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

oncology Oncology

A data-driven approach to a chemotherapy recommendation model based on deep learning for patients with colorectal cancer in Korea.

In BMC medical informatics and decision making ; h5-index 38.0

BACKGROUND : Clinical Decision Support Systems (CDSSs) have recently attracted attention as a method for minimizing medical errors. Existing CDSSs are limited in that they do not reflect actual data. To overcome this limitation, we propose a CDSS based on deep learning.

METHODS : We propose the Colorectal Cancer Chemotherapy Recommender (C3R), which is a deep learning-based chemotherapy recommendation model. Our model improves on existing CDSSs in which data-based decision making is not well supported. C3R is configured to study the clinical data collected at the Gachon Gil Medical Center and to recommend appropriate chemotherapy based on the data. To validate the model, we compared the treatment concordance rate with the National Comprehensive Cancer Network (NCCN) Guidelines, a representative set of cancer treatment guidelines, and with the results of the Gachon Gil Medical Center's Colorectal Cancer Treatment Protocol (GCCTP).

RESULTS : For the C3R model, the treatment concordance rates with the NCCN guidelines were 70.5% for Top-1 Accuracy and 84% for Top-2 Accuracy. The treatment concordance rates with the GCCTP were 57.9% for Top-1 Accuracy and 77.8% for Top-2 Accuracy.

CONCLUSIONS : This model is significant, i.e., it is the first colon cancer treatment clinical decision support system in Korea that reflects actual data. In the future, if sufficient data can be secured through cooperation among multiple organizations, more reliable results can be obtained.

Park Jin-Hyeok, Baek Jeong-Heum, Sym Sun Jin, Lee Kang Yoon, Lee Youngho


Chemotherapy recommendation, Colorectal Cancer, Deep learning, Knowledge-based clinical decision support system (CDSS)

General General

Multi-scale supervised clustering-based feature selection for tumor classification and identification of biomarkers and targets on genomic data.

In BMC genomics ; h5-index 78.0

BACKGROUND : The small number of samples and the curse of dimensionality hamper the better application of deep learning techniques for disease classification. Additionally, the performance of clustering-based feature selection algorithms is still far from being satisfactory due to their limitation in using unsupervised learning methods. To enhance interpretability and overcome this problem, we developed a novel feature selection algorithm. In the meantime, complex genomic data brought great challenges for the identification of biomarkers and therapeutic targets. The current some feature selection methods have the problem of low sensitivity and specificity in this field.

RESULTS : In this article, we designed a multi-scale clustering-based feature selection algorithm named MCBFS which simultaneously performs feature selection and model learning for genomic data analysis. The experimental results demonstrated that MCBFS is robust and effective by comparing it with seven benchmark and six state-of-the-art supervised methods on eight data sets. The visualization results and the statistical test showed that MCBFS can capture the informative genes and improve the interpretability and visualization of tumor gene expression and single-cell sequencing data. Additionally, we developed a general framework named McbfsNW using gene expression data and protein interaction data to identify robust biomarkers and therapeutic targets for diagnosis and therapy of diseases. The framework incorporates the MCBFS algorithm, network recognition ensemble algorithm and feature selection wrapper. McbfsNW has been applied to the lung adenocarcinoma (LUAD) data sets. The preliminary results demonstrated that higher prediction results can be attained by identified biomarkers on the independent LUAD data set, and we also structured a drug-target network which may be good for LUAD therapy.

CONCLUSIONS : The proposed novel feature selection method is robust and effective for gene selection, classification, and visualization. The framework McbfsNW is practical and helpful for the identification of biomarkers and targets on genomic data. It is believed that the same methods and principles are extensible and applicable to other different kinds of data sets.

Xu Da, Zhang Jialin, Xu Hanxiao, Zhang Yusen, Chen Wei, Gao Rui, Dehmer Matthias


Biomarker, Classification, Clustering, Feature selection, Machine learning, Therapeutic target

Public Health Public Health

Improvement on Hypertension Management with Pharmacological and Non-Pharmacological Approaches: Current Perspectives.

In Current pharmaceutical design ; h5-index 57.0

PURPOSE : Improving hypertension management is still one of the severest challenges in public health worldwide. Existing guidelines do not reach a consensus on the optimal Blood Pressure (BP) target. Therefore, how to effectively manage hypertension based on individual characteristics of patients, combined with pharmacological and nonpharmacological approach, has become a problem to be urgently considered.

METHODS : Reports published in PubMed that covered Pharmacological and Non-Pharmacological Approaches in subjects taking hypertension management were reviewed by the group independently and collectively. Practical recommendations for hypertension management were established by the panel.

RESULTS : Pharmacological mechanism, action characteristics and main adverse reactions varied across different pharmacological agents, and patients with hypertension often require a combination of antihypertensive medications to achieve target BP range. Non-pharmacological treatment provides an additional effective method for improving therapy adherence and long-term BP control, reducing Cardiovascular Diseases risk and slowing down the progression of the disease.

CONCLUSION : This review summarizes the available literature on the most convincing Guideline-principles, pharmacological treatment, biotechnology interference, interventional surgical treatment, managing hypertension with technical means of big data, Artificial Intelligence and Behavioral Intervention, as well as providing future directions, for facilitating Current and Developing knowledge into clinical implementation.

Hong Dongsheng, Shan Wenya


Antihypertensive drugs, artificial intelligence, biotechnology interference, hypertension management, pharmacological approaches\n

Surgery Surgery

A brief history of artificial intelligence and robotic surgery in orthopedics & traumatology and future expectations.

In Joint diseases and related surgery

Recently, the rate of the production and renewal of information makes it almost impossible to be updated. It is quite difficult to process and interpret large amounts of data by human beings. Unlimited memory capacities, learning abilities, artificial intelligence (AI) applications, and robotic surgery techniques cause orthopedic surgeons to be concerned about losing their jobs. The idea of AI, which was first introduced in 1956, has evolved over time by revealing deep learning and evolutionary plexus that can mimic the human neuron cell. Image processing is the leading improvement in developed algorithms. Theoretically, these algorithms appear to be quite successful in interpreting medical images and orthopedic decision support systems for preoperative evaluation. Robotic surgeons have emerged as significant competitors in carrying out the taken decisions. The first robotic applications of orthopedic surgery started in 1992 with the ROBODOC system. Applications started with hip arthroplasty continued with knee arthroplasty. Publications indicate that problems such as blood loss and infection caused by the long operation time in the early stages have been overcome in time with the help of learning systems. Comparative studies conducted with humans indicate that robots are better than humans in providing limb lengthening, patient satisfaction, and cost. As in all new technologies, the developments in both AI applications and robotics surgery indicate that technology is in favor in terms of cost/benefit analyses. Although studies indicate that new technologies are more successful than humans, the replacement of technology with experience and long-term results with traditional methods will not be observed in the near future.

Beyaz Salih


Pathology Pathology

A Demonstration of Machine Learning in Detecting Frequency Following Responses in American Neonates.

In Perceptual and motor skills

In this study, we sought to evaluate the efficiencies of multiple machine learning algorithms in detecting neonates' Frequency Following Responses (FFRs). We recorded continuous brainwaves from 43 American neonates in response to a pre-recorded monosyllable/i/with a rising frequency contour. Recordings were classified into response and no response categories. Six response features were extracted from each recording and served as predictors in FFR identification. Twenty-three supervised machine learning algorithms with mean efficiency values of 86.0%, 94.4%, 97.2%, and 97.5% when 1, 10, 100, and 1000 random iterations were implemented, respectively. These high efficiency values obtained from the neonatal FFRs demonstrate that machine learning algorithms can help assess pitch processing in neonates and can be applied to auditory screening and intervention services for neonates at risk for disorders associated with decreased pitch processing.

Hart Breanna N, Jeng Fuh-Cherng


auditory electrophysiology, efficiency, frequency following response, machine learning, neonates, random iteration

General General

Predicting Daily Sheltering Arrangements among Youth Experiencing Homelessness Using Diary Measurements Collected by Ecological Momentary Assessment.

In International journal of environmental research and public health ; h5-index 73.0

Youths experiencing homelessness (YEH) often cycle between various sheltering locations including spending nights on the streets, in shelters and with others. Few studies have explored the patterns of daily sheltering over time. A total of 66 participants completed 724 ecological momentary assessments that assessed daily sleeping arrangements. Analyses applied a hypothesis-generating machine learning algorithm (component-wise gradient boosting) to build interpretable models that would select only the best predictors of daily sheltering from a large set of 92 variables while accounting for the correlated nature of the data. Sheltering was examined as a three-category outcome comparing nights spent literally homeless, unstably housed or at a shelter. The final model retained 15 predictors. These predictors included (among others) specific stressors (e.g., not having a place to stay, parenting and hunger), discrimination (by a friend or nonspecified other; due to race or homelessness), being arrested and synthetic cannabinoids use (a.k.a., "kush"). The final model demonstrated success in classifying the categorical outcome. These results have implications for developing just-in-time adaptive interventions for improving the lives of YEH.

Suchting Robert, Businelle Michael S, Hwang Stephen W, Padhye Nikhil S, Yang Yijiong, Santa Maria Diane M


daily sleeping arrangement, data science, electronic momentary assessment, machine learning, youth experiencing homelessness