Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Public Health Public Health

Predictive Risk Models for Wound Infection-Related Hospitalization or ED Visits in Home Health Care Using Machine-Learning Algorithms.

In Advances in skin & wound care

OBJECTIVE : Wound infection is prevalent in home healthcare (HHC) and often leads to hospitalizations. However, none of the previous studies of wounds in HHC have used data from clinical notes. Therefore, the authors created a more accurate description of a patient's condition by extracting risk factors from clinical notes to build predictive models to identify a patient's risk of wound infection in HHC.

METHODS : The structured data (eg, standardized assessments) and unstructured information (eg, narrative-free text charting) were retrospectively reviewed for HHC patients with wounds who were served by a large HHC agency in 2014. Wound infection risk factors were identified through bivariate analysis and stepwise variable selection. Risk predictive performance of three machine learning models (logistic regression, random forest, and artificial neural network) was compared.

RESULTS : A total of 754 of 54,316 patients (1.39%) had a hospitalization or ED visit related to wound infection. In the bivariate logistic regression, language describing wound type in the patient's clinical notes was strongly associated with risk (odds ratio, 9.94; P < .05). The areas under the curve were 0.82 in logistic regression, 0.75 in random forest, and 0.78 in artificial neural network. Risk prediction performance of the models improved (by up to 13.2%) after adding risk factors extracted from clinical notes.

CONCLUSIONS : Logistic regression showed the best risk prediction performance in prediction of wound infection-related hospitalization or ED visits in HHC. The use of data extracted from clinical notes can improve the performance of risk prediction models.

Song Jiyoun, Woo Kyungmi, Shang Jingjing, Ojo Marietta, Topaz Maxim


Surgery Surgery

Thousands of induced germline mutations affecting immune cells identified by automated meiotic mapping coupled with machine learning.

In Proceedings of the National Academy of Sciences of the United States of America

Forward genetic studies use meiotic mapping to adduce evidence that a particular mutation, normally induced by a germline mutagen, is causative of a particular phenotype. Particularly in small pedigrees, cosegregation of multiple mutations, occasional unawareness of mutations, and paucity of homozygotes may lead to erroneous declarations of cause and effect. We sought to improve the identification of mutations causing immune phenotypes in mice by creating Candidate Explorer (CE), a machine-learning software program that integrates 67 features of genetic mapping data into a single numeric score, mathematically convertible to the probability of verification of any putative mutation-phenotype association. At this time, CE has evaluated putative mutation-phenotype associations arising from screening damaging mutations in ∼55% of mouse genes for effects on flow cytometry measurements of immune cells in the blood. CE has therefore identified more than half of genes within which mutations can be causative of flow cytometric phenovariation in Mus musculus The majority of these genes were not previously known to support immune function or homeostasis. Mouse geneticists will find CE data informative in identifying causative mutations within quantitative trait loci, while clinical geneticists may use CE to help connect causative variants with rare heritable diseases of immunity, even in the absence of linkage information. CE displays integrated mutation, phenotype, and linkage data, and is freely available for query online.

Xu Darui, Lyon Stephen, Bu Chun Hui, Hildebrand Sara, Choi Jin Huk, Zhong Xue, Liu Aijie, Turer Emre E, Zhang Zhao, Russell Jamie, Ludwig Sara, Mahrt Elena, Nair-Gill Evan, Shi Hexin, Wang Ying, Zhang Duanwu, Yue Tao, Wang Kuan-Wen, SoRelle Jeffrey A, Su Lijing, Misawa Takuma, McAlpine William, Sun Lei, Wang Jianhui, Zhan Xiaoming, Choi Mihwa, Farokhnia Roxana, Sakla Andrew, Schneider Sara, Coco Hannah, Coolbaugh Gabrielle, Hayse Braden, Mazal Sara, Medler Dawson, Nguyen Brandon, Rodriguez Edward, Wadley Andrew, Tang Miao, Li Xiaohong, Anderton Priscilla, Keller Katie, Press Amanda, Scott Lindsay, Quan Jiexia, Cooper Sydney, Collie Tiffany, Qin Baifang, Cardin Jennifer, Simpson Rochelle, Tadesse Meron, Sun Qihua, Wise Carol A, Rios Jonathan J, Moresco Eva Marie Y, Beutler Bruce


ENU mutagenesis, automated meiotic mapping, flow cytometry, immune cells, machine learning

General General

Knowledge Implementation and Transfer With an Adaptive Learning Network for Real-Time Power Management of the Plug-in Hybrid Vehicle.

In IEEE transactions on neural networks and learning systems

Essential decision-making tasks such as power management in future vehicles will benefit from the development of artificial intelligence technology for safe and energy-efficient operations. To develop the technique of using neural network and deep learning in energy management of the plug-in hybrid vehicle and evaluate its advantage, this article proposes a new adaptive learning network that incorporates a deep deterministic policy gradient (DDPG) network with an adaptive neuro-fuzzy inference system (ANFIS) network. First, the ANFIS network is built using a new global K-fold fuzzy learning (GKFL) method for real-time implementation of the offline dynamic programming result. Then, the DDPG network is developed to regulate the input of the ANFIS network with the real-world reinforcement signal. The ANFIS and DDPG networks are integrated to maximize the control utility (CU), which is a function of the vehicle's energy efficiency and the battery state-of-charge. Experimental studies are conducted to testify the performance and robustness of the DDPG-ANFIS network. It has shown that the studied vehicle with the DDPG-ANFIS network achieves 8% higher CU than using the MATLAB ANFIS toolbox on the studied vehicle. In five simulated real-world driving conditions, the DDPG-ANFIS network increased the maximum mean CU value by 138% over the ANFIS-only network and 5% over the DDPG-only network.

Zhou Quan, Zhao Dezong, Shuai Bin, Li Yanfei, Williams Huw, Xu Hongming


General General

Integrating molecular graph data of drugs and multiple -omic data of cell lines for drug response prediction.

In IEEE/ACM transactions on computational biology and bioinformatics

Previous studies have either learned drugs features from their string or numeric representations, which are not natural forms of drugs, or only used genomic data of cell lines for the drug response prediction problem. Here, we proposed a deep learning model, GraOmicDRP, to learn drugs features from their graph representation and integrate multiple -omic data of cell lines. In GraOmicDRP, drugs are represented as graphs of bindings among atoms; meanwhile, cell lines are depicted by not only genomic but also transcriptomic and epigenomic data. Graph convolutional and convolutional neural networks were used to learn the representation of drugs and cell lines, respectively. A combination of the two representations was then used to be representative of each pair of drug-cell line. Finally, the response value of each pair was predicted by a fully connected network. Experimental results indicate that transcriptomic data shows the best among single -omic data; meanwhile, the combinations of transcriptomic and other omic data achieved the best performance overall in terms of both Root Mean Square Error and Pearson correlation coefficient. In addition, we also show that GraOmicDRP outperforms some state-of-the-art methods, including ones integrating omic data with drug information such as GraphDRP, and ones using omic data without drug information such as DeepDR and MOLI.

Nguyen Giang Thi Thu, Vu Duc-Hoa, Le Duc-Hau


Pathology Pathology

A Polarization-Imaging-Based Machine Learning Framework for Quantitative Pathological Diagnosis of Cervical Precancerous Lesions.

In IEEE transactions on medical imaging ; h5-index 74.0

Polarization images encode high resolution microstructural information even at low resolution. We propose a framework combining polarization imaging and traditional microscopy imaging, constructing a dual-modality machine learning framework that is not only accurate but also generalizable and interpretable. We demonstrate the viability of our proposed framework using the cervical intraepithelial neoplasia grading task, providing a polarimetry feature parameter to quantitatively characterize microstructural variations with lesion progression in hematoxylin-eosin-stained pathological sections of cervical precancerous tissues. By taking advantages of polarization imaging techniques and machine learning methods, the model enables interpretable and quantitative diagnosis of cervical precancerous lesion cases with improved sensitivity and accuracy in a low-resolution and wide-field system. The proposed framework applies routine image-analysis technology to identify the macro-structure and segment the target region in H&E-stained pathological images, and then employs emerging polarization method to extract the micro-structure information of the target region, which intends to expand the boundary of the current image-heavy digital pathology, bringing new possibilities for quantitative medical diagnosis.

Dong Yang, Wan Jiachen, Wang Xingjian, Xue Jing-Hao, Zou Jibin, He Honghui, Li Pengcheng, Hou Anli, Ma Hui


General General

Automatically evaluating balance using machine learning and data from a single inertial measurement unit.

In Journal of neuroengineering and rehabilitation ; h5-index 53.0

BACKGROUND : Recently, machine learning techniques have been applied to data collected from inertial measurement units to automatically assess balance, but rely on hand-engineered features. We explore the utility of machine learning to automatically extract important features from inertial measurement unit data for balance assessment.

FINDINGS : Ten participants with balance concerns performed multiple balance exercises in a laboratory setting while wearing an inertial measurement unit on their lower back. Physical therapists watched video recordings of participants performing the exercises and rated balance on a 5-point scale. We trained machine learning models using different representations of the unprocessed inertial measurement unit data to estimate physical therapist ratings. On a held-out test set, we compared these learned models to one another, to participants' self-assessments of balance, and to models trained using hand-engineered features. Utilizing the unprocessed kinematic data from the inertial measurement unit provided significant improvements over both self-assessments and models using hand-engineered features (AUROC of 0.806 vs. 0.768, 0.665).

CONCLUSIONS : Unprocessed data from an inertial measurement unit used as input to a machine learning model produced accurate estimates of balance performance. The ability to learn from unprocessed data presents a potentially generalizable approach for assessing balance without the need for labor-intensive feature engineering, while maintaining comparable model performance.

Kamran Fahad, Harrold Kathryn, Zwier Jonathan, Carender Wendy, Bao Tian, Sienko Kathleen H, Wiens Jenna


Balance training, Machine learning, Telerehabilitation, Wearable sensors