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

Surgery Surgery

Machine learning prediction algorithm for in-hospital mortality following body contouring.

In Plastic and reconstructive surgery ; h5-index 62.0

BACKGROUND : Body contouring is a common procedure, but it is worth attention due to concerns for a variety of complications, and even potential for death. As a result, the purpose of this study was to determine the key predictors following body contouring and create models for the risk of mortality using diverse machine learning models.

METHODS : The National Inpatient Sample (NIS) database from 2015 to 2017 was queried to identify patients undergoing body contouring. Candidate predictors such as demographics, comorbidities, personal history, postoperative complications, operative features were included. The outcome was the in-hospital mortality. Models were compared on area under the curve (AUC), accuracy, sensitivity, specificity, positive and negative predictive values, and decision curve analysis (DCA) curve.

RESULTS : Overall, 8214 patients undergoing body contouring were identified, among whom 141 (1.72%) patients died in the hospital. Variable importance plot demonstrated that sepsis was the variable with greatest importance across all machine learning algorithms, followed by Elixhauser Comorbidity Index (ECI), cardiac arrest (CA), and so forth. Naïve Bayes (NB) had a higher predictive performance (AUC 0.898, 95% CI 0.884 to 0.911) among these eight machine learning models. Similarly, in the DCA curve, the NB also demonstrated a higher net benefit (ie, the correct classification of in-hospital deaths considering a trade-off between false-negatives and false-positives)-over the other seven models across a range of threshold probability values.

CONCLUSIONS : The machine learning models, as indicated by our study, can be used to predict in-hospital deaths for patients at risk who underwent body contouring.

Peng Chi, Yang Fan, Jian Yu, Peng Liwei, Zhang Chenxu, Chen Chenxin, Lin Zhen, Li Yuejun, He Jia, Jin Zhichao

2023-Mar-21

Radiology Radiology

Does deep learning software improve the consistency and performance of radiologists with various levels of experience in assessing bi-parametric prostate MRI?

In Insights into imaging

OBJECTIVE : To investigate whether commercially available deep learning (DL) software improves the Prostate Imaging-Reporting and Data System (PI-RADS) scoring consistency on bi-parametric MRI among radiologists with various levels of experience; to assess whether the DL software improves the performance of the radiologists in identifying clinically significant prostate cancer (csPCa).

METHODS : We retrospectively enrolled consecutive men who underwent bi-parametric prostate MRI at a 3 T scanner due to suspicion of PCa. Four radiologists with 2, 3, 5, and > 20 years of experience evaluated the bi-parametric prostate MRI scans with and without the DL software. Whole-mount pathology or MRI/ultrasound fusion-guided biopsy was the reference. The area under the receiver operating curve (AUROC) was calculated for each radiologist with and without the DL software and compared using De Long's test. In addition, the inter-rater agreement was investigated using kappa statistics.

RESULTS : In all, 153 men with a mean age of 63.59 ± 7.56 years (range 53-80) were enrolled in the study. In the study sample, 45 men (29.80%) had clinically significant PCa. During the reading with the DL software, the radiologists changed their initial scores in 1/153 (0.65%), 2/153 (1.3%), 0/153 (0%), and 3/153 (1.9%) of the patients, yielding no significant increase in the AUROC (p > 0.05). Fleiss' kappa scores among the radiologists were 0.39 and 0.40 with and without the DL software (p = 0.56).

CONCLUSIONS : The commercially available DL software does not increase the consistency of the bi-parametric PI-RADS scoring or csPCa detection performance of radiologists with varying levels of experience.

Arslan Aydan, Alis Deniz, Erdemli Servet, Seker Mustafa Ege, Zeybel Gokberk, Sirolu Sabri, Kurtcan Serpil, Karaarslan Ercan

2023-Mar-20

Deep learning, Magnetic resonance imaging, Prostate cancer

General General

ASmiR: a machine learning framework for prediction of abiotic stress-specific miRNAs in plants.

In Functional & integrative genomics

Abiotic stresses have become a major challenge in recent years due to their pervasive nature and shocking impacts on plant growth, development, and quality. MicroRNAs (miRNAs) play a significant role in plant response to different abiotic stresses. Thus, identification of specific abiotic stress-responsive miRNAs holds immense importance in crop breeding programmes to develop cultivars resistant to abiotic stresses. In this study, we developed a machine learning-based computational model for prediction of miRNAs associated with four specific abiotic stresses such as cold, drought, heat and salt. The pseudo K-tuple nucleotide compositional features of Kmer size 1 to 5 were used to represent miRNAs in numeric form. Feature selection strategy was employed to select important features. With the selected feature sets, support vector machine (SVM) achieved the highest cross-validation accuracy in all four abiotic stress conditions. The highest cross-validated prediction accuracies in terms of area under precision-recall curve were found to be 90.15, 90.09, 87.71, and 89.25% for cold, drought, heat and salt respectively. Overall prediction accuracies for the independent dataset were respectively observed 84.57, 80.62, 80.38 and 82.78%, for the abiotic stresses. The SVM was also seen to outperform different deep learning models for prediction of abiotic stress-responsive miRNAs. To implement our method with ease, an online prediction server "ASmiR" has been established at https://iasri-sg.icar.gov.in/asmir/ . The proposed computational model and the developed prediction tool are believed to supplement the existing effort for identification of specific abiotic stress-responsive miRNAs in plants.

Pradhan Upendra Kumar, Meher Prabina Kumar, Naha Sanchita, Rao Atmakuri Ramakrishna, Kumar Upendra, Pal Soumen, Gupta Ajit

2023-Mar-20

Abiotic stress, Computational biology, Deep learning, Machine learning, miRNAs

Cardiology Cardiology

A cardiologist's guide to machine learning in cardiovascular disease prognosis prediction.

In Basic research in cardiology

A modern-day physician is faced with a vast abundance of clinical and scientific data, by far surpassing the capabilities of the human mind. Until the last decade, advances in data availability have not been accompanied by analytical approaches. The advent of machine learning (ML) algorithms might improve the interpretation of complex data and should help to translate the near endless amount of data into clinical decision-making. ML has become part of our everyday practice and might even further change modern-day medicine. It is important to acknowledge the role of ML in prognosis prediction of cardiovascular disease. The present review aims on preparing the modern physician and researcher for the challenges that ML might bring, explaining basic concepts but also caveats that might arise when using these methods. Further, a brief overview of current established classical and emerging concepts of ML disease prediction in the fields of omics, imaging and basic science is presented.

Kresoja Karl-Patrik, Unterhuber Matthias, Wachter Rolf, Thiele Holger, Lurz Philipp

2023-Mar-20

Arrhythmia, Artificial intelligence, Atherosclerosis, Genetics, Heart failure, Machine learning

General General

Artificial intelligence to predict outcomes of head and neck radiotherapy.

In Clinical and translational radiation oncology

Head and neck radiotherapy induces important toxicity, and its efficacy and tolerance vary widely across patients. Advancements in radiotherapy delivery techniques, along with the increased quality and frequency of image guidance, offer a unique opportunity to individualize radiotherapy based on imaging biomarkers, with the aim of improving radiation efficacy while reducing its toxicity. Various artificial intelligence models integrating clinical data and radiomics have shown encouraging results for toxicity and cancer control outcomes prediction in head and neck cancer radiotherapy. Clinical implementation of these models could lead to individualized risk-based therapeutic decision making, but the reliability of the current studies is limited. Understanding, validating and expanding these models to larger multi-institutional data sets and testing them in the context of clinical trials is needed to ensure safe clinical implementation. This review summarizes the current state of the art of machine learning models for prediction of head and neck cancer radiotherapy outcomes.

Bang Chulmin, Bernard Galaad, Le William T, Lalonde Arthur, Kadoury Samuel, Bahig Houda

2023-Mar

ADASYN, adaptive synthetic sampling, AI, artificial intelligence, ANN, artificial neural network, AUC, Area Under the ROC Curve, Artificial intelligence, BMI, body mass index, C-Index, concordance index, CART, Classification and Regression Tree, CBCT, cone-beam computed tomography, CIFE, conditional informax feature extraction, CNN, convolutional neural network, CRT, chemoradiation, CT, computed tomography, Cancer outcomes, DL, deep learning, DM, distant metastasis, DSC, Dice Similarity Coefficient, DSS, clinical decision support systems, DT, Decision Tree, DVH, Dose-volume histogram, GANs, Generative Adversarial Networks, GB, Gradient boosting, GPU, graphical process units, HNC, head and neck cancer, HPV, human papillomavirus, HR, hazard ratio, Head and neck cancer, IAMB, incremental association Markov blanket, IBDM, image based data mining, IBMs, image biomarkers, IMRT, intensity-modulated RT, KNN, k nearest neighbor, LLR, Local linear forest, LR, logistic regression, LRR, loco-regional recurrence, MIFS, mutual information based feature selection, ML, machine learning, MRI, Magnetic resonance imaging, MRMR, Minimum redundancy feature selection, Machine learning, N-MLTR, Neural Multi-Task Logistic Regression, NPC, nasopharynx, NTCP, Normal Tissue Complication Probability, OPC, oropharyngeal cancer, ORN, osteoradionecrosis, OS, overall survival, PCA, Principal component analysis, PET, Positron emission tomography, PG, parotid glands, PLR, Positive likelihood ratio, PM, pharyngeal mucosa, PTV, Planning target volumes, PreSANet, deep preprocessor module and self-attention, Predictive modeling, QUANTEC, Quantitative Analyses of Normal Tissue Effects in the Clinic, RF, random forest, RFC, random forest classifier, RFS, recurrence free survival, RLR, Rigid logistic regression, RRF, Regularized random forest, RSF, random survival forest, RT, radiotherapy, RTLI, radiation-induced temporal lobe injury, Radiomic, SDM, shared decision making, SMG, submandibular glands, SMOTE, synthetic minority over-sampling technique, STIC, sticky saliva, SVC, support vector classifier, SVM, support vector machine, XGBoost, extreme gradient boosting

General General

Machine learning-based immune prognostic model and ceRNA network construction for lung adenocarcinoma.

In Journal of cancer research and clinical oncology

PURPOSE : Lung adenocarcinoma (LUAD) is a malignant tumor with a high lethality rate. Immunotherapy has become a breakthrough in cancer treatment and improves patient survival and prognosis. Therefore, it is necessary to find new immune-related markers. However, the current research on immune-related markers in LUAD is not sufficient. Therefore, there is a need to find new immune-related biomarkers to help treat LUAD patients.

METHODS : In this study, a bioinformatics approach combined with a machine learning approach screened reliable immune-related markers to construct a prognostic model to predict the overall survival (OS) of LUAD patients, thus promoting the clinical application of immunotherapy in LUAD. The experimental data were obtained from The Cancer Genome Atlas (TCGA) database, including 535 LUAD and 59 healthy control samples. Firstly, the Hub gene was screened using a bioinformatics approach combined with the Support Vector Machine Recursive Feature Elimination algorithm; then, a multifactorial Cox regression analysis by constructing an immune prognostic model for LUAD and a nomogram to predict the OS rate of LUAD patients. Finally, the regulatory mechanism of Hub genes in LUAD was analyzed by ceRNA.

RESULTS : Five genes, ADM2, CDH17, DKK1, PTX3, and AC145343.1, were screened as potential immune-related genes in LUAD. Among them, ADM2 and AC145343.1 had a good prognosis in LUAD patients (HR < 1) and were novel markers. The remaining three genes screened were associated with poor prognosis in LUAD patients (HR > 1). In addition, the experimental results showed that patients in the low-risk group had better OS rates than those in the high-risk group (P < 0.001).

CONCLUSION : In this paper, we propose an immune prognostic model to predict OS rate in LUAD patients and show the correlation between five immune genes and the level of immune-related cell infiltration. It provides new markers and additional ideas for immunotherapy in patients with LUAD.

He Xiaoqian, Su Ying, Liu Pei, Chen Cheng, Chen Chen, Guan Haoqin, Lv Xiaoyi, Guo Wenjia

2023-Mar-20

Immune prognostic model, Lung adenocarcinoma, SVM-RFE, WGCNA, ceRNA