Featured
-
-
Article
| Open AccessIdentification and validation of a blood- based diagnostic lipidomic signature of pediatric inflammatory bowel disease
Diagnostic blood-based biomarkers of pediatric IBD are limited. Here, the authors demonstrate a diagnostic lipidomic signature, comprising only of two molecular lipids. Translation of this signature into a scalable test has the potential to support clinical decision making.
- Samira Salihovic
- , Niklas Nyström
- & Jonas Halfvarson
-
Article
| Open AccessDevelopment and deployment of a histopathology-based deep learning algorithm for patient prescreening in a clinical trial
Here, the authors develop a deep-learning algorithm to predict biomarkers from histopathological imaging in advanced urothelial cancer patients. This method detects suitable patients for targeted therapy clinical trials with a significant reduction in molecular testing, providing cost and time savings in real-world clinical settings.
- Albert Juan Ramon
- , Chaitanya Parmar
- & Kristopher A. Standish
-
Article
| Open AccessArtificial intelligence enables precision diagnosis of cervical cytology grades and cervical cancer
Cervical screening is a key method for detecting cervical cancer, but is limited by pathologist detection. Here, the authors use artificial intelligence to predict cytology grades from whole slide images.
- Jue Wang
- , Yunfang Yu
- & Herui Yao
-
Article
| Open AccessRapid and on-site wireless immunoassay of respiratory virus aerosols via hydrogel-modulated resonators
Infectious respiratory viruses have been an everlasting threaten to public health. Here, authors report a wireless immunoassay technology based on immuno-responsive hydrogel-modulated resonant sensors, which facilitate on-site respiratory virus surveillance.
- Xin Li
- , Rujing Sun
- & Qingjun Liu
-
Article
| Open AccessUltrasensitive single-step CRISPR detection of monkeypox virus in minutes with a vest-pocket diagnostic device
The recent monkeypox outbreak highlighted the need for rapid and accurate diagnosis of this disease. Here, authors develop an ultrasensitive and streamlined CRISPR assay using miniaturized device, which can detect monkeypox virus in rash fluid swab, oral swab, saliva, and urine within 15 minutes.
- Yunxiang Wang
- , Hong Chen
- & Shengqi Wang
-
Article
| Open AccessIn-depth correlation analysis between tear glucose and blood glucose using a wireless smart contact lens
The correlation between tear glucose and blood glucose is still controversial. Here, the authors demonstrated the correlation between tear glucose and blood glucose in both animal models and human subjects using smart contact lenses.
- Wonjung Park
- , Hunkyu Seo
- & Jang-Ung Park
-
Article
| Open AccessDeep learning model for personalized prediction of positive MRSA culture using time-series electronic health records
Identification of patients at high risk of methicillin-resistant Staphylococcus aureus (MRSA) infection could improve treatment outcomes by optimising antimicrobial therapy. Here the authors develop a deep learning model that uses electronic health record data from the United States to predict MRSA culture positivity.
- Masayuki Nigo
- , Laila Rasmy
- & Degui Zhi
-
Article
| Open AccessEnhancing the fairness of AI prediction models by Quasi-Pareto improvement among heterogeneous thyroid nodule population
Artificial Intelligence (AI) models for medical diagnosis often face challenges of generalizability and fairness. Here, the authors show that the Quasi-Pareto Improvement approach is widely applicable to improving AI models among less-prevalent subgroups, promoting equitable healthcare outcomes.
- Siqiong Yao
- , Fang Dai
- & Hui Lu
-
Article
| Open AccessRapid deep learning-assisted predictive diagnostics for point-of-care testing
A key aim in the development of diagnostic assays is improving diagnostic speed while maintaining sensitivity. Here the authors report an approach for the rapid and accurate analysis of lateral flow tests, which integrates time-series deep learning and AI verification, achieving a diagnostic time of 1-2 minutes.
- Seungmin Lee
- , Jeong Soo Park
- & Jeong Hoon Lee
-
Article
| Open AccessFlexible and cost-effective genomic surveillance of P. falciparum malaria with targeted nanopore sequencing
Genomic surveillance of Plasmodium falciparum could improve monitoring of drug resistance, but implementation has been hampered due to the large and complex genome. Here, de Cesare et al. develop a flexible and cost-effective nanopore sequencing approach to detect drug resistance and diagnostic escape for P. falciparum malaria.
- Mariateresa de Cesare
- , Mulenga Mwenda
- & Jason A. Hendry
-
Article
| Open AccessEarly onset diagnosis in Alzheimer’s disease patients via amyloid-β oligomers-sensing probe in cerebrospinal fluid
In this work, the authors characterize a small molecule fluorescent probe pioneering early diagnosis of Alzheimer’s disease through identification of amyloid-β oligomers in patients’ cerebrospinal fluid, demonstrating potential for clinical application.
- Jusung An
- , Kyeonghwan Kim
- & Jong Seung Kim
-
Article
| Open AccessCongenital heart disease detection by pediatric electrocardiogram based deep learning integrated with human concepts
Congenital heart disease is life threatening, and its screening is complex and costly. Here, authors use AI to detect the disease based on pediatric electrocardiogram, suggesting superior performance over cardiologists.
- Jintai Chen
- , Shuai Huang
- & Huiying Liang
-
Article
| Open AccessRapid and visual identification of β-lactamase subtypes for precision antibiotic therapy
The rapid identification of drug-resistant bacteria is vital for effective treatment and to avoid antibiotic misuse. Here authors report a paper-based sensor which utilises chromogenic carbapenem and cephalosporin substrates for the identification and discrimination of β-lactamase subtypes.
- Wenshuai Li
- , Jingqi Li
- & Dingbin Liu
-
Article
| Open AccessA Machine Learning-Driven Virtual Biopsy System For Kidney Transplant Patients
Despite being recommended, day-zero biopsies are often not performed, due to the cost and time. Here, the authors show that machine learning and donor’s basic parameters can predict the biopsy, offering a reliable virtual estimation of the day-zero biopsy findings.
- Daniel Yoo
- , Gillian Divard
- & Alexandre Loupy
-
Article
| Open AccessDermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma
Artificial intelligence has become popular as a cancer classification tool, but there is distrust of such systems due to their lack of transparency. Here, the authors develop an explainable AI system which produces text- and region-based explanations alongside its classifications which was assessed using clinicians’ diagnostic accuracy, diagnostic confidence, and their trust in the system.
- Tirtha Chanda
- , Katja Hauser
- & Titus J. Brinker
-
Article
| Open AccessAutonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial
Diabetic retinopathy is a complication of diabetes that can be prevented through screening, yet adherence is low. Here, the authors show that autonomous AI increases diabetic eye exam completion in a diverse cohort of youth with diabetes.
- Risa M. Wolf
- , Roomasa Channa
- & Michael D. Abramoff
-
Article
| Open AccessQuick model-based viscoelastic clot strength predictions from blood protein concentrations for cybermedical coagulation control
Available viscoelastic models of blood flow and blood coagulation are unsuited for a cybermedical input-output type of control system application. Here the authors present validated viscoelastic coagulation models that use quickly-measurable protein concentrations to forecast slow clot strength curves for future automation.
- Damon E. Ghetmiri
- , Alessia J. Venturi
- & Amor A. Menezes
-
Article
| Open AccessAI co-pilot bronchoscope robot
The unequal distribution of medical resources means that bronchoscopic services are often unavailable in underdeveloped areas. Here, the authors present an AI co-pilot bronchoscope robot that features a user-friendly plug-and-play catheter and an AI-human shared control algorithm, to enable novice doctors to conduct lung examinations safely.
- Jingyu Zhang
- , Lilu Liu
- & Haojian Lu
-
Article
| Open AccessDeep learning-based phenotyping reclassifies combined hepatocellular-cholangiocarcinoma
Combined hepatocellular-cholangiocarcinomas (cHCC-CCA) are challenging to diagnose, as they exhibit features of hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICCA). Here, the authors use deep learning to re-classify cHCC-CCA tumours into HCC or ICCA based on histopathology images.
- Julien Calderaro
- , Narmin Ghaffari Laleh
- & Jakob Nikolas Kather
-
Article
| Open AccessFetal biometry and amniotic fluid volume assessment end-to-end automation using Deep Learning
Fetal biometry and amniotic fluid volume are essential but strenuous measurements in fetal ultrasound screening. Here, the authors show that deep learning models can automate these measurements with high accuracy, using a large and diverse dataset of Moroccan fetal ultrasound images.
- Saad Slimani
- , Salaheddine Hounka
- & El Houssine Bouyakhf
-
Article
| Open AccessHierarchical AI enables global interpretation of culture plates in the era of digital microbiology
DeepColony is a multi-level AI solution for the interpretation of bacterial culturing images in clinical microbiology laboratory automations. Here, the authors show it allows presumptive identification and quantitation of relevant pathogens at both colony- and plate-level.
- Alberto Signoroni
- , Alessandro Ferrari
- & Karissa Culbreath
-
Article
| Open AccessAutomatic correction of performance drift under acquisition shift in medical image classification
Automatic correction of performance drift caused by changes in image acquisition is key for safe AI deployment. Here, the authors present a solution that restores the expected clinical performance of image classification systems in breast screening and histopathology.
- Mélanie Roschewitz
- , Galvin Khara
- & Ben Glocker
-
Article
| Open AccessImproving model fairness in image-based computer-aided diagnosis
Deep learning models can reflect and amplify human bias, potentially resulting inaccurate missed diagnoses. Here, the authors show that by leveraging the marginal pairwise equal opportunity, their model reduces bias in medical image classification by over 35% compared to baseline models, with minimal impact on AUC values.
- Mingquan Lin
- , Tianhao Li
- & Yifan Peng
-
Article
| Open AccessMetagenomic sequencing of post-mortem tissue samples for the identification of pathogens associated with neonatal deaths
Rapid identification of pathogens in neonatal infection, and corresponding antimicrobial susceptibility profiles, would improve patient outcomes and assist in antibiotic stewardship. In this work, the authors utilize metagenomic next-generation sequencing of post-mortem tissue samples to identify pathogens associated with neonatal deaths.
- Vicky L. Baillie
- , Shabir A. Madhi
- & Courtney P. Olwagen
-
Article
| Open AccessDecentralized federated learning through proxy model sharing
Federated learning enables multi-institutional collaborations on decentralized data with improved privacy protection. Here, authors propose a new scheme for decentralized federated learning with much less communication overhead and stronger privacy.
- Shivam Kalra
- , Junfeng Wen
- & H. R. Tizhoosh
-
Article
| Open AccessBridging clinic and wildlife care with AI-powered pan-species computational pathology
Artificial Intelligence (AI) has the potential of assisting the study and diagnosis of veterinary cancers. Here, the authors build a cancer digital pathology atlas encompassing multiple animal species and demonstrate an AI approach for comparative pathology, which yields insights about immune response and morphological similarities.
- Khalid AbdulJabbar
- , Simon P. Castillo
- & Yinyin Yuan
-
Article
| Open AccessSample-to-answer platform for the clinical evaluation of COVID-19 using a deep learning-assisted smartphone-based assay
The lateral flow assay (LFA) has been considered a rapid test tool but with low sensitivity hampering the precise diagnosis. Here, the authors report bioengineered enrichment tools for LFAs with enhanced sensitivity and specificity that can reinforce LFA’s clinical performance.
- Seungmin Lee
- , Sunmok Kim
- & Jeong Hoon Lee
-
Article
| Open AccessSingle test-based diagnosis of multiple cancer types using Exosome-SERS-AI for early stage cancers
Early detection of multiple cancers through a single method could be clinically important. Here the authors report the diagnostic performance for early detection for multiple cancers using surface-enhanced Raman spectroscopy (SERS) profiles of exosomes from a single blood test and artificial intelligence in a retrospective study design.
- Hyunku Shin
- , Byeong Hyeon Choi
- & Yeonho Choi
-
Article
| Open AccessPCR-like performance of rapid test with permselective tunable nanotrap
Lateral flow assays are valuable rapid diagnostic tests, but low sensitivity can hinder their precision. Here, the authors report an enrichment method using nanoporous AAO and red blood cell membranes, which when applied to patient samples prior to analysis can improve sensitivity up to 20-fold.
- Seong Jun Park
- , Seungmin Lee
- & Jeong Hoon Lee
-
Review Article
| Open AccessSmartphone-based platforms implementing microfluidic detection with image-based artificial intelligence
Smartphone-based mobile health platforms have drawn increasing attention from researchers developing point-of-care testing devices. Here the authors summarize recent progress and future directions of approaches combining microfluidics and artificial intelligence.
- Bangfeng Wang
- , Yiwei Li
- & Bi-Feng Liu
-
Article
| Open AccessSequence terminus dependent PCR for site-specific mutation and modification detection
Rapid and facile detection of specific nucleic acid modifications could have numerous applications. Here the authors present Specific Terminal Mediated Polymerase Chain Reaction (STEM-PCR) as a generic and accessible approach, and demonstrate proof-of-principle cancer biomarker detection.
- Gaolian Xu
- , Hao Yang
- & Hongchen Gu
-
Article
| Open AccessTEFM variants impair mitochondrial transcription causing childhood-onset neurological disease
Van Haute et al describe autosomal recessive TEFM variants that impair mitochondrial transcription elongation and reduce the levels of promoter distal mitochondrial RNA transcripts, leading to heterogeneous mitochondrial diseases with a treatable neuromuscular transmission defect.
- Lindsey Van Haute
- , Emily O’Connor
- & Rita Horvath
-
Article
| Open AccessWireless theranostic smart contact lens for monitoring and control of intraocular pressure in glaucoma
Glaucoma is an irreversible ocular disease that may lead to vision loss. Here the authors develop a theranostic smart contact lens with an intraocular pressure sensor, a flexible drug delivery system, wireless power and communication systems and an application specific integrated circuit chip for both monitoring and control of intraocular pressure in glaucoma induced rabbits.
- Tae Yeon Kim
- , Jee Won Mok
- & Sei Kwang Hahn
-
Article
| Open AccessA suite of PCR-LwCas13a assays for detection and genotyping of Treponema pallidum in clinical samples
Clinical diagnosis of Treponema pallidum subspecies pallidum (TPA), the causative agent of syphilis, depends upon serological testing, which has reduced sensitivity for some stages of the disease. Accompanying methods to complement serological testing also have distinct limitations. In this work, authors develop an assay that combines PCR with CRISPR-LwCas13a, and demonstrate sensitivity and specificity on clinically confirmed syphilis samples.
- Wentao Chen
- , Hao Luo
- & Heping Zheng
-
Article
| Open AccessSelf-evolving vision transformer for chest X-ray diagnosis through knowledge distillation
Although deep learning-based computer-aided diagnosis systems have recently achieved expert level performance, developing a robust model requires large, high-quality data with annotations. Here, the authors present a framework which can improve the performance of vision transformer simultaneously with self-supervision and self-training.
- Sangjoon Park
- , Gwanghyun Kim
- & Jong Chul Ye
-
Article
| Open AccessWireless implantable optical probe for continuous monitoring of oxygen saturation in flaps and organ grafts
Although continuous monitoring of tissue oxygenation is critically important after tissue/organ graft procedures, current technologies have key limitations. Here, the authors develop a miniaturized, minimally invasive, self-anchoring optical probe and demonstrate continuous monitoring of oxygenation in porcine flap and organ models.
- Hexia Guo
- , Wubin Bai
- & John A. Rogers
-
Article
| Open AccessCombining rapid antigen testing and syndromic surveillance improves community-based COVID-19 detection in a low-income country
Rapid antigen tests and syndromic surveillance for identification of COVID-19 cases are limited by low sensitivity and specificity, respectively. Here, the authors use data from Bangladesh and show that combining the two methods improves diagnostic accuracy in a range of epidemiological scenarios.
- Fergus J. Chadwick
- , Jessica Clark
- & Ayesha Sania
-
Article
| Open AccessIntelligent wireless theranostic contact lens for electrical sensing and regulation of intraocular pressure
Towards intelligent treatment for glaucoma, here authors demonstrate integrated wireless theranostic contact lenses for in situ electrical sensing of intraocular pressure and on demand anti-glaucoma drug delivery.
- Cheng Yang
- , Qianni Wu
- & Xi Xie
-
Article
| Open AccessDigital plasmonic nanobubble detection for rapid and ultrasensitive virus diagnostics
Digital immunoassays are powerful platforms but are complex and require multiple steps to perform. Here the authors show that digital plasmonic nanobubble detection allows rapid and ultrasensitive diagnostics via a one-step homogeneous immunoassay.
- Yaning Liu
- , Haihang Ye
- & Zhenpeng Qin
-
Article
| Open AccessAutomated multilabel diagnosis on electrocardiographic images and signals
The application of artificial intelligence for automated diagnosis of electrocardiograms can improve care in remote settings but is limited by the reliance on infrequently available signal-based data. Here, the authors report the development of a multi-label automated diagnosis model for electrocardiographic images.
- Veer Sangha
- , Bobak J. Mortazavi
- & Rohan Khera
-
Article
| Open AccessActive label cleaning for improved dataset quality under resource constraints
High quality labels are important for model performance, evaluation and selection in medical imaging. As manual labelling is time-consuming and costly, the authors explore and benchmark various resource-effective methods for improving dataset quality.
- Mélanie Bernhardt
- , Daniel C. Castro
- & Ozan Oktay
-
Article
| Open AccessPaper microfluidic implementation of loop mediated isothermal amplification for early diagnosis of hepatitis C virus
Current HCV nucleic acid-based diagnosis is largely performed in centralised laboratories. Here, the authors present a pan-genotypic RNA assay, based on reverse transcriptase loop mediated isothermal amplification and develop a low-cost prototype paper-based lateral flow device for point-of-care use, providing a visually read result within 40 min.
- Weronika Witkowska McConnell
- , Chris Davis
- & Jonathan M. Cooper
-
Article
| Open AccessThe reduction of race and gender bias in clinical treatment recommendations using clinician peer networks in an experimental setting
Race and gender bias in healthcare contribute to health disparities. Here the authors show in an experimental setting that structured information sharing networks among clinicians can reduce race and gender bias in medical decisions.
- Damon Centola
- , Douglas Guilbeault
- & Jingwen Zhang
-
Article
| Open AccessDeep learning-based transformation of H&E stained tissues into special stains
Performing multiple histological stains on a biopsy can be costly and time consuming. Here the authors present a method for the digital transformation of H&E stained tissue into special stains (e.g., PAS, Masson’s Trichrome and Jones silver stain), and demonstrate that it improves diagnoses over the use of H&E only.
- Kevin de Haan
- , Yijie Zhang
- & Aydogan Ozcan
-
Article
| Open AccessAll-printed stretchable corneal sensor on soft contact lenses for noninvasive and painless ocular electrodiagnosis
Though smart contact lenses are an attractive technology for recording electroretinogram signals, existing approaches suffer from poor mechanical reliability, chemical stability and wettability. Here, the authors report an all-printed stretchable corneal sensor built on commercial soft contact lenses.
- Kyunghun Kim
- , Ho Joong Kim
- & Chi Hwan Lee
-
Article
| Open AccessStandardization of ELISA protocols for serosurveys of the SARS-CoV-2 pandemic using clinical and at-home blood sampling
Understanding the infection parameters and host responses against SARS-CoV-2 require data from large cohorts using standardized methods. Here, the authors optimize a serum ELISA protocol that has minimal cross-reactivity and flexible sample collection workflow in an attempt to standardize data generation and help inform on COVID-19 pandemic and immunity.
- Carleen Klumpp-Thomas
- , Heather Kalish
- & Kaitlyn Sadtler
-
Article
| Open AccessDevelopment and evaluation of an artificial intelligence system for COVID-19 diagnosis
In some contexts, rapid detection of COVID-19 from CT scans can be crucial for optimal patient management. Here, the authors present a Deep Learning system for this task with multi-center data, human reader comparison and age stratified results.
- Cheng Jin
- , Weixiang Chen
- & Jianjiang Feng
-
Article
| Open AccessMassive and rapid COVID-19 testing is feasible by extraction-free SARS-CoV-2 RT-PCR
SARS-CoV-2 infection is widely diagnosed by RT-PCR, but RNA extraction is a bottleneck for fast and cheap diagnosis. Here, the authors develop protocols to perform RT-PCR directly on heat-inactivated subject samples or samples lysed with readily available detergents and benchmark performance against 597 clinically diagnosed patient samples.
- Ioanna Smyrlaki
- , Martin Ekman
- & Björn Reinius
-
Article
| Open AccessUltrasensitive and visual detection of SARS-CoV-2 using all-in-one dual CRISPR-Cas12a assay
Rapid and early detection of SARS-CoV-2 will aid intervention to stop disease spread. Here the authors present a one-pot CRISPR-based rapid detection system with visual readout.
- Xiong Ding
- , Kun Yin
- & Changchun Liu