Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients

Mortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes and efficient utilization of resources. Accessibility of electronic health records (EHR) has enabled data-driven predictive modeling using machine learning. However, very few studies rely solely on unstructured clinical notes from the EHR for mortality prediction. In this work, we propose a framework to predict short, mid, and long-term mortality in adult ICU patients using unstructured clinical notes from the MIMIC III database, natural language processing (NLP), and machine learning (ML) models. Depending on the statistical description of the patients’ length of stay, we define the short-term as 48-hour and 4-day period, the mid-term as 7-day and 10-day period, and the long-term as 15-day and 30-day period after admission. We found that by only using clinical notes within the 24 hours of admission, our framework can achieve a high area under the receiver operating characteristics (AU-ROC) score for short, mid and long-term mortality prediction tasks. The test AU-ROC scores are 0.87, 0.83, 0.83, 0.82, 0.82, and 0.82 for 48-hour, 4-day, 7-day, 10-day, 15-day, and 30-day period mortality prediction, respectively. We also provide a comparative study among three types of feature extraction techniques from NLP: frequency-based technique, fixed embedding-based technique, and dynamic embedding-based technique. Lastly, we provide an interpretation of the NLP-based predictive models using feature-importance scores.

An entropy-based image watermarking scheme by improving robustness in shearlet and wavelet domain

The existing robust digital watermarking schemes mainly embed information in the fixed positions or with fixed embedding strength, while seldom considering adaptive adjustment based on the characteristics of the cover image, thus it reduces the imperceptibility and the robustness of watermarking. Aiming at these issues, we propose a scheme which can be able to dynamically adjust the watermark embedding position and strength. Therefore, it guarantees the trade-off between robustness and imperceptibility. The appropriate embedding positions are dynamically selected for the watermark by comparing the image entropy, and the embedding strength of the image blocks are adaptively adjusted according to the entropy and the Just Noticeable Difference (JND) model in the Human Visual System (HVS)-based wavelet domain. Singular Value Decomposition (SVD) is performed on the image blocks to ensure the resistant ability of geometric attacks. The experimental results show that the scheme has good imperceptibility as well as strong robustness against various attacks. The robustness in common attacks is improved by at least 1% compared with similar watermarking schemes.

An Adaptive Embedding Strength Watermarking Algorithm Based on Shearlets’ Capture Directional Features

The discrete wavelet transform (DWT) is unable to represent the directional features of an image. Similarly, a fixed embedding strength is not able to establish an ideal balance between imperceptibility and robustness of a watermarked image. In this work, we propose an adaptive embedding strength watermarking algorithm based on shearlets’ capture directional features (S-AES). We improve the watermarking algorithm in the domain of DWT using non-subsampled shearlet transform (NSST). The improvement is made in terms of coping with anti-geometric attacks. The embedding strength is optimized by artificial bee colony (ABC) to achieve higher robustness under the premise of satisfying imperceptibility. The principle components (PC) of the watermark are embedded into the host image to overcome the false positive problem. The simulation results show that the proposed algorithm has better imperceptibility and strong robustness against multi-attacks, especially those of high intensity.

PVO-Based Reversible Data Hiding Exploiting Two-Layer Embedding for Enhancing Image Fidelity

Recently, Li et al. proposed a data hiding method based on pixel value ordering (PVO) and prediction error expansion (PEE). In their method, maximum and minimum values were predicted and the pixel values were modified to embed secret data. Thereafter, many scholars have proposed improvisations to the original PVO method. In this paper, a Reversible data hiding (RDH) method is proposed where the secret data is dispersed into two layers using different modes of operations. The second layer changes the dividing mode, and the first and the second layers do not take duplicate blocks. Under a fixed embedding capacity, threshold value and block size are controlled, complex blocks are filtered and the secret data is hidden in smooth blocks. This paper also compares the effectiveness of four well-known PVO series methods, the latest PVO methods, difference expansion (DE) method and reduced difference expansion (RDE) method. Experimental results show that the proposed method reduces distortion in the image, thereby enhancing the visual symmetry/quality compared to previous state-of-the-art methods and increasing its high application value.

A New Digital Watermarking Method for Data Integrity Protection in the Perception Layer of IoT

Since its introduction, IoT (Internet of Things) has enjoyed vigorous support from governments and research institutions around the world, and remarkable achievements have been obtained. The perception layer of IoT plays an important role as a link between the IoT and the real world; the security has become a bottleneck restricting the further development of IoT. The perception layer is a self-organizing network system consisting of various resource-constrained sensor nodes through wireless communication. Accordingly, the costly encryption mechanism cannot be applied to the perception layer. In this paper, a novel lightweight data integrity protection scheme based on fragile watermark is proposed to solve the contradiction between the security and restricted resource of perception layer. To improve the security, we design a position random watermark (PRW) strategy to calculate the embedding position by temporal dynamics of sensing data. The digital watermark is generated by one-way hash function SHA-1 before embedding to the dynamic computed position. In this way, the security vulnerabilities introduced by fixed embedding position can not only be solved effectively, but also achieve zero disturbance to the data. The security analysis and simulation results show that the proposed scheme can effectively ensure the integrity of the data at low cost.

An Adjustable Interpolation-based Data Hiding Algorithm Based on LSB Substitution and Histogram Shifting

Data hiding can be regarded as a type of image processing techniques. Other image processing operations are usually integrated to increase the embedding capacity or decrease the visual distortion. Interpolation is an example of this type of operation. However, previous interpolation-based data hiding algorithms suffered from low and fixed embedding capacity and high visual distortion. This study proposes a more effective two-stage data hiding algorithm based on interpolation, LSB substitution, and histogram shifting. First, the authors modify the formula for embedding capacity calculation and make some adjustments on the sample pixels determination. A threshold is used to obtain the block complexity and each embeddable pixel has a different amount of message embedded. Second, an LSB substitution method and an optimal pixel adjustment process are adopted to raise the image quality. Finally, the authors' proposed algorithm can support adjustable embedding capacity. Compared to the previous algorithm, the experimental results demonstrate the feasibility of the proposed method.

THE POINT-SET EMBEDDABILITY PROBLEM FOR PLANE GRAPHS

In this paper, we study the point-set embeddability problem, i.e., given a planar graph and a set of points, is there a mapping of the vertices to the points such that the resulting straight-line drawing is planar? It was known that this problem is NP-hard if the embedding can be chosen, but becomes polynomial for triangulated graphs of treewidth 3. We show here that in fact it can be answered for all planar graphs with a fixed combinatorial embedding that have constant treewidth and constant face-degree. We prove that as soon as one of the conditions is dropped (i.e., either the treewidth is unbounded or some faces have large degrees), point-set embeddability with a fixed embedding becomes NP-hard. The NP-hardness holds even for a 3-connected planar graph with constant treewidth, triangulated planar graphs, or 2-connected outer-planar graphs. These results also show that the convex point-set embeddability problem (where faces must be convex) is NP-hard, but we prove that it becomes polynomial if the graph has bounded treewidth and bounded maximum degree.