Using Digital Phenotyping to Discriminate Unipolar Depression and Bipolar Disorder: Systematic Review by Rongrong Zhong, XiaoHui Wu, Jun Chen, Yiru Fang

“…For each included study, the following information was extracted: demographic characteristics, diagnostic criteria or psychiatric assessments, details of the technological tools and data types, duration of data collection, data preprocessing methods, selected variables or features, machine learning algorithms or statistical tests, validation, and main findings. …”
Get full text

Long-term Variation of Sensible Heat Flux over the Qinghai-Xizang Plateau from 1984 to 2020 by Runzhi LEI, Ye YU, Guobin ZHOU, Jianglin LI, Yanfei LIU

“…Sensible heat flux （SH） is one of the main physical quantities characterizing the thermal effect of the Qinghai-Xizang Plateau， which is affected by the surface temperature， air temperature， heat exchange coefficient and wind speed.However， different heat exchange coefficient （CH）calculation methods give SH with different values.To solve this， in this study， three CH calculation methods are used to calculate the SH using the conventional meteorological observation data from 89 stations on the Qinghai-Xizang Plateau for 1984 -2020.The SHs obtained by different CH algorithms are verified using in situ SH observations from 5 flux stations.The results indicate that the SH calculated by Chen and Weng （1984） （CH-CW） scheme is the best in terms of the smallest bias between the caculations and observaitons.The long-term trend of SH calculated with CH-CW scheme and the characteristics and causes of the long-term change over the Qinghai-Xizang Plateau are analyzed using PLFIM piecewise linear fitting model.The results show that the trend of the annual SH over the Qinghai-Xizang Plateau have turning points at 1999 and 2009.The SH decreased from 1984 to 1999， increased significantly from 1999 to 2009， and showed a weak downward trend from 2009 to 2020.The turning points of SH trend in summer are 2000 and 2010， respectively.The turning points of SH trend in other seasons are the same as the annual SH.The overall trend of SH in spring， summer and autumn is consistent with the annual trend， characterized by "weakened - strengthened - weakened".The SH in winter continued to increase from 2009 to 2020， but with a much weaker trend compared with that from 1999 to 2009.Attribution analysis shows that the decrease of annual SH from 1984 to 1999 is mainly attributed to the decrease of wind speed； the increase of annual SH from 1999 to 2009 was mainly due to the increase of surface-air temperature difference caused by the significant increase of surface temperature， and less to the slow down of wind speed increase.From 2009 to 2020， the significant increase of wind speed led to a decrease of CH， and the relative faster increase of air temperature compared to the increase of the surface temperature lead to a decrease in the surface-air temperature difference， both of which contributed to the decrease of the annual average SH during this period， with the negative contribution from the surface-air temperature difference much lager than that from the CH change.…”
Get full text

Development of a warning model for drug-induced liver injury in the older patients by Qiaozhi Hu, Qiaozhi Hu, Xiaoqi Li, Xiaoqi Li, Dan Zou, Zhiyao He, Zhiyao He, Ting Xu

“…The performance of 8 ML algorithms—XGBoost, LightGBM, Random Forest, AdaBoost, CatBoost, Gradient Boosting Decision Trees, Artificial Neural Network, and TabNet—was assessed. …”
Get full text

Features of Statistical Accounting of Allergic Diseases in Children — Evidence from Moscow by Anita R. Denisova, Alexander B. Malahov, Alexandr N. Pampura, Elena A. Vishneva, Margarita A. Soloshenko, Nikoloz M. Gaboshvili, Leyla S. Namazova-Baranova

“…The differences in the incidence rates of allergic diseases revealed by a comparative analysis of data from various sources — UMIAS and FSO No. 12 — indicate the need to improve both the system of statistical registration of incidence and the development of modern algorithms for early diagnosis and dynamic monitoring of children with allergies.…”
Get full text

Neuro-fuzzy inference system and white shark optimization of coagulation-flocculation of aquaculture wastewater treatment by A.F. Mohamed, H. Rezk

“…Therefore, the objective of this study is determining the optimal operating condition of coagulation-flocculation through optimizing the values of the three input parameters.METHODS: Artificial intelligence and recent optimzation algorithms are integrated to achieve the purpose of this study work. …”
Get full text

Divergent crop mapping accuracies across different field types in smallholder farming regions by Xin Huang, Anton Vrieling, Yue Dou, Xueying Li, Andrew Nelson

“…This study provides a new perspective on crop type mapping in smallholder farming regions by using a simple and relevant categorization of field types and offers valuable insights on potentials and limitations for large-scale crop type mapping using machine learning algorithms.…”
Get full text

Comparing acoustic representations for deep learning-based classification of underwater acoustic signals: A case study on orca (Orcinus orca) vocalizations by Fabio Frazao, Ruth Joy, Michael Dowd

“…The spectrogram is well-suited for many such pattern recognition algorithms, including those developed for computer vision, such as convolutional neural networks. …”
Get full text

Expression Characteristics and Prognostic Value of KLRG2 in Endometrial Cancer: A Comprehensive Analysis Based on Multi-Omics Data by Xiaoyan Huang, Ailian Li, Dianbo Xu

“…Epigenetic regulation was assessed through methylation profiling (UALCAN/MethSurv), and immune correlations were evaluated using TIMER/ESTIMATE algorithms. <b>Results</b>: KLRG2 was significantly overexpressed in EC tissues compared to normal endometrium (<i>p</i> < 0.001), validated by immunohistochemistry and qPCR. …”
Get full text

Characterisation of cardiovascular disease (CVD) incidence and machine learning risk prediction in middle-aged and elderly populations: data from the China health and retirement lo... by Qing Huang, Zihao Jiang, Bo Shi, Jiaxu Meng, Li Shu, Fuyong Hu, Jing Mi

“…Five machine learning (ML) algorithms were employed for risk prediction. Data preprocessing included missing value imputation via random forest. …”
Get full text

Medical Data over Sound—CardiaWhisper Concept by Radovan Stojanović, Jovan Đurković, Mihailo Vukmirović, Blagoje Babić, Vesna Miranović, Andrej Škraba

“…Emphasis is placed on describing the system architecture and its key components, as well as the software methodologies used for signal decoding on the receiver side, where several algorithms are implemented using open-source, platform-independent technologies, such as JavaScript, HTML, and CSS. …”
Get full text

GAB-YOLO: a lightweight deep learning model for real-time detection of abnormal behaviors in juvenile greater amberjack fish by Mingxin Liu, Mingxin Liu, Chun Zhang, Cong Lin, Cong Lin

“…Meanwhile, existing automated detection algorithms often struggle with a trade-off between detection accuracy and model size. …”
Get full text

Integration of graph neural networks and transcriptomics analysis identify key pathways and gene signature for immunotherapy response and prognosis of skin melanoma by Maodong Ye, Shuai Ren, Huanjuan Luo, Xiumin Wu, Hongwei Lian, Xiangna Cai, Yingchang Ji

“…Graph neural networks (GNNs), alongside other deep learning algorithms and bioinformatics approaches, have demonstrated substantial promise in advancing cancer diagnosis and treatment strategies. …”
Get full text

Predicting outcomes of expectant and medical management in early pregnancy miscarriage using machine learning to develop and validate multivariable clinical prediction models by Sughashini Murugesu, Kristofer Linton-Reid, Emily Braun, Jennifer Barcroft, Nina Cooper, Margaret Pikovsky, Alex Novak, Nina Parker, Catriona Stalder, Maya Al-Memar, Srdjan Saso, Eric O. Aboagye, Tom Bourne

“…A combination of eight linear, Bayesian, neural-net and tree-based machine learning algorithms were applied to ten different feature sets. …”
Get full text

Nitrogen content estimation of apple trees based on simulated satellite remote sensing data by Meixuan Li, Xicun Zhu, Xicun Zhu, Xinyang Yu, Cheng Li, Dongyun Xu, Ling Wang, Dong Lv, Yuyang Ma

“…Support Vector Machine (SVM) and Backpropagation Neural Network (BPNN) algorithms were used to construct and screen the optimal models for apple tree nitrogen content estimation.ResultsResults showed that visible light, red edge, near-infrared, and yellow edge bands were sensitive bands for estimating apple tree nitrogen content. …”
Get full text

Multimodal AI for Home Wound Patient Referral Decisions From Images With Specialist Annotations by Reza Saadati Fard, Emmanuel Agu, Palawat Busaranuvong, Deepak Kumar, Shefalika Gautam, Bengisu Tulu, Diane Strong

“…Additionally, to interpret DM-WAT&#x2019;s recommendations, the Score-CAM and Captum interpretation algorithms provided insights into the specific parts of the image and text inputs that the model focused on during decision-making.…”
Get full text

Integrating transcriptomics and hybrid machine learning enables high-accuracy diagnostic modeling for nasopharyngeal carcinoma by Hehe Wang, Junge Zhang, Peng Cheng, Lujie Yu, Chunlin Li, Yaowen Wang

“…Differential expression analysis identified 293 differentially expressed genes (DEGs). Twelve ML algorithms (including Stepglm, glmBoost, and RF) were systematically combined into 113 distinct models to classify NPC versus normal tissues. …”
Get full text

Adverse drug reaction assessment of pembrolizumab in cervical cancer treatment: a real-world pharmacovigilance study using the FAERS database by Huiping Zhang, Zhuo Zhou, Juan Wang, Shan Wang, Jie Ren, Ming Zhang, Mingyi Yang

“…Disproportionality analyses were performed using multiple algorithms, including the reporting odds ratio (ROR), proportional reporting ratio (PRR), Bayesian confidence propagation neural network (BCPNN), and multi-item gamma Poisson shrinker (MGPS). …”
Get full text

Tissue Is the Issue: A Systematic Review of Methods for the Determination of Infarct Volume in Acute Ischaemic Stroke by Fatimah Al Ahmed, Patrick Kennelly, Darragh Herlihy, Jorin Bejleri, David J. Williams, John J. Thornton, Shona Pfeiffer

“…However, differences in operating algorithms and lack of standardisation of image acquisition parameters, quality, and format may impact performance and reproducibility. …”
Get full text

Integrating transcriptomic and metabolomic analyses to characterize the potential function of SLC1A5 in thyroid cancer by Fengling Shan, Lan Wang, Xinyu Lu, Meihong Zhou, Zi Wang, Jingjing Lou, Xingdang Liu

“…In addition, we explored for the connection of SLC1A5 with the tumor microenvironment using algorithms like ESTIMATE and CIBERSORT. Results High SLC1A5 expression in THCA is related with a poor prognosis and advanced clinical stage. …”
Get full text

Machine learning approaches for predicting feed intake in Australian Merino, Corriedale, and Dohne Merino sheep by Fernando Amarilho-Silveira, Ignacio De Barbieri, Elly A. Navajas, Jaime Araujo Cobuci, Gabriel Ciappesoni

“…The dataset was randomly partitioned into two subsets: one for training (80%) the algorithms and the other for direct validation (20%). …”
Get full text