publications

2024

1. Effect of machine learning models on clinician prediction of postoperative complications: the Perioperative ORACLE randomised clinical trial

   Bradley A. Fritz , Christopher R. King , Mohamed Abdelhack, and 16 more authors

   British Journal of Anaesthesia, 2024
2. Examining the Role of Neuroticism Polygenic Risk in Late Life Cognitive Change: A UK Biobank Study

   Niki Akbarian , Mahbod Ebrahimi , Fernanda C. Dos Santos , and 8 more authors

   Behavioral Sciences, 2024

   Abs

   Cognitive decline is a public health concern affecting about 50 million individuals worldwide. Neuroticism, defined as the trait disposition to experience intense and frequent negative emotions, has been associated with an increased risk of late-life cognitive decline. However, the underlying biological mechanisms of this association remain unknown. This study investigated the relationship between genetic predisposition to neuroticism, computed by polygenic risk score (PRS), and performance in cognitive domains of reasoning, processing speed, visual attention, and memory in individuals over age 60. The sample consisted of UK Biobank participants with genetic and cognitive data available (N = 10,737, 4686 females; mean age = 63.4 ± 2.71). The cognitive domains were assessed at baseline for all participants and seven years later for a subset (N = 645, 262 females; mean age = 62.9 ± 2.44). Neuroticism PRS was not associated cross-sectionally with cognitive measures (p > 0.05). However, the trajectory of change for processing speed (β = 0.020; 95% CI = [0.006, 0.035], adjusted p = 0.0148), visual attention (β = −0.077; 95% CI = [−0.0985, −0.0553], adjusted p = 1.412 × 10−11), and memory (β = −0.033; 95% CI = [−0.0535, −0.0131], adjusted p = 0.005) was significantly associated with neuroticism PRS. Specifically, a higher genetic predisposition to neuroticism was associated with less decline in these cognitive domains. This trend persisted after sensitivity analysis using complete cases, although it only remained nominally significant for visual attention.

3. Open Access

   Identifying Psychosocial and Ecological Determinants of Enthusiasm In Youth: Integrative Cross-Sectional Analysis Using Machine Learning

   Roberta M Dolling-Boreham , Akshay Mohan , Mohamed Abdelhack, and 4 more authors

   JMIR Public Health Surveill, Sep 2024
4. Effect of machine learning models on clinician prediction of postoperative complications: the Perioperative ORACLE randomised clinical trial

   Bradley A. Fritz , Christopher R. King , Mohamed Abdelhack, and 16 more authors

   British Journal of Anaesthesia, Sep 2024

   HTML
5. Open Access

   Social Vulnerability and Surgery Outcomes: A Cross-sectional Analysis

   Mohamed Abdelhack, Sandhya Tripathi , Yixin Chen , and 2 more authors

   BMC Public Health, Sep 2024

   HTML
6. Open Access

   Ten simple rules for pushing boundaries of inclusion at academic events

   Siobhan Mackenzie Hall , Daniel Kochin , Carmel Carne , and 11 more authors

   PLOS Computational Biology, Sep 2024
7. Open Access

   Multi-view representation learning for tabular data integration using inter-feature relationships

   Sandhya Tripathi , Bradley A. Fritz , Mohamed Abdelhack, and 3 more authors

   Journal of Biomedical Informatics, Sep 2024

   Abs

   Objective: An applied problem facing all areas of data science is harmonizing data sources. Joining data from multiple origins with unmapped and only partially overlapping features is a prerequisite to developing and testing robust, generalizable algorithms, especially in healthcare. This integrating is usually resolved using meta-data such as feature names, which may be unavailable or ambiguous. Our goal is to design methods that create a mapping between structured tabular datasets derived from electronic health records independent of meta-data. Methods: We evaluate methods in the challenging case of numeric features without reliable and distinctive univariate summaries, such as nearly Gaussian and binary features. We assume that a small set of features are a priori mapped between two datasets, which share unknown identical features and possibly many unrelated features. Inter-feature relationships are the main source of identification which we expect. We compare the performance of contrastive learning methods for feature representations, novel partial auto-encoders, mutual-information graph optimizers, and simple statistical baselines on simulated data, public datasets, the MIMIC-III medical-record changeover, and perioperative records from before and after a medical-record system change. Performance was evaluated using both mapping of identical features and reconstruction accuracy of examples in the format of the other dataset. Results: Contrastive learning-based methods overall performed the best, often substantially beating the literature baseline in matching and reconstruction, especially in the more challenging real data experiments. Partial auto-encoder methods showed on-par matching with contrastive methods in all synthetic and some real datasets, along with good reconstruction. However, the statistical method we created performed reasonably well in many cases, with much less dependence on hyperparameter tuning. When validating feature match output in the EHR dataset we found that some mistakes were actually a surrogate or related feature as reviewed by two subject matter experts. Conclusion: In simulation studies and real-world examples, we find that inter-feature relationships are effective at identifying matching or closely related features across tabular datasets when meta-data is not available. Decoder architectures are also reasonably effective at imputing features without an exact match.

2023

1. Open Access

   Opposing brain signatures of sleep in task-based and resting-state conditions

   Mohamed Abdelhack, Peter Zhukovsky , Milos Milic , and 6 more authors

   Nature Communications, Sep 2023

   HTML
2. Open Access

   Reconstructing visual illusory experiences from human brain activity

   Fan L. Cheng , Tomoyasu Horikawa , Kei Majima , and 5 more authors

   Science Advances, Sep 2023

   Abs HTML

   Visual illusions provide valuable insights into the brain’s interpretation of the world given sensory inputs. However, the precise manner in which brain activity translates into illusory experiences remains largely unknown. Here, we leverage a brain decoding technique combined with deep neural network (DNN) representations to reconstruct illusory percepts as images from brain activity. The reconstruction model was trained on natural images to establish a link between brain activity and perceptual features and then tested on two types of illusions: illusory lines and neon color spreading. Reconstructions revealed lines and colors consistent with illusory experiences, which varied across the source visual cortical areas. This framework offers a way to materialize subjective experiences, shedding light on the brain’s internal representations of the world. Images generated from brain activity mirror illusory experiences, revealing neural representations behind subjective perception.

3. An Intraoperative Telemedicine Program to Improve Perioperative Quality Measures: The ACTFAST-3 Randomized Clinical Trial

   Christopher R King , Stephen Gregory , Bradley A Fritz , and 8 more authors

   JAMA Network Open, Sep 2023
4. Abstract

   A Convolutional Neural Network Model classifies Beat-to-Beat Arterial Pressure Time-Series: Sex Stratification and Cardiovascular Risk Prediction

   Nour Mounira Bakkar , Abdalrhman Mostafa , Mohamed Abdelhack, and 1 more author

   Sep 2023

   HTML
5. Abstract

   Shared Neural Representations Between Sleep and Depression and Their Effect on Visual Perception

   Mohamed Abdelhack, Peter Zhukovsky , Milos Milic , and 2 more authors

   Biological Psychiatry, Sep 2023

   HTML
6. Open Access

   A Modulation Layer to Increase Neural Network Robustness Against Data Quality Issues

   Mohamed Abdelhack, Jiaming Zhang , Sandhya Tripathi , and 5 more authors

   Transactions on Machine Learning Research, Sep 2023

   HTML Code

2022

1. Sex-specific associations between lifetime diagnosis of bipolar disorder and cardiovascular disease: A cross-sectional analysis of 257,673 participants from the UK Biobank

   Abigail Ortiz , Marcos Sanches , Mohamed Abdelhack, and 6 more authors

   Journal of Affective Disorders, Sep 2022

   Bib HTML

   @article{ORTIZ2022,
     title = {Sex-specific associations between lifetime diagnosis of bipolar disorder and cardiovascular disease: A cross-sectional analysis of 257,673 participants from the UK Biobank},
     journal = {Journal of Affective Disorders},
     year = {2022},
     issn = {0165-0327},
     url = {https://www.sciencedirect.com/science/article/pii/S0165032722010539},
     author = {Ortiz, Abigail and Sanches, Marcos and Abdelhack, Mohamed and Schwaiger, Tyler R. and Wainberg, Michael and Tripathy, Shreejoy J. and Felsky, Daniel and Mulsant, Benoit H. and Fiedorowicz, Jess G.},
     keywords = {Mood disorders, Cardiovascular, Bipolar disorder, Morbidity, Sex, Coronary artery disease}
   }

2. Open Access

   An in vivo assay to study locomotion in Caenorhabditis elegans

   Mohamed Abdelhack

   MethodsX, Sep 2022

   HTML

2021

1. Machine Learning–Based Predictive Modeling of Anxiety and Depressive Symptoms During 8 Months of the COVID-19 Global Pandemic: Repeated Cross-sectional Survey Study

   Katrina Hueniken , Nibene Habib Somé , Mohamed Abdelhack, and 7 more authors

   JMIR mental health, Sep 2021

   HTML

2020

1. Update

   Update to ‘Deep-learning model for predicting 30-day postoperative mortality’(Br J Anaesth 2019; 123: 688–95)

   Bradley A Fritz , Mohamed Abdelhack, Christopher R King , and 2 more authors

   BJA: British Journal of Anaesthesia, Sep 2020

   HTML
2. Toolkit

   An Open-source Tool for Hyperspectral Image Augmentation in Tensorflow

   Mohamed Abdelhack

   arXiv preprint arXiv:2003.13502, Sep 2020

   HTML Code

2019

1. Preprint

   Conflicting Bottom-up and Top-down Signals during Misrecognition of Visual Objects

   Mohamed Abdelhack, and Yukiyasu Kamitani

   bioRxiv, Sep 2019

   HTML

2018

1. Open Access

   Sharpening of hierarchical visual feature representations of blurred images

   Mohamed Abdelhack, and Yukiyasu Kamitani

   Eneuro, Sep 2018

   HTML Code
2. Regional differences in Purkinje cell morphology in the cerebellar vermis of male mice

   Hermina Nedelescu , Mohamed Abdelhack, and Arwel T Pritchard

   Journal of neuroscience research, Sep 2018

   HTML Code

2017

1. Abstract

   Top-down neural processing that supplements missing image features revealed by brain decoding with deep neural network representation

   Mohamed Abdelhack, and Yukiyasu Kamitani

   Journal of Vision, Sep 2017

   HTML

2013

1. Open Access

   Comparative morphology of dendritic arbors in populations of Purkinje cells in mouse sulcus and apex

   Hermina Nedelescu , and Mohamed Abdelhack

   Neural Plasticity, Sep 2013

   Bib HTML Code

   @article{nedelescu2013comparative,
     title = {Comparative morphology of dendritic arbors in populations of Purkinje cells in mouse sulcus and apex},
     author = {Nedelescu, Hermina and Abdelhack, Mohamed},
     journal = {Neural Plasticity},
     volume = {2013},
     year = {2013},
     publisher = {Hindawi},
   }