Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Surgery Surgery

Predicting Survival after Extracorporeal Membrane Oxygenation using Machine Learning.

In The Annals of thoracic surgery ; h5-index 58.0

BACKGROUND : Venous-arterial extracorporeal membrane oxygenation (VA-ECMO) undoubtedly saves many lives, but is associated with a high degree of patient morbidity, mortality, and resource utilization. We aimed to develop a machine learning algorithm to augment clinical decision making related to VA-ECMO.

METHODS : Patients supported by VA-ECMO at a single institution from May 2011 to October 2018 were retrospectively reviewed. Laboratory values from only the initial 48 hours of VA-ECMO support were used. Data were split into 70% for training, 15% validation and 15% withheld for testing. Feature importance was estimated and dimensionality reduction techniques were utilized. A deep neural network was trained to predict survival to discharge and the final model was assessed using the independent testing cohort. Model performance was compared to that of the SAVE score using a receiver operator characteristic curve.

RESULTS : Of the 282 eligible adult VA-ECMO patients, 117 (41%) survived to discharge. A total of 1.96 million laboratory values were extracted from the electronic medical record, from which 270 different summary variables were derived for each patient. The most important variables in predicting the primary outcome included lactate, age, total bilirubin, and creatinine. For the testing cohort, the final model achieved 82% overall accuracy and a greater area under the curve (AUC) than the SAVE score (0.92 vs 0.65, p=0.01) in predicting survival to discharge.

CONCLUSIONS : This proof of concept study demonstrates the potential for machine learning models to augment clinical decision making for VA-ECMO patients. Further development with multi-institutional data is warranted.

Ayers Brian, Wood Katherine, Gosev Igor, Prasad Sunil


General General

The anti-ageing effects of a natural peptide discovered by Artificial Intelligence.

In International journal of cosmetic science

OBJECTIVE : As skin ages, impaired extracellular matrix (ECM) protein synthesis and increased action of degradative enzymes manifests as atrophy, wrinkling and laxity. There is mounting evidence for the functional role of exogenous peptides across many areas, including in offsetting the effects of cutaneous ageing. Here, using an artificial intelligence (AI) approach, we identified peptide RTE62G (pep_RTE62G), a naturally occurring, unmodified peptide with ECM stimulatory properties. The AI-predicted anti-ageing properties of pep_RTE62G were then validated through in vitro, ex vivo and proof of concept clinical testing.

METHODS : A deep learning approach was applied to unlock pep_RTE62G from a plant source, Pisum sativum (pea). Cell culture assays of human dermal fibroblasts (HDFs) and keratinocytes (HaCaTs) were subsequently used to evaluate the in vitro effect of pep_RTE62G. Distinct activities such as cell proliferation and ECM protein production properties were determined by ELISA assays. Cell migration was assessed using a wound healing assay, while ECM protein synthesis and gene expression were analysed respectively by immunofluorescence microscopy and PCR. Immunohistochemistry of human skin explants was employed to further investigate the induction of ECM proteins by pep_RTE62G ex vivo. Finally, the clinical effect of pep_RTE626 was evaluated in a proof of concept 28-day pilot study.

RESULTS : In vitro testing confirmed that pep_RTE62G is an effective multi-functional anti-ageing ingredient. In HaCaTs, pep_RTE62G treatment significantly increases both cellular proliferation and migration. Similarly, in HDFs, pep_RTE62G consistently induced the neosynthesis of ECM proteins elastin and collagen; effects that are upheld in human skin explants. Lastly, in our proof of concept clinical study, application of pep_RTE626 over 28 days demonstrated anti-wrinkle and collagen stimulatory potential.

CONCLUSION : pep_RTE62G represents a natural, unmodified peptide with AI predicted and experimentally validated anti-ageing properties. Our results affirm the utility of AI in the discovery of novel, functional topical ingredients.

Kennedy Kathy, Cal Roi, Casey Rory, Lopez Cyril, Adelfio Alessandro, Molloy Brendan, Wall Audrey M, Holton Thérèse A, Khaldi Nora


Anti-ageing, Artificial Intelligence, Cell culture, Claim substantiation in vivo, ECM protein synthesis, Elisa, Proteomics, in vitro; Genomics

General General

Benchmarking predictions of MHC class I restricted T cell epitopes in a comprehensively studied model system.

In PLoS computational biology

T cell epitope candidates are commonly identified using computational prediction tools in order to enable applications such as vaccine design, cancer neoantigen identification, development of diagnostics and removal of unwanted immune responses against protein therapeutics. Most T cell epitope prediction tools are based on machine learning algorithms trained on MHC binding or naturally processed MHC ligand elution data. The ability of currently available tools to predict T cell epitopes has not been comprehensively evaluated. In this study, we used a recently published dataset that systematically defined T cell epitopes recognized in vaccinia virus (VACV) infected C57BL/6 mice (expressing H-2Db and H-2Kb), considering both peptides predicted to bind MHC or experimentally eluted from infected cells, making this the most comprehensive dataset of T cell epitopes mapped in a complex pathogen. We evaluated the performance of all currently publicly available computational T cell epitope prediction tools to identify these major epitopes from all peptides encoded in the VACV proteome. We found that all methods were able to improve epitope identification above random, with the best performance achieved by neural network-based predictions trained on both MHC binding and MHC ligand elution data (NetMHCPan-4.0 and MHCFlurry). Impressively, these methods were able to capture more than half of the major epitopes in the top N = 277 predictions within the N = 767,788 predictions made for distinct peptides of relevant lengths that can theoretically be encoded in the VACV proteome. These performance metrics provide guidance for immunologists as to which prediction methods to use, and what success rates are possible for epitope predictions when considering a highly controlled system of administered immunizations to inbred mice. In addition, this benchmark was implemented in an open and easy to reproduce format, providing developers with a framework for future comparisons against new tools.

Paul Sinu, Croft Nathan P, Purcell Anthony W, Tscharke David C, Sette Alessandro, Nielsen Morten, Peters Bjoern


General General

Predicting host taxonomic information from viral genomes: A comparison of feature representations.

In PLoS computational biology

The rise in metagenomics has led to an exponential growth in virus discovery. However, the majority of these new virus sequences have no assigned host. Current machine learning approaches to predicting virus host interactions have a tendency to focus on nucleotide features, ignoring other representations of genomic information. Here we investigate the predictive potential of features generated from four different 'levels' of viral genome representation: nucleotide, amino acid, amino acid properties and protein domains. This more fully exploits the biological information present in the virus genomes. Over a hundred and eighty binary datasets for infecting versus non-infecting viruses at all taxonomic ranks of both eukaryote and prokaryote hosts were compiled. The viral genomes were converted into the four different levels of genome representation and twenty feature sets were generated by extracting k-mer compositions and predicted protein domains. We trained and tested Support Vector Machine, SVM, classifiers to compare the predictive capacity of each of these feature sets for each dataset. Our results show that all levels of genome representation are consistently predictive of host taxonomy and that prediction k-mer composition improves with increasing k-mer length for all k-mer based features. Using a phylogenetically aware holdout method, we demonstrate that the predictive feature sets contain signals reflecting both the evolutionary relationship between the viruses infecting related hosts, and host-mimicry. Our results demonstrate that incorporating a range of complementary features, generated purely from virus genome sequences, leads to improved accuracy for a range of virus host prediction tasks enabling computational assignment of host taxonomic information.

Young Francesca, Rogers Simon, Robertson David L


Surgery Surgery

Visual Speech Recognition: Improving Speech Perception in Noise through Artificial Intelligence.

In Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery

OBJECTIVES : To compare speech perception (SP) in noise for normal-hearing (NH) individuals and individuals with hearing loss (IWHL) and to demonstrate improvements in SP with use of a visual speech recognition program (VSRP).

STUDY DESIGN : Single-institution prospective study.

SETTING : Tertiary referral center.

SUBJECTS AND METHODS : Eleven NH and 9 IWHL participants in a sound-isolated booth facing a speaker through a window. In non-VSRP conditions, SP was evaluated on 40 Bamford-Kowal-Bench speech-in-noise test (BKB-SIN) sentences presented by the speaker at 50 A-weighted decibels (dBA) with multiperson babble noise presented from 50 to 75 dBA. SP was defined as the percentage of words correctly identified. In VSRP conditions, an infrared camera was used to track 35 points around the speaker's lips during speech in real time. Lip movement data were translated into speech-text via an in-house developed neural network-based VSRP. SP was evaluated similarly in the non-VSRP condition on 42 BKB-SIN sentences, with the addition of the VSRP output presented on a screen to the listener.

RESULTS : In high-noise conditions (70-75 dBA) without VSRP, NH listeners achieved significantly higher speech perception than IWHL listeners (38.7% vs 25.0%, P = .02). NH listeners were significantly more accurate with VSRP than without VSRP (75.5% vs 38.7%, P < .0001), as were IWHL listeners (70.4% vs 25.0% P < .0001). With VSRP, no significant difference in SP was observed between NH and IWHL listeners (75.5% vs 70.4%, P = .15).

CONCLUSIONS : The VSRP significantly increased speech perception in high-noise conditions for NH and IWHL participants and eliminated the difference in SP accuracy between NH and IWHL listeners.

Raghavan Arun M, Lipschitz Noga, Breen Joseph T, Samy Ravi N, Kohlberg Gavriel D


artificial intelligence, computer vision, hearing loss, lip reading, speech perception, speech-in-noise, visual speech recognition

General General

Reframing Telehealth: Regulation, Licensing, and Reimbursement in Connected Care.

In Obstetrics and gynecology clinics of North America

Complexity in regulation and reimbursement of telehealth across the United States yields inconsistent use and availability of services. Drivers of this variation stem from existing regulatory, licensing, and payment policy that was designed for face-to-face care. Emerging technology for connected care continues to outpace the rules that govern its use. This article explores the drivers of uncertainty around regulation and payment of remote care services, and provides a roadmap for fulfillment of the benefits of connected care.

McCauley Janet L, Swartz Anthony E


Artificial intelligence, Connected care, Fee for service, Reimbursement, Telehealth, Telemedicine, Value-based care, Virtual care