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

oncology Oncology

Comparison of Normal Tissue Complication Probability (NTCP) Models Using Machine Learning for Predicting Temporal Lobe Injury after Intensity-Modulated Radiotherapy in Nasopharyngeal Carcinoma: a Large Registry-Based Retrospective Study from China.

In Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology

PURPOSE : To develop predictive models with dosimetric and clinical variables for temporal lobe injury (TLI) in nasopharyngeal carcinoma (NPC) after intensity-modulated radiotherapy (IMRT).

MATERIALS AND METHODS : Data of 8194 NPC patients who received IMRT-based treatment were retrospectively reviewed. TLI was diagnosed by magnetic resonance imaging. Dosimetric factors were selected by penalized regression and machine learning, with area under the receiver operating curve (AUC) calculated. Cox proportional hazards models containing the most predictive dosimetric factor with/without clinical variables were performed. A nomogram was generated as a visualization of Cox regression for predicting TLI-free survival.

RESULTS : During median follow-up of 66.8 months (interquartile range [IQR] 54.2-82.2 months), 12.1% of patients (989/8194) developed TLI. Median latency from IMRT to TLI was 36 months (IQR 28-47 months). D0.5cc (dose delivered to 0.5-cm3 temporal-lobe volume) was the most predictive dosimetric factor (AUC: 0.799). Tolerance dose for 5% and 50% probabilities to develop TLI in 5 years were 65.06 Gy (95% confidence interval [CI]: 64.19-65.92) and 89.75 Gy (95% CI: 87.39-92.11), respectively. A nomogram comprising age, T stage, and D0.5cc significantly outperformed the model with only D0.5cc in predicting TLI (C-index: 0.78 vs. 0.737 in train set; 0.775 vs. 0.73 in test set; both P < 0.001). The nomogram-defined high-risk group had worse 5-year TLI-free survival.

CONCLUSIONS : D0.5cc of 65.06 Gy was the tolerance dose of the temporal lobe. Reducing D0.5cc decreased risk of TLI, especially in older patients with advanced T stage. The nomogram could predict TLI precisely and allow individualized follow-up management.

Wen Dan-Wan, Lin Li, Mao Yan-Ping, Chen Chun-Yan, Chen Fo-Ping, Wu Chen-Fei, Huang Xiao-Dan, Li Zhi-Xuan, Xu Si-Si, Kou Jia, Yang Xing-Li, Ma Jun, Sun Ying, Zhou Guan-Qun

2021-Jan-20

Intensity-modulated radiotherapy, Machine learning, Nasopharyngeal carcinoma, Nomogram, Normal tissue complication probability, Temporal lobe injury

Ophthalmology Ophthalmology

Machine learning approach for intraocular disease prediction based on aqueous humor immune mediator profiles.

In Ophthalmology ; h5-index 90.0

PURPOSE : Various immune mediators have crucial roles in the pathogenesis of intraocular diseases. Machine learning can be used to automatically select and weigh various predictors to develop models maximizing predictive power. However, these techniques have not yet been extensively applied studies focused on intraocular diseases. We evaluated whether five machine learning algorithms applied to the data of immune mediator levels in aqueous humor can accurately predict the actual diagnoses of 17 selected intraocular diseases, and identified which immune mediators drive the predictive power of a machine learning model.

DESIGN : Cross-sectional study.

PARTICIPANTS : 512 eyes with diagnoses of 17 intraocular diseases.

METHODS : Aqueous humor samples were collected, and the concentrations of 28 immune mediators were determined using a cytometric bead array. Each immune mediator was ranked according to its importance using five machine learning algorithms: random forest (RF), linear support vector machine (SVM), radial basis function SVM, decision tree and naïve Bayes classifier. Stratified k-fold cross-validation was used in evaluation of algorithms with dataset divided into training and test datasets.

MAIN OUTCOME MEASURES : The algorithms were evaluated in terms of precision, recall, accuracy, F-score, area under the receiver operating characteristics curve, area under the precision-recall curve and mean decrease in Gini index.

RESULTS : Among the five machine learning models, RF yielded the highest classification accuracy in multi-class differentiation of 17 intraocular diseases. The RF prediction models for vitreoretinal lymphoma, acute retinal necrosis, endophthalmitis, rhegmatogenous retinal detachment, and primary open angle glaucoma achieved the highest classification accuracy, precision, and recall. RF recognized vitreoretinal lymphoma, acute retinal necrosis, endophthalmitis, rhegmatogenous retinal detachment and primary open angle glaucoma with the top five F-scores. The three highest-ranking relevant immune mediators were IL-10, IP-10 and angiogenin for prediction of vitreoretinal lymphoma; Mig, IFN-γ and IP-10 for acute retinal necrosis; and IL-6, G-CSF and IL-8 for endophthalmitis.

CONCLUSIONS : RF algorithms based on 28 immune mediators in aqueous humor successfully predicted the diagnosis of vitreoretinal lymphoma, acute retinal necrosis, and endophthalmitis. Overall, the findings of the present study contribute to increased knowledge on new biomarkers that can potentially facilitate diagnosis of intraocular diseases in the future.

Nezu Naoya, Usui Yoshihiko, Saito Akira, Shimizu Hiroyuki, Asakage Masaki, Yamakawa Naoyuki, Tsubota Kinya, Wakabayashi Yoshihiro, Narimatsu Akitomo, Umazume Kazuhiko, Maruyama Katsuhiko, Sugimoto Masahiro, Kuroda Masahiko, Goto Hiroshi

2021-Jan-20

General General

Solar radiation prediction using boosted decision tree regression model: A case study in Malaysia.

In Environmental science and pollution research international

Reliable and accurate prediction model capturing the changes in solar radiation is essential in the power generation and renewable carbon-free energy industry. Malaysia has immense potential to develop such an industry due to its location in the equatorial zone and its climatic characteristics with high solar energy resources. However, solar energy accounts for only 2-4.6% of total energy utilization. Recently, in developed countries, various prediction models based on artificial intelligence (AI) techniques have been applied to predict solar radiation. In this study, one of the most recent AI algorithms, namely, boosted decision tree regression (BDTR) model, was applied to predict the changes in solar radiation based on collected data in Malaysia. The proposed model then compared with other conventional regression algorithms, such as linear regression and neural network. Two different normalization techniques (Gaussian normalizer binning normalizer), splitting size, and different input parameters were investigated to enhance the accuracy of the models. Sensitivity analysis and uncertainty analysis were introduced to validate the accuracy of the proposed model. The results revealed that BDTR outperformed other algorithms with a high level of accuracy. The funding of this study could be used as a reliable tool by engineers to improve the renewable energy sector in Malaysia and provide alternative sustainable energy resources.

Jumin Ellysia, Basaruddin Faridah Bte, Yusoff Yuzainee Bte Md, Latif Sarmad Dashti, Ahmed Ali Najah

2021-Jan-23

Boosted decision tree regression, Correlation coefficient, Machine learning algorithm, Neural network and linear regression, Solar radiation prediction, Weather parameters

Radiology Radiology

Association of AI quantified COVID-19 chest CT and patient outcome.

In International journal of computer assisted radiology and surgery

PURPOSE : Severity scoring is a key step in managing patients with COVID-19 pneumonia. However, manual quantitative analysis by radiologists is a time-consuming task, while qualitative evaluation may be fast but highly subjective. This study aims to develop artificial intelligence (AI)-based methods to quantify disease severity and predict COVID-19 patient outcome.

METHODS : We develop an AI-based framework that employs deep neural networks to efficiently segment lung lobes and pulmonary opacities. The volume ratio of pulmonary opacities inside each lung lobe gives the severity scores of the lobes, which are then used to predict ICU admission and mortality with three different machine learning methods. The developed methods were evaluated on datasets from two hospitals (site A: Firoozgar Hospital, Iran, 105 patients; site B: Massachusetts General Hospital, USA, 88 patients).

RESULTS : AI-based severity scores are strongly associated with those evaluated by radiologists (Spearman's rank correlation 0.837, [Formula: see text]). Using AI-based scores produced significantly higher ([Formula: see text]) area under the ROC curve (AUC) values. The developed AI method achieved the best performance of AUC = 0.813 (95% CI [0.729, 0.886]) in predicting ICU admission and AUC = 0.741 (95% CI [0.640, 0.837]) in mortality estimation on the two datasets.

CONCLUSIONS : Accurate severity scores can be obtained using the developed AI methods over chest CT images. The computed severity scores achieved better performance than radiologists in predicting COVID-19 patient outcome by consistently quantifying image features. Such developed techniques of severity assessment may be extended to other lung diseases beyond the current pandemic.

Fang Xi, Kruger Uwe, Homayounieh Fatemeh, Chao Hanqing, Zhang Jiajin, Digumarthy Subba R, Arru Chiara D, Kalra Mannudeep K, Yan Pingkun

2021-Jan-23

Artificial intelligence, COVID-19, Chest CT, Patient outcome, Severity scoring

Pathology Pathology

Deep learning system for lymph node quantification and metastatic cancer identification from whole-slide pathology images.

In Gastric cancer : official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association

BACKGROUND : Traditional diagnosis methods for lymph node metastases are labor-intensive and time-consuming. As a result, diagnostic systems based on deep learning (DL) algorithms have become a hot topic. However, current research lacks testing with sufficient data to verify performance. The aim of this study was to develop and test a deep learning system capable of identifying lymph node metastases.

METHODS : 921 whole-slide images of lymph nodes were divided into two cohorts: training and testing. For lymph node quantification, we combined Faster RCNN and DeepLab as a cascade DL algorithm to detect regions of interest. For metastatic cancer identification, we fused Xception and DenseNet-121 models and extracted features. Prospective testing to verify the performance of the diagnostic system was performed using 327 unlabeled images. We further validated the proposed system using Positive Predictive Value (PPV) and Negative Predictive Value (NPV) criteria.

RESULTS : We developed a DL-based system capable of automated quantification and identification of metastatic lymph nodes. The accuracy of lymph node quantification was shown to be 97.13%. The PPV of the combined Xception and DenseNet-121 model was 93.53%, and the NPV was 97.99%. Our experimental results show that the differentiation level of metastatic cancer affects the recognition performance.

CONCLUSIONS : The diagnostic system we established reached a high level of efficiency and accuracy of lymph node diagnosis. This system could potentially be implemented into clinical workflow to assist pathologists in making a preliminary screening for lymph node metastases in gastric cancer patients.

Hu Yajie, Su Feng, Dong Kun, Wang Xinyu, Zhao Xinya, Jiang Yumeng, Li Jianming, Ji Jiafu, Sun Yu

2021-Jan-23

Deep learning, Gastric cancer, Lymph node metastasis, Lymph node quantification

Public Health Public Health

Lilikoi V2.0: a deep learning-enabled, personalized pathway-based R package for diagnosis and prognosis predictions using metabolomics data.

In GigaScience

BACKGROUND : previously we developed Lilikoi, a personalized pathway-based method to classify diseases using metabolomics data. Given the new trends of computation in the metabolomics field, it is important to update Lilikoi software.

RESULTS : here we report the next version of Lilikoi as a significant upgrade. The new Lilikoi v2.0 R package has implemented a deep learning method for classification, in addition to popular machine learning methods. It also has several new modules, including the most significant addition of prognosis prediction, implemented by Cox-proportional hazards model and the deep learning-based Cox-nnet model. Additionally, Lilikoi v2.0 supports data preprocessing, exploratory analysis, pathway visualization, and metabolite pathway regression.

CONCULSION : Lilikoi v2.0 is a modern, comprehensive package to enable metabolomics analysis in R programming environment.

Fang Xinying, Liu Yu, Ren Zhijie, Du Yuheng, Huang Qianhui, Garmire Lana X

2021-Jan-23

classification, deep learning, metabolomics, neural network, pathway, prognosis, survival analysis, visualization