4.6 Review

Exploring alternative approaches to precision medicine through genomics and artificial intelligence - a systematic review

Related references

Note: Only part of the references are listed.
Article Social Sciences, Interdisciplinary

PRISMA2020: An R package and Shiny app for producing PRISMA 2020-compliant flow diagrams, with interactivity for optimised digital transparency and Open Synthesis

Neal R. Haddaway et al.

Summary: We have developed a user-friendly tool for producing PRISMA 2020-compliant flow diagrams for users with coding experience and, importantly, for users without prior experience in coding by making use of Shiny. This free-to-use tool will make it easier to produce clear and PRISMA 2020-compliant systematic review flow diagrams. Significantly, users can also produce interactive flow diagrams for the first time, allowing readers of their reviews to smoothly and swiftly explore and navigate to further details of the methods and results of a review.

CAMPBELL SYSTEMATIC REVIEWS (2022)

Article Biochemical Research Methods

spaCI: deciphering spatial cellular communications through adaptive graph model

Ziyang Tang et al.

Summary: Cell-cell communications are essential for biological signalling and play crucial roles in complex diseases. The development of single-cell spatial transcriptomics (SCST) technologies allows us to explore the spatial landscapes of cell communication. However, accurately inferring cellular communications from SCST data is challenging due to dropout events and noisy signals. In this study, we propose a novel adaptive graph model named spaCI, which integrates spatial locations and gene expression profiles to identify active ligand-receptor signalling axes between neighboring cells. By benchmarking with other methods, spaCI demonstrates superior performance on simulation data and real SCST datasets. Furthermore, spaCI can identify upstream transcriptional factors involved in the active ligand-receptor interactions. Applying spaCI to mouse cortex and non-small cell lung cancer datasets, we uncover hidden ligand-receptor interactions and reveal the importance of SMAD3 in regulating crosstalk between fibroblasts and tumors. Overall, spaCI addresses the challenges in interrogating SCST data to gain insights into cellular communications, enabling the discovery of disease mechanisms, effective biomarkers, and therapeutic targets.

BRIEFINGS IN BIOINFORMATICS (2022)

Article Radiology, Nuclear Medicine & Medical Imaging

Automatic semantic segmentation of kidney cysts in MR images of patients affected by autosomal-dominant polycystic kidney disease

Timothy L. Kline et al.

Summary: This study developed and validated a fully automated approach for semantic segmentation of renal cysts in MR images of patients with ADPKD. The automated method performed at the level of interobserver variability and showed comparable consistency with manual segmentation in terms of cyst volume.

ABDOMINAL RADIOLOGY (2021)

Article Computer Science, Artificial Intelligence

Finding reduced Raman spectroscopy fingerprint of skin samples for melanoma diagnosis through machine learning

Daniella Castro Araujo et al.

Summary: Early detection of cutaneous melanoma is crucial for successful treatment. This study introduces a machine learning approach using raw skin Raman spectra data to classify benign and malignant skin lesions with high efficiency. The research also demonstrates the effectiveness of a high-performance model using a miniaturized spectral range, paving the way for the development of a cheaper and dedicated Raman spectrometer for fast and accurate cancer diagnosis.

ARTIFICIAL INTELLIGENCE IN MEDICINE (2021)

Article Multidisciplinary Sciences

Treatment selection using prototyping in latent-space with application to depression treatment

Akiva Kleinerman et al.

Summary: This article introduces a novel deep learning-based treatment selection approach that strikes a balance between the fully personalized paradigm and sub-grouping paradigm in depression treatment. The approach shows promising results in effectively addressing complex issues in treating depression.

PLOS ONE (2021)

Article Multidisciplinary Sciences

A machine learning approach to identify distinct subgroups of veterans at risk for hospitalization or death using administrative and electronic health record data

Ravi B. Parikh et al.

Summary: Identifying individuals at risk for future hospitalization or death is a major priority of population health management strategies. This study used machine learning clustering methods and linked comorbidity-based, sociodemographic, and psychobehavioral data to identify subgroups of high-risk Veterans, showing distinct utilization and outcome patterns among different subgroups.

PLOS ONE (2021)

Article Chemistry, Analytical

A Deep Learning-Based Camera Approach for Vital Sign Monitoring Using Thermography Images for ICU Patients

Simon Lyra et al.

Summary: In this study, infrared thermography was used for camera-based skin temperature measurement, combined with low-cost hardware and advanced algorithms for real-time vital sign extraction. A clinical trial demonstrated good performance of the proposed method.

SENSORS (2021)

Article Multidisciplinary Sciences

Automated system for diagnosing endometrial cancer by adopting deep-learning technology in hysteroscopy

Yu Takahashi et al.

Summary: This study introduces an artificial-intelligence-based system for automatically detecting regions affected by endometrial cancer from hysteroscopic images. By employing machine-learning techniques and a continuity analysis method, along with combining three neural network models, the diagnostic accuracy increased from 80% to over 90%. This method shows promise in facilitating timely diagnosis of endometrial cancer in the future.

PLOS ONE (2021)

Article Multidisciplinary Sciences

Artificial intelligence and leukocyte epigenomics: Evaluation and prediction of late-onset Alzheimer's disease

Ray O. Bahado-Singh et al.

Summary: This study evaluated the utility of leucocyte epigenomic-biomarkers for Alzheimer's Disease detection and identified differentially methylated genes associated with AD. Artificial intelligence methodologies accurately predicted AD, demonstrating high accuracy and potential in disease detection.

PLOS ONE (2021)

Article Multidisciplinary Sciences

Comparison of machine-learning methodologies for accurate diagnosis of sepsis using microarray gene expression data

Dominik Schaack et al.

Summary: The study investigated the feasibility of molecular-level sample classification of sepsis through in silico meta-analysis of microarray gene expression data. Machine-learning-based solutions like decision tree, random forest, support vector machine, and deep-learning neural networks were compared for differential expression analysis, with the latter three demonstrating excellent diagnostic performance surpassing most other published solutions.

PLOS ONE (2021)

Article Multidisciplinary Sciences

Pneumonia detection in chest X-ray images using an ensemble of deep learning models

Rohit Kundu et al.

Summary: Pneumonia, a respiratory infection caused by bacteria or viruses, affects developing and underdeveloped nations more severely; early diagnosis is crucial, with chest X-ray imaging being the common method used.

PLOS ONE (2021)

Article Multidisciplinary Sciences

Predicting drug sensitivity of cancer cells based on DNA methylation levels

Sofia P. Miranda et al.

Summary: This study focused on predicting cytotoxic responses of eight anti-cancer drugs using DNA methylation profiles from 987 cell lines. Machine learning algorithms, including classification and regression methods, were used to evaluate predictive performance, with classification algorithms performing best with training on cell lines with extreme drug-response values and regression algorithms performing best with training on the full range of drug-response values. Patient responses could not be reliably predicted based on models derived from cell lines, except for correlations found with the Random Forests algorithm and Temozolomide responses for low-grade gliomas.

PLOS ONE (2021)

Article Multidisciplinary Sciences

Statistical methods versus machine learning techniques for donor-recipient matching in liver transplantation

David Guijo-Rubio et al.

Summary: This study investigated Donor-Recipient matching using the United Network for Organ Sharing database and found that the traditional statistical method LR outperformed multiple machine learning techniques and standard scores at the 5-year endpoint, suggesting limitations of machine learning methods in improving liver allocation performance.

PLOS ONE (2021)

Article Multidisciplinary Sciences

Reproducibility of automated habenula segmentation via deep learning in major depressive disorder and normal controls with 7 Tesla MRI

Sang-Heon Lim et al.

Summary: This study introduced an automated segmentation and volume estimation method for the habenula in 7 Tesla magnetic resonance imaging using a deep learning-based approach. The method demonstrated high precision and recall rates, as well as a strong dice similarity coefficient, indicating its potential usefulness in future psychiatric disease studies.

SCIENTIFIC REPORTS (2021)

Proceedings Paper Computer Science, Information Systems

Intelligent Chatbot for Prediction and Management of Stress

Tushar Sharma et al.

Summary: The Stress Management and Prediction application is an end user support and consultation project that uses neural network and machine learning techniques to train data and predict the patient's stress level, showing measures to take.

2021 11TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING, DATA SCIENCE & ENGINEERING (CONFLUENCE 2021) (2021)

Article Critical Care Medicine

Coagulation phenotypes in sepsis and effects of recombinant human thrombomodulin: an analysis of three multicentre observational studies

Daisuke Kudo et al.

Summary: We identified four sepsis phenotypes based on coagulation markers. The treatment effects of thrombomodulin varied across different sepsis phenotypes. This discovery will facilitate future trials of thrombomodulin targeting specific sepsis phenotypes with high FDP and D-dimer levels.

CRITICAL CARE (2021)

Review Clinical Neurology

Imaging-Based Algorithm for the Local Grading of Glioma

E. D. H. Gates et al.

AMERICAN JOURNAL OF NEURORADIOLOGY (2020)

Article Biology

Estimating individualized treatment regimes from crossover designs

Crystal T. Nguyen et al.

BIOMETRICS (2020)

Article Multidisciplinary Sciences

Unveiling new disease, pathway, and gene associations via multi-scale neural network

Thomas Gaudelet et al.

PLOS ONE (2020)

Article Multidisciplinary Sciences

Benchmarking machine learning models on multi-centre eICU critical care dataset

Seyedmostafa Sheikhalishahi et al.

PLOS ONE (2020)

Article Psychology, Clinical

Personalized prediction of antidepressant v. placebo response: evidence from the EMBARC study

Christian A. Webb et al.

PSYCHOLOGICAL MEDICINE (2019)

Article Multidisciplinary Sciences

Drug sensitivity prediction with high-dimensional mixture regression

Qianyun Li et al.

PLOS ONE (2019)

Article Multidisciplinary Sciences

Real-time gastric polyp detection using convolutional neural networks

Xu Zhang et al.

PLOS ONE (2019)

Article Urology & Nephrology

Automatic Measurement of Kidney and Liver Volumes from MR Images of Patients Affected by Autosomal Dominant Polycystic Kidney Disease

Maatje D. A. van Gastel et al.

JOURNAL OF THE AMERICAN SOCIETY OF NEPHROLOGY (2019)

Article Multidisciplinary Sciences

In silico analysis of the V66M variant of human BDNF in psychiatric disorders: An approach to precision medicine

Clara Carolina Silva De Oliveira et al.

PLOS ONE (2019)

Article Engineering, Biomedical

High Precision Digitization of Paper-Based ECG Records: A Step Toward Machine Learning

Mohammed Baydoun et al.

IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE (2019)

Article Psychiatry

GWAS-based machine learning approach to predict duloxetine response in major depressive disorder

Malgorzata Maciukiewicz et al.

JOURNAL OF PSYCHIATRIC RESEARCH (2018)

Article Multidisciplinary Sciences

Preoperative and postoperative prediction of long-term meningioma outcomes

Efstathios D. Gennatas et al.

PLOS ONE (2018)

Article Multidisciplinary Sciences

An emotional modulation model as signature for the identification of children developmental disorders

Arianna Mencattini et al.

SCIENTIFIC REPORTS (2018)

Article Multidisciplinary Sciences

Using resting state functional MRI to build a personalized autism diagnosis system

Omar Dekhil et al.

PLOS ONE (2018)

Article Multidisciplinary Sciences

A radiomic approach for adaptive radiotherapy in non-small cell lung cancer patients

Sara Ramella et al.

PLOS ONE (2018)

Article Multidisciplinary Sciences

An immunogenic personal neoantigen vaccine for patients with melanoma

Patrick A. Ott et al.

NATURE (2017)

Article Clinical Neurology

Novel Screening Tool for Stroke Using Artificial Neural Network

Vida Abedi et al.

STROKE (2017)

Article Multidisciplinary Sciences

Development of machine learning models for diagnosis of glaucoma

Seong Jae Kim et al.

PLOS ONE (2017)

Article Multidisciplinary Sciences

Use of a machine learning framework to predict substance use disorder treatment success

Laura Acion et al.

PLOS ONE (2017)

Article Multidisciplinary Sciences

Can machine-learning improve cardiovascular risk prediction using routine clinical data?

Stephen F. Weng et al.

PLOS ONE (2017)

Article Multidisciplinary Sciences

Prominent features of the amino acid mutation landscape in cancer

Zachary A. Szpiech et al.

PLOS ONE (2017)

Article Computer Science, Interdisciplinary Applications

Appraisal of adaptive neuro-fuzzy computing technique for estimating anti-obesity properties of a medicinal plant

Mahnaz Kazemipoor et al.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2015)