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

General General

3D car-detection based on a Mobile Deep Sensor Fusion Model and real-scene applications.

In PloS one ; h5-index 176.0

Unmanned vehicles need to make a comprehensive perception of the surrounding environmental information during driving. Perception of automotive information is of significance. In the field of automotive perception, the sterevision of car-detection plays a vital role and sterevision can calculate the length, width, and height of a car, making the car more specific. However, under the existing technology, it is impossible to obtain accurate detection in a complex environment by relying on a single sensor. Therefore, it is particularly important to study the complex sensing technology based on multi-sensor fusion. Recently, with the development of deep learning in the field of vision, a mobile sensor-fusion method based on deep learning is proposed and applied in this paper--Mobile Deep Sensor Fusion Model (MDSFM). The content of this article is as follows. It does a data processing that projects 3D data to 2D data, which can form a dataset suitable for the model, thereby training data more efficiently. In the modules of LiDAR, it uses a revised squeezeNet structure to lighten the model and reduce parameters. In the modules of cameras, it uses the improved design of detecting module in R-CNN with a Mobile Spatial Attention Module (MSAM). In the fused part, it uses a dual-view deep fusing structure. And then it selects images from the KITTI's datasets for validation to test this model. Compared with other recognized methods, it shows that our model has a fairly good performance. Finally, it implements a ROS program on the experimental car and our model is in good condition. The result shows that it can improve performance of detecting easy cars significantly through MDSFM. It increases the quality of the detected data and improves the generalized ability of car-detection model. It improves contextual relevance and preserves background information. It remains stable in driverless environments. It is applied in the realistic scenario and proves that the model has a good practical value.

Zhang Qiang, Hu Xiaojian, Su Ziyi, Song Zhihong

2020

General General

Forecasting outbound student mobility: A machine learning approach.

In PloS one ; h5-index 176.0

BACKGROUND : A country's ability to become a prominent knowledge economy is tied closely to its ability to acquire skilled people who can compete internationally while resolving challenges of the future. To equip students with competence that can only by gained by being immersed in a foreign environment, outbound mobility is vital.

METHODS : To analyze outbound student mobility in Taiwan using time series methods, this study aims to propose a hybrid approach FSDESVR which combines feature selection (FS) and support vector regression (SVR) with differential evolution (DE). FS and a DE algorithm were used for selecting reliable input features and determining the optimal initial parameters of SVR, respectively, to achieve high forecast accuracy.

RESULTS : The proposed approach was examined using a dataset of outbound Taiwanese student mobility to ten countries between 1998 and 2018. Without the requirements of any special conditions for the proprieties of the objective function and constraints, the FSDESVR model retained the advantage of FS, SVR, and DE. A comparison of the FSDESVR model and other forecasting models revealed that FSDESVR provided the lowest mean absolute percentage error (MAPE) and root mean square error (RMSE) results for all the analyzed nations. The experimental results indicate that FSDESVR achieved higher forecasting accuracy than the compared models from the literature.

CONCLUSION : With the recognition of outbound values, key findings of Taiwanese outbound student mobility, and accurate application of the FSDESVR model, education administration units are exposed to a more in-depth view of future student mobility, which enables the implement of a more accurate education curriculum.

Yang Stephanie, Chen Hsueh-Chih, Chen Wen-Ching, Yang Cheng-Hong

2020

General General

Shape-to-graph mapping method for efficient characterization and classification of complex geometries in biological images.

In PLoS computational biology

With the ever-increasing quality and quantity of imaging data in biomedical research comes the demand for computational methodologies that enable efficient and reliable automated extraction of the quantitative information contained within these images. One of the challenges in providing such methodology is the need for tailoring algorithms to the specifics of the data, limiting their areas of application. Here we present a broadly applicable approach to quantification and classification of complex shapes and patterns in biological or other multi-component formations. This approach integrates the mapping of all shape boundaries within an image onto a global information-rich graph and machine learning on the multidimensional measures of the graph. We demonstrated the power of this method by (1) extracting subtle structural differences from visually indistinguishable images in our phenotype rescue experiments using the endothelial tube formations assay, (2) training the algorithm to identify biophysical parameters underlying the formation of different multicellular networks in our simulation model of collective cell behavior, and (3) analyzing the response of U2OS cell cultures to a broad array of small molecule perturbations.

Pilcher William, Yang Xingyu, Zhurikhina Anastasia, Chernaya Olga, Xu Yinghan, Qiu Peng, Tsygankov Denis

2020-Sep

General General

Postimplementation Evaluation of a Machine Learning-Based Deterioration Risk Alert to Enhance Sepsis Outcome Improvements.

In Nursing administration quarterly

Machine learning-based early warning systems (EWSs) can detect clinical deterioration more accurately than point-score tools. In patients with sepsis, however, the timing and scope of sepsis interventions relative to an advanced EWS alert are not well understood. The objectives of this study were to evaluate the timing and frequency of fluid bolus therapy, new antibiotics, and Do Not Resuscitate (DNR) status relative to the time of an advanced EWS alert. We conducted 2 rounds of chart reviews of patients with an EWS alert admitted to community hospitals of a large integrated health system in Northern California (round 1: n = 21; round 2: n = 47). We abstracted patient characteristics and process measures of sepsis intervention and performed summary statistics. Sepsis decedents were older and sicker at admission and alert time. Most EWS alerts occurred near admission, and most sepsis interventions occurred before the first alert. Of 14 decedents, 12 (86%) had a DNR order before death. Fluid bolus therapy and new intravenous antibiotics frequently occurred before the alert, suggesting a potential overlap between sepsis care in the emergency department and the first alert following admission. Two tactics to minimize alerts that may not motivate new sepsis interventions are (1) locking out the alert during the immediate time after hospital admission; and (2) triaging and reviewing patients with alerts outside of the unit before activating a bedside response. Some decedents may have been on a palliative/end-of-life trajectory, because DNR orders were very common among decedents. Nurse leaders sponsoring or leading machine learning projects should consider tactics to reduce false-positive and clinically meaningless alerts dispatched to clinical staff.

Linnen Daniel T, Hu Xiao, Stephens Caroline E

General General

Artificial Intelligence Forecasting Census and Supporting Early Decisions.

In Nursing administration quarterly

Matching resources to demand is a daily challenge for hospital leadership. In interdisciplinary collaboration, nurse leaders and data scientists collaborated to develop advanced machine learning to support early proactive decisions to improve ability to accommodate demand. When hundreds or even thousands of forecasts are made, it becomes important to let machines do the hard work of mathematical pattern recognition, while efficiently using human feedback to address performance and accuracy problems. Nurse leaders and data scientists collaborated to create a usable, low-error predictive model to let machines do the hard work of pattern recognition and model evaluation, while efficiently using nurse leader domain expert feedback to address performance and accuracy problems. During the evaluation period, the overall census mean absolute percentage error was 3.7%. ALEx's predictions have become part of the team's operational norm, helping them anticipate and prepare for census fluctuations. This experience suggests that operational leaders empowered with effective predictive analytics can take decisive proactive staffing and capacity management choices. Predictive analytic information can also result in team learning and ensure safety and operational excellence is supported in all aspects of the organization.

Griner Todd E, Thompson Michael, High Heidi, Buckles Jenny

Surgery Surgery

[Analysis of treatment modalities and prognosis of patients with gallbladder cancer in China from 2010 to 2017].

In Zhonghua wai ke za zhi [Chinese journal of surgery]

Objective: To evaluate the clinical characteristics and prognosis of gallbladder cancer (GBC) patients in China. Methods: This retrospective multicenter cohort study enrolled 3 528 consecutive GBC patients diagnosed between January 2010 to December 2017 in 15 hospitals from 10 provinces. There were 1 345 (38.12%) males and 2 183 (61.88%) females.The age of diagnosis was (63.7±10.8) years old (range: 26 to 99 years old) .There were 213 patients (6.04%) in stage 0 to Ⅰ, whereas 1 059 (30.02%) in stage Ⅱ to Ⅲ, 1 874 (53.12%) in stage Ⅳ, and 382 (10.83%) unavailable. Surgery was performed on 2 255 patients (63.92%) . Three hundred and thirty-six patients received chemotherapy or radiotherapy (9.52%; of which 172 were palliative); 1 101 (31.21%) received only supportive treatment.The patient source, treatment and surgery, pathology, concomitant gallstone, and prognosis were analyzed. Results: Among the 3 528 GBC patients, 959 (27.18%) were from East China, 603 (17.09%) from East-North China, 1 533 (43.45%) from Central China, and 433(12.27%) from West China. Among the 1 578 resectable tumor, 665 (42.14%) underwent radical surgery, 913 (57.86%) underwent surgery that failed to follow the guidelines.Eight hundred and ninety-one (56.46%) patients were diagnosed before surgery, 254 (16.10%) during surgery, and 381 (24.14%) after surgery (time point of diagnosis couldn't be determined in 52 patients) .Among the 1 578 patients with resectable tumor, 759 (48.10%) had concomitant gallstone.Among the 665 patients underwent radical surgery, 69 (10.4%) showed positive resection margin, 510 (76.7%) showed negative resection margin, and 86 (12.9%) unreported margin status.The 5-year overall survival rate (5yOS) for the 3 528-patient cohort was 23.0%.The 5yOS for patients with resectable tumor was 39.6%, for patients with stage ⅣB tumor without surgery was 5.4%, and for patients with stage ⅣB tumor underwent palliative surgery was 4.7%. Conclusions: More than half GBC patients in China are diagnosed in stage Ⅳ.Curative intent surgery is valuable in improving prognosis of resectable GBC.The treatment of GBC needs further standardization.Effective comprehensive treatment for GBC is in urgent need.

Ren T, Li Y S, Geng Y J, Li M L, Wu X S, Wu W W, Wang X A, Shu Y J, Bao R F, Dong P, Gong W, Gu J, Wang X F, Lu J H, Mu J S, Pan W H, Zhang X, Zhang X L, Fei Z W, Zhang Z Y, Wang Y, Cao H, Sun B, Cui Y F, Zhu C F, Li B, Zheng L H, Qian Y B, Liu J, Dang X Y, Liu C, Peng S Y, Quan Z W, Liu Y B

2020-Sep-01

Disease attributes, Gallbladder neoplasms, Prognosis, Surgery