10nm. The photocatalytic activity of ZnFe(2)O(4) under visible light (λ>400 nm) was evaluated by the degradation of Acid Orange II (AOII) at different sintering temperatures, the amount of ZnFe(2)O(4), and the concentration of H(2)O(2). The photocatalytic degradation of AOII was almost complete within 2h in H(2)O(2)/visible light system. The high efficiency for AOII degradation was attributed to the strong absorption of ZnFe(2)O(4) in visible-light region and the generation of reactive OH by H(2)O(2) in the system. The involvement of OH in oxidizing AOII was examined by determining the photocurrent of ZnFe(2)O(4), [OH], and degradation rates using different scavengers. Organic compounds as intermediates of the degradation process were identified by LC/MS. Moreover, ZnFe(2)O(4) retained their degradation efficiencies for a series of repetitive batch runs, indicating the true photocatalytic process.