Article
Automation & Control Systems
Mingxuan Liang, Kai Zhou
Summary: A probabilistic fault diagnosis framework using a Gaussian process classifier was developed to account for uncertainties in prediction, showcasing unique capability and outperforming other machine learning models in accuracy and robustness in systematic case studies. Sensor fusion with spatial vibration measurements further enhances fault diagnosis performance. Leveraging the probabilistic feature facilitates future research on extended fault diagnosis using limited fault labels.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Urology & Nephrology
Olivier Cussenot, Raphaele Renard-Penna, Sarah Montagne, Valerie Ondet, Antoine Pilon, Jerome Guechot, Eva Comperat, Freddie Hamdy, Alastair Lamb, Geraldine Cancel-Tassin
Summary: This study evaluates different scenarios for the management of early diagnosis of cancer (PCa) in men at high genetic risk using blood and urinary molecular biomarkers in combination with clinical information alongside multiparametric magnetic resonance imaging (mpMRI). The results suggest that screening based on mpMRI is more effective for detecting clinically significant PCa lesions compared to blood markers, and it is recommended to consider a baseline mpMRI for men at high genetic risk starting from the age of 40.
Article
Clinical Neurology
Minji Bang, Yae Won Park, Jihwan Eom, Sung Soo Ahn, Jinna Kim, Seung-Koo Lee, Sang-Hyuk Lee
Summary: The study found that radiomic features can help differentiate patients with PDA from healthy controls, aiding in the accurate diagnosis of PDA. The results suggest that radiomic features from fear-circuit structures can reveal microstructural aberrations underlying the pathogenesis of PDA.
JOURNAL OF AFFECTIVE DISORDERS
(2022)
Article
Computer Science, Information Systems
Dang Nguyen, Sunil Gupta, Santu Rana, Alistair Shilton, Svetha Venkatesh
Summary: In real-world applications, fairness of machine learning classifiers is often more crucial than accuracy. Post-processing methods are effective tools for improving fairness of black-box ML classifiers, but many require true labels for training. This paper proposes a novel post-processing method based on Gaussian process that adjusts labels to maximize fairness while maintaining accuracy.
INFORMATION SCIENCES
(2021)
Article
Oncology
M. Abdul-Latif, H. Tharmalingam, Y. Tsang, P. J. Hoskin
Summary: Cervical Cancer is the fourth most common cancer in women worldwide, and there is a need for predictive and prognostic biomarkers to identify populations at risk of poorer treatment response and survival. Magnetic resonance imaging (MRI) is routinely used in cervical cancer and has the potential to provide biomarkers. However, most studies focus on single MRI techniques, highlighting the need for combined approaches to better characterize tumors and identify biomarkers.
Article
Metallurgy & Metallurgical Engineering
Xian-ling Li, Jian-feng Zhang, Chun-hui Zhao, Jin-liang Ding, You-xian Sun
Summary: With the increasing complexity of industrial processes, the nonlinearity of high-dimensional industrial data poses challenges for fault diagnosis. This study proposes a sparse Gaussian feature extractor (SGFE) that learns meaningful features related to fault categories by projecting the raw data into a feature space with the fault label dimension.
JOURNAL OF CENTRAL SOUTH UNIVERSITY
(2022)
Review
Cardiac & Cardiovascular Systems
Kerrick Hesse, Mohammed Y. Khanji, Nay Aung, Ghaith Sharaf Dabbagh, Steffen E. Petersen, C. Anwar A. Chahal
Summary: Cardiac disease can affect the heart in a non-uniform manner, and cardiovascular magnetic resonance (CMR) imaging can provide detailed information on structural and functional heterogeneity that is not captured by standard global measures. CMR-derived heterogeneity biomarkers have the potential to facilitate early diagnosis, better risk stratification, and more comprehensive prediction of treatment response. However, there are challenges in standardizing CMR imaging protocols and testing radiomic features in small patient samples. A proposed roadmap includes defining normal reference ranges, statistical modeling against diagnosis and outcomes in large studies, and comprehensive validations.
EUROPEAN HEART JOURNAL-CARDIOVASCULAR IMAGING
(2023)
Article
Cardiac & Cardiovascular Systems
Hannah N. Marmor, Michael N. Kammer, Stephen A. Deppen, Maren Shipe, Valerie F. Welty, Khushbu Patel, Caroline Godfrey, Ehab Billatos, James G. Herman, David O. Wilson, Amanda K. Kussrow, Darryl J. Bornhop, Fabien Maldonado, Heidi Chen, Eric L. Grogan
Summary: The study aimed to compare different methods in diagnosing indeterminate pulmonary nodules, and the results showed that the integrated biomarker model had higher diagnostic accuracy.
JOURNAL OF THORACIC AND CARDIOVASCULAR SURGERY
(2023)
Article
Health Care Sciences & Services
Sheng Li, Yukang Que, Rui Yang, Peng He, Shenglin Xu, Yong Hu
Summary: This study aimed to develop novel and efficient predictive models for the diagnosis of osteosarcoma and to identify potential targets for exploring osteosarcoma markers. By screening differentially expressed genes and constructing diagnostic and prognostic models, this study provides new insights for the early diagnosis and treatment of osteosarcoma.
JOURNAL OF PERSONALIZED MEDICINE
(2023)
Article
Engineering, Multidisciplinary
Zhenyu Deng, Chenggen Quan, Fajie Duan
Summary: This paper proposes a robust fault diagnosis approach for reliable classification and high accuracy through feature importance distribution and overall process optimization. Experimental results demonstrate that the method outperforms traditional approaches in different scenarios with significantly higher accuracy levels.
Article
Chemistry, Multidisciplinary
Aikaterini S. Karampasi, Antonis D. Savva, Vasileios Ch. Korfiatis, Ioannis Kakkos, George K. Matsopoulos
Summary: Effective detection of autism spectrum disorder (ASD) is complex, machine learning methods are helpful but face challenges due to scarce biomarkers and variability in imported attributes. This study focuses on identifying efficacious biomarkers for ASD classification using functional magnetic resonance imaging data.
APPLIED SCIENCES-BASEL
(2021)
Article
Mathematics
Ying Chen, Qi Da, Weizhang Liang, Peng Xiao, Bing Dai, Guoyan Zhao
Summary: The evaluation of rockburst damage potential is crucial for rockburst risk management and personnel safety. This study proposes a bagged ensemble of Gaussian process classifiers to assess rockburst damage potential with an imbalanced dataset, and improves the model performance by integrating data preprocessing and under-sampling technique. The empirical results demonstrate the feasibility of this method.
Article
Radiology, Nuclear Medicine & Medical Imaging
Yuvnik Trada, Paul Keall, Michael Jameson, Daniel Moses, Peter Lin, Phillip Chlap, Lois Holloway, Myo Min, Dion Forstner, Allan Fowler, Mark T. Lee
Summary: Combining DWI MRI and FDG-PET/CT for measuring tumor changes during radiotherapy can predict treatment response in mucosal head and neck carcinoma. Evaluating ADC mean and MTV together improves the accuracy of predicting local recurrence.
EUROPEAN RADIOLOGY
(2023)
Article
Medicine, General & Internal
Sathyabaarathi Ravichandran, Ushashi Banerjee, D. R. Gayathri Devi, Rooparani Kandukuru, Chandrani Thakur, Dipshikha Chakravortty, Kithiganahalli Narayanaswamy Balaji, Amit Singh, Nagasuma Chandra
Summary: By analyzing blood transcriptomes and human protein interaction networks, we discovered a 10-gene panel with high predictive performance to distinguish viral from bacterial infections. We developed a new standalone patient-wise score with high diagnostic accuracy, which was validated in multiple datasets from different countries and a new cohort from South India.
Article
Medicine, Research & Experimental
Shan Huang, Andreas Blutke, Annette Feuchtinger, Uwe Klemm, Robby Zachariah Tom, Susanna M. Hofmann, Andre C. Stiel, Vasilis Ntziachristos
Summary: The study found that multispectral optoacoustic tomography (MSOT) can non-invasively visualize lipids in laboratory mice, particularly for the assessment and monitoring of fatty liver disease. By monitoring the clearance kinetics of indocyanine green in the liver, MSOT can also serve as a biomarker for evaluating the severity of hepatic steatosis.
EMBO MOLECULAR MEDICINE
(2021)
Article
Psychology, Clinical
Nathalie E. Holz, Dorothea L. Floris, Alberto Llera, Pascal M. Aggensteiner, Seyed Mostafa Kia, Thomas Wolfers, Sarah Baumeister, Boris Boettinger, Jeffrey C. Glennon, Pieter J. Hoekstra, Andrea Dietrich, Melanie C. Saam, Ulrike M. E. Schulze, David J. Lythgoe, Steve C. R. Williams, Paramala Santosh, Mireia Rosa-Justicia, Nuria Bargallo, Josefina Castro-Fornieles, Celso Arango, Maria J. Penzol, Susanne Walitza, Andreas Meyer-Lindenberg, Marcel Zwiers, Barbara Franke, Jan Buitelaar, Jilly Naaijen, Daniel Brandeis, Christian Beckmann, Tobias Banaschewski, Andre F. Marquand
Summary: This study aimed to reveal the neurobiological characteristics of disruptive behavior disorders (DBD) by integrating individual deviation patterns from multiple imaging modalities. The results showed that DBD patients exhibited increased age-related deviations in the amygdala, suggesting a possible maturational delay. Furthermore, the study identified neural signatures associated with aggression, including the default mode network (DMN), striatum, and amygdala.
PSYCHOLOGICAL MEDICINE
(2023)
Article
Psychiatry
Dorothea L. Floris, Han Peng, Varun Warrier, Michael V. Lombardo, Charlotte M. Pretzsch, Clara Moreau, Alex Tsompanidis, Weikang Gong, Maarten Mennes, Alberto Llera, Daan van Rooij, Marianne Oldehinkel, Natalie J. Forde, Tony Charman, Julian Tillmann, Tobias Banaschewski, Carolin Moessnang, Sarah Durston, Rosemary J. Holt, Christine Ecker, Flavio Dell'Acqua, Eva Loth, Thomas Bourgeron, Declan G. M. Murphy, Andre F. Marquand, Meng-Chuan Lai, Jan K. Buitelaar, Simon Baron-Cohen, Christian F. Beckmann
Summary: Using deep learning on brain images, the authors found that both autistic males and females tend to have neuroanatomy more similar to males, as well as social cognitive features and gene expression patterns associated with male characteristics. These neurophenotypes provide important insights into the biological mechanisms underlying autism.
AMERICAN JOURNAL OF PSYCHIATRY
(2023)
Article
Clinical Neurology
Bernabe Bustos, Kimberley Billingsley, Cornelis Blauwendraat, J. Raphael Gibbs, Ziv Gan-Or, Dimitri Krainc, Andrew B. Singleton, Steven J. Lubbe
Summary: Bustos et al. conducted the first genome-wide meta-analysis of common short tandem repeats (STRs) in Parkinson's disease and identified four new independent risk factors. They found that STRs contribute to the heritability of Parkinson's disease and that STR-associated genes are enriched in Parkinson's disease-relevant tissues and pathways.
Article
Psychiatry
Vania Tavares, Evangelos Vassos, Andre Marquand, James Stone, Isabel Valli, Gareth J. Barker, Hugo Ferreira, Diana Prata
Summary: This study aimed to predict the transition to psychosis from an At Risk Mental State (ARMS) by using a combination of machine learning, structural magnetic resonance imaging (sMRI), genome-wide genotypes, and environmental risk factors as predictors. The results suggested that none of the modalities alone, namely neuroimaging, genetic data, or environmental data, could predict psychosis from an ARMS statistically better than chance, indicating the need to re-evaluate the value of sMRI data and genome-wide genotypes in predicting psychosis risk.
FRONTIERS IN PSYCHIATRY
(2023)
Review
Biochemistry & Molecular Biology
Samuel J. Westwood, Valeria Parlatini, Katya Rubia, Samuele Cortese, Edmund J. S. Sonuga-Barke, European ADHD Guidelines Grp EAGG
Summary: This meta-analysis examined the effects of computerized cognitive training (CCT) on clinical, neuropsychological, and academic outcomes in individuals with attention-deficit/hyperactivity disorder (ADHD). The results showed that CCT had no significant impact on overall symptoms or hyperactivity/impulsivity symptoms of ADHD, but had a small improvement in inattention symptoms. CCT improved working memory, but did not affect other neuropsychological or academic outcomes.
MOLECULAR PSYCHIATRY
(2023)
Article
Clinical Neurology
Pierre-Emmanuel Sugier, Elise A. Lucotte, Cloe Domenighetti, Matthew H. Law, Mark M. Iles, Kevin Brown, Christopher Amos, James D. McKay, Rayjean J. Hung, Mojgan Karimi, Delphine Bacq-Daian, Anne Boland-Auge, Robert Olaso, Jean-francois Deleuze, Fabienne Lesueur, Evgenia Ostroumova, Ausrele Kesminiene, Florent de Vathaire, Pascal Guenel, Ashwin Ashok Kumar Sreelatha, Claudia Schulte, Sandeep Grover, Patrick May, Dheeraj R. Bobbili, Milena Radivojkov-Blagojevic, Peter Lichtner, Andrew B. Singleton, Dena G. Hernandez, Connor Edsall, George D. Mellick, Alexander Zimprich, Walter Pirker, Ekaterina Rogaeva, Anthony E. Lang, Sulev Koks, Pille Taba, Suzanne Lesage, Alexis Brice, Jean-Christophe Corvol, Marie-Christine Chartier-Harlin, Eugenie Mutez, Kathrin Brockmann, Angela B. Deutschlaender, Georges M. Hadjigeorgiou, Efthimios Dardiotis, Leonidas Stefanis, Athina Maria Simitsi, Enza Maria Valente, Simona Petrucci, Letizia Straniero, Anna Zecchinelli, Gianni Pezzoli, Laura Brighina, Carlo Ferrarese, Grazia Annesi, Andrea Quattrone, Monica Gagliardi, Hirotaka Matsuo, Akiyoshi Nakayama, Nobutaka Hattori, Kenya Nishioka, Sun Ju Chung, Yun Joong Kim, Pierre Kolber, Bart P. C. van de Warrenburg, Bastiaan R. Bloem, Jan Aasly, Mathias Toft, Lasse Pihlstrom, Leonor Correia Guedes, Joaquim J. Ferreira, Soraya Bardien, Jonathan Carr, Eduardo Tolosa, Mario Ezquerra, Pau Pastor, Monica Diez-Fairen, Karin Wirdefeldt, Nancy Pedersen, Caroline Ran, Andrea C. Belin, Andreas Puschmann, Emil Ygland Roedstroem, Carl E. Clarke, Karen E. Morrison, Manuela Tan, Dimitri Krainc, Lena F. Burbulla, Matt J. Farrer, Rejko Kruger, Thomas Gasser, Manu Sharma, Therese Truong, Alexis Elbaz
Summary: By using genome-wide association studies, this study found that Parkinson's disease (PD) is genetically correlated with melanoma and prostate cancer, while it is inversely correlated with ovarian cancer. These findings suggest that pleiotropic genes contribute to the association between PD and specific cancers.
MOVEMENT DISORDERS
(2023)
Article
Clinical Neurology
Serena Verdi, Seyed Mostafa Kia, Keir X. X. Yong, Duygu Tosun, Jonathan M. Schott, Andre F. Marquand, James H. Cole
Summary: Using neuroanatomical normative modeling, we found significant individual differences and outliers in cortical thickness in AD patients, MCI patients, and controls. These differences were associated with cognitive function, β-amyloid, phosphorylated-tau, and ApoE genotype. Cortical thickness heterogeneity was also predictive of conversion from MCI to AD.
Article
Biology
Saige Rutherford, Pieter Barkema, Ivy F. Tso, Chandra Sripada, Christian F. Beckmann, Henricus G. Ruhe, Andre F. Marquand, Chris Baker
Summary: In this study, we extended the normative model repository introduced in Rutherford et al., 2022a to include normative models for lifespan trajectories of structural surface area and brain functional connectivity. We used two resting-state network atlases (Yeo-17 and Smith-10) and an updated online platform to transfer these models to new data sources. Through benchmarking tasks, we demonstrated the value of normative modeling features compared to raw data features, especially in group difference testing and classification tasks. These accessible resources are intended to promote the broader adoption of normative modeling in the neuroimaging community.
Article
Psychiatry
Steve Lukito, Owen G. O'Daly, David J. Lythgoe, John Hodsoll, Stefanos Maltezos, Mark Pitts, Emily Simonoff, Katya Rubia
Summary: Autism spectrum disorder (ASD) often co-occurs with attention-deficit/hyperactivity disorder (ADHD) and people with these conditions have frontostriatal functional atypicality during motor inhibition. We compared the neural and neurocognitive correlates of motor inhibition and performance monitoring in young adult males with pure and combined presentations with age-and sex-matched typically developing controls, to explore shared or disorder-specific atypicality. Only young adult males with ASD + ADHD had neurofunctional atypicality in brain regions associated with performance monitoring, while inhibition difficulties on go/no-go task performance was shared with ADHD.
TRANSLATIONAL PSYCHIATRY
(2023)
Article
Neurosciences
Hongxu Pan, Zhenhua Liu, Jinghong Ma, Yuanyuan Li, Yuwen Zhao, Xiaoxia Zhou, Yaqin Xiang, Yige Wang, Xun Zhou, Runcheng He, Yali Xie, Qiao Zhou, Kai Yuan, Qian Xu, Qiying Sun, Junling Wang, Xinxiang Yan, Hainan Zhang, Chunyu Wang, Lifang Lei, Weiguo Liu, Xuejing Wang, Xuebing Ding, Tao Wang, Zheng Xue, Zhentao Zhang, Ling Chen, Qing Wang, Yonghong Liu, Jiayu Tang, Xuewei Zhang, Shifang Peng, Chaodong Wang, Jianqing Ding, Chunfeng Liu, Lijuan Wang, Haibo Chen, Lu Shen, Hong Jiang, Xinyin Wu, Hongzhuan Tan, Dan Luo, Shuiyuan Xiao, Xiang Chen, Jieqiong Tan, Zhengmao Hu, Chao Chen, Kun Xia, Zhuohua Zhang, Jia Nee Foo, Cornelis Blauwendraat, Mike Nalls, Andrew Singleton, Jun Liu, Piu Chan, Houfeng Zheng, Jinchen Li, Jifeng Guo, Jian Yang, Beisha Tang
Summary: Through GWAS and WGS, genetic variants associated with Parkinson's disease were identified in the Chinese population, revealing both genetic homogeneity and heterogeneity of the disease across different ethnic groups. These findings highlight the importance of WGS in improving our understanding of the genetic architecture of Parkinson's disease.
NPJ PARKINSONS DISEASE
(2023)
Article
Neurosciences
Sergio Kaiser, Luqing Zhang, Brit Mollenhauer, Jaison Jacob, Simonne Longerich, Jorge Del-Aguila, Jacob Marcus, Neha Raghavan, David Stone, Olumide Fagboyegun, Douglas Galasko, Mohammed Dakna, Bilada Bilican, Mary Dovlatyan, Anna Kostikova, Jingyao Li, Brant Peterson, Michael Rotte, Vinicius Sanz, Tatiana Foroud, Samantha J. Hutten, Mark Frasier, Hirotaka Iwaki, Andrew Singleton, Ken Marek, Karen Crawford, Fiona Elwood, Mirko Messa, Pablo Serrano-Fernandez
Summary: This study comprehensively analyzed the cerebrospinal fluid proteomes of Parkinson's disease patients, identifying potential causal proteins and revealing proteome differences between different subgroups of patients. The findings provide insights into the pathogenesis and clinical heterogeneity of Parkinson's disease, and have implications for the development of personalized medicine and therapeutic targets.
NPJ PARKINSONS DISEASE
(2023)
Article
Neurosciences
Kalpana M. Merchant, Tanya Simuni, Janel Fedler, Chelsea Caspell-Garcia, Michael Brumm, Kelly N. H. Nudelman, Elizabeth Tengstrandt, Frank Hsieh, Roy N. Alcalay, Christopher Coffey, Lana Chahine, Tatiana Foroud, Andrew Singleton, Daniel Weintraub, Samantha Hutten, Todd Sherer, Brit Mollenhauer, Andrew Siderowf, Caroline Tanner, Ken Marek
Summary: We quantified concentrations of three isoforms of BMP in different cohorts of Parkinson's disease patients and found that LRRK2 and GBA1 gene mutations were associated with elevated BMP levels. However, BMP is not a prognostic or disease progression biomarker.
NPJ PARKINSONS DISEASE
(2023)
Review
Allergy
Shona Cameron, Ali Donnelly, Conor Broderick, Tomoki Arichi, Ullrich Bartsch, Paola Dazzan, Jesper Elbeling, Emma Godfrey, Paul Gringras, Lauren C. Heathcote, Desaline Joseph, Tobias C. Wood, Carmine Pariante, Katya Rubia, Carsten Flohr
Summary: Atopic dermatitis is a chronic, pruritic and inflammatory skin condition that is associated with various comorbidities such as airway disease, food allergies, atopic eye disease, and autoimmune conditions. It can significantly impact the quality of life for both patients and their families, causing sleep disturbance and mental health problems. Recent findings suggest that inflammation and sleep disruption play a key role in the development and exacerbation of AD.
Review
Biochemistry & Molecular Biology
Valeria Parlatini, Takashi Itahashi, Yeji Lee, Siwei Liu, Thuan T. Nguyen, Yuta Y. Aoki, Stephanie J. Forkel, Marco Catani, Katya Rubia, Juan H. Zhou, Declan G. Murphy, Samuele Cortese
Summary: This study conducted a systematic review and meta-analysis of diffusion weighted imaging (DWI) studies to investigate abnormal anatomical brain connections in ADHD. The findings show white matter alterations in projection, commissural and association pathways, especially reduced fractional anisotropy (FA), which are associated with symptom severity and cognitive deficits. Despite some methodological limitations, these findings have important implications for understanding the brain effects of ADHD and guiding clinical interventions.
MOLECULAR PSYCHIATRY
(2023)
Review
Biochemistry & Molecular Biology
Samuel J. Westwood, Aldo Alberto Conti, Wanjie Tang, Shuang Xue, Samuele Cortese, Katya Rubia
Summary: This systematic review and meta-analysis examined the effects of external trigeminal nerve stimulation (eTNS) on clinical and cognitive outcomes in neurological and psychiatric disorders. A total of 55 peer-reviewed articles, based on 48 trials, were included in the analysis. The results showed that eTNS combined with anti-migraine medication significantly improved migraine pain intensity, quality of life, and dimensional measures of depression across various disorders. More well-designed and adequately powered randomized controlled trials are needed to further validate these findings and determine optimal dosage guidance for eTNS.
MOLECULAR PSYCHIATRY
(2023)