Using predictive machine learning models for drug response simulation by calibrating patient-specific pathway signatures

AbstractThe utility of pathway signatures lies in their capability to determine whether a specific pathway or biological process is dysregulated in a given patient. These signatures have been widely used in machine learning (ML) methods for a variety of applications including precision medicine, drug repurposing, and drug discovery. In this work, we leverage highly predictive ML models for drug response simulation in individual patients by calibrating the pathway activity scores of disease samples. Using these ML models and an intuitive scoring algorithm to modify the signatures of patients, we evaluate whether a given sample that was formerly classified as diseased, could be predicted as normal following drug treatment simulation. We then use this technique as a proxy for the identification of potential drug candidates. Furthermore, we demonstrate the ability of our methodology to successfully identify approved and clinically investigated drugs for four different cancers, outperforming six comparable state-of-the-art methods. We also show how this approach can deconvolute a drugs’ mechanism of action and propose combination therapies. Taken together, our methodology could be promising to support clinical decision-making in personalized medicine by simulating a drugs’ effect on a given patient.

Download Full-text

Using predictive machine learning models for drug response simulation by calibrating patient-specific pathway signatures

10.1101/2020.12.06.413435 ◽

2020 ◽

Author(s):

Sepehr Golriz Khatami ◽

Sarah Mubeen ◽

Vinay Srinivas Bharadhwaj ◽

Alpha Tom Kodamullil ◽

Martin Hofmann-Apitius ◽

...

Keyword(s):

Machine Learning ◽

Drug Response ◽

Clinical Decision Making ◽

Biological Process ◽

Drug Repurposing ◽

Clinical Decision ◽

Patient Specific ◽

Drug Candidates ◽

Scoring Algorithm ◽

Specific Pathway

AbstractThe utility of pathway signatures lies in their capability to determine whether a specific pathway or biological process is dysregulated in a given patient. These signatures have been widely used in machine learning (ML) methods for a variety of applications including precision medicine, drug repurposing, and drug discovery. In this work, we leverage highly predictive ML models for drug response simulation in individual patients by calibrating the pathway activity scores of disease samples. Using these ML models and a novel scoring algorithm to modify the signatures of patients, we evaluate whether a given sample that was formerly classified as diseased, could be predicted as normal following drug treatment simulation. We then use this technique as a proxy for the identification of potential drug candidates. Furthermore, we demonstrate the ability of our methodology to successfully identify approved and clinically investigated drugs for three different cancers. We also show how this approach can deconvolute a drugs’ mechanism of action and propose combination therapies. Taken together, our methodology could be promising to support clinical decision-making in personalized medicine by simulating a drugs’ effect on a given patient.

Download Full-text

A machine learning framework for automated diagnosis and computer-assisted planning in plastic and reconstructive surgery

Scientific Reports ◽

10.1038/s41598-019-49506-1 ◽

2019 ◽

Vol 9 (1) ◽

Cited By ~ 2

Author(s):

Paul G. M. Knoops ◽

Athanasios Papaioannou ◽

Alessandro Borghi ◽

Richard W. F. Breakey ◽

Alexander T. Wilson ◽

...

Keyword(s):

Machine Learning ◽

Decision Making ◽

Reconstructive Surgery ◽

Clinical Decision Making ◽

Specific Treatment ◽

Operation Time ◽

Clinical Decision ◽

Patient Specific ◽

Computer Assisted ◽

Plastic And Reconstructive Surgery

Abstract Current computational tools for planning and simulation in plastic and reconstructive surgery lack sufficient precision and are time-consuming, thus resulting in limited adoption. Although computer-assisted surgical planning systems help to improve clinical outcomes, shorten operation time and reduce cost, they are often too complex and require extensive manual input, which ultimately limits their use in doctor-patient communication and clinical decision making. Here, we present the first large-scale clinical 3D morphable model, a machine-learning-based framework involving supervised learning for diagnostics, risk stratification, and treatment simulation. The model, trained and validated with 4,261 faces of healthy volunteers and orthognathic (jaw) surgery patients, diagnoses patients with 95.5% sensitivity and 95.2% specificity, and simulates surgical outcomes with a mean accuracy of 1.1 ± 0.3 mm. We demonstrate how this model could fully-automatically aid diagnosis and provide patient-specific treatment plans from a 3D scan alone, to help efficient clinical decision making and improve clinical understanding of face shape as a marker for primary and secondary surgery.

Download Full-text

Machine learning in clinical decision making

Med ◽

10.1016/j.medj.2021.04.006 ◽

2021 ◽

Author(s):

Lorenz Adlung ◽

Yotam Cohen ◽

Uria Mor ◽

Eran Elinav

Keyword(s):

Machine Learning ◽

Decision Making ◽

Clinical Decision Making ◽

Clinical Decision

Download Full-text

Cancer Grade Model: a multi-gene machine learning-based risk classification for improving prognosis in breast cancer

British Journal of Cancer ◽

10.1038/s41416-021-01455-1 ◽

2021 ◽

Author(s):

E. Amiri Souri ◽

A. Chenoweth ◽

A. Cheung ◽

S. N. Karagiannis ◽

S. Tsoka

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Clinical Decision Making ◽

Histological Grade ◽

Tumour Size ◽

Clinical Decision ◽

Gene Signature ◽

Risk Classification ◽

Breast Cancers ◽

Grade 3

Abstract Background Prognostic stratification of breast cancers remains a challenge to improve clinical decision making. We employ machine learning on breast cancer transcriptomics from multiple studies to link the expression of specific genes to histological grade and classify tumours into a more or less aggressive prognostic type. Materials and methods Microarray data of 5031 untreated breast tumours spanning 33 published datasets and corresponding clinical data were integrated. A machine learning model based on gradient boosted trees was trained on histological grade-1 and grade-3 samples. The resulting predictive model (Cancer Grade Model, CGM) was applied on samples of grade-2 and unknown-grade (3029) for prognostic risk classification. Results A 70-gene signature for assessing clinical risk was identified and was shown to be 90% accurate when tested on known histological-grade samples. The predictive framework was validated through survival analysis and showed robust prognostic performance. CGM was cross-referenced with existing genomic tests and demonstrated the competitive predictive power of tumour risk. Conclusions CGM is able to classify tumours into better-defined prognostic categories without employing information on tumour size, stage, or subgroups. The model offers means to improve prognosis and support the clinical decision and precision treatments, thereby potentially contributing to preventing underdiagnosis of high-risk tumours and minimising over-treatment of low-risk disease.

Download Full-text

Clinician checklist for assessing suitability of machine learning applications in healthcare

BMJ Health & Care Informatics ◽

10.1136/bmjhci-2020-100251 ◽

2021 ◽

Vol 28 (1) ◽

pp. e100251

Author(s):

Ian Scott ◽

Stacey Carter ◽

Enrico Coiera

Keyword(s):

Machine Learning ◽

Large Scale ◽

Clinical Decision Making ◽

Improve Patient Care ◽

Clinical Decision ◽

Routine Care ◽

Machine Learning Algorithms ◽

Clinical Settings ◽

Machine Learning Applications ◽

Key Issues

Machine learning algorithms are being used to screen and diagnose disease, prognosticate and predict therapeutic responses. Hundreds of new algorithms are being developed, but whether they improve clinical decision making and patient outcomes remains uncertain. If clinicians are to use algorithms, they need to be reassured that key issues relating to their validity, utility, feasibility, safety and ethical use have been addressed. We propose a checklist of 10 questions that clinicians can ask of those advocating for the use of a particular algorithm, but which do not expect clinicians, as non-experts, to demonstrate mastery over what can be highly complex statistical and computational concepts. The questions are: (1) What is the purpose and context of the algorithm? (2) How good were the data used to train the algorithm? (3) Were there sufficient data to train the algorithm? (4) How well does the algorithm perform? (5) Is the algorithm transferable to new clinical settings? (6) Are the outputs of the algorithm clinically intelligible? (7) How will this algorithm fit into and complement current workflows? (8) Has use of the algorithm been shown to improve patient care and outcomes? (9) Could the algorithm cause patient harm? and (10) Does use of the algorithm raise ethical, legal or social concerns? We provide examples where an algorithm may raise concerns and apply the checklist to a recent review of diagnostic imaging applications. This checklist aims to assist clinicians in assessing algorithm readiness for routine care and identify situations where further refinement and evaluation is required prior to large-scale use.

Download Full-text

Machine-learning based prediction of Cushing’s syndrome in dogs attending UK primary-care veterinary practice

Scientific Reports ◽

10.1038/s41598-021-88440-z ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Imogen Schofield ◽

David C. Brodbelt ◽

Noel Kennedy ◽

Stijn J. M. Niessen ◽

David B. Church ◽

...

Keyword(s):

Machine Learning ◽

Cushing’S Syndrome ◽

Clinical Decision Making ◽

Predictive Performance ◽

Clinical Decision ◽

Cushing's Syndrome ◽

Machine Learning Algorithms ◽

Learning Methods ◽

Machine Learning Methods ◽

Clinical Records

AbstractCushing’s syndrome is an endocrine disease in dogs that negatively impacts upon the quality-of-life of affected animals. Cushing’s syndrome can be a challenging diagnosis to confirm, therefore new methods to aid diagnosis are warranted. Four machine-learning algorithms were applied to predict a future diagnosis of Cushing's syndrome, using structured clinical data from the VetCompass programme in the UK. Dogs suspected of having Cushing's syndrome were included in the analysis and classified based on their final reported diagnosis within their clinical records. Demographic and clinical features available at the point of first suspicion by the attending veterinarian were included within the models. The machine-learning methods were able to classify the recorded Cushing’s syndrome diagnoses, with good predictive performance. The LASSO penalised regression model indicated the best overall performance when applied to the test set with an AUROC = 0.85 (95% CI 0.80–0.89), sensitivity = 0.71, specificity = 0.82, PPV = 0.75 and NPV = 0.78. The findings of our study indicate that machine-learning methods could predict the future diagnosis of a practicing veterinarian. New approaches using these methods could support clinical decision-making and contribute to improved diagnosis of Cushing’s syndrome in dogs.

Download Full-text

Machine learning for dose-volume histogram based clinical decision-making support system in radiation therapy plans for brain tumors

Clinical and Translational Radiation Oncology ◽

10.1016/j.ctro.2021.09.001 ◽

2021 ◽

Author(s):

Pawel Siciarz ◽

Salem Alfaifi ◽

Eric Van Uytven ◽

Shrinivas Rathod ◽

Rashmi Koul ◽

...

Keyword(s):

Machine Learning ◽

Decision Making ◽

Radiation Therapy ◽

Brain Tumors ◽

Support System ◽

Clinical Decision Making ◽

Clinical Decision ◽

Dose Volume Histogram ◽

Dose Volume ◽

Decision Making Support

Download Full-text

Vital signs assessed in initial clinical encounters predict COVID-19 mortality in an NYC hospital system

Scientific Reports ◽

10.1038/s41598-020-78392-1 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Elza Rechtman ◽

Paul Curtin ◽

Esmeralda Navarro ◽

Sharon Nirenberg ◽

Megan K. Horton

Keyword(s):

Machine Learning ◽

New York ◽

Clinical Decision Making ◽

Care Delivery ◽

Vital Signs ◽

Clinical Decision ◽

Rapid Identification ◽

Gradient Boosting ◽

Hospital System ◽

Response Strategies

AbstractTimely and effective clinical decision-making for COVID-19 requires rapid identification of risk factors for disease outcomes. Our objective was to identify characteristics available immediately upon first clinical evaluation related COVID-19 mortality. We conducted a retrospective study of 8770 laboratory-confirmed cases of SARS-CoV-2 from a network of 53 facilities in New-York City. We analysed 3 classes of variables; demographic, clinical, and comorbid factors, in a two-tiered analysis that included traditional regression strategies and machine learning. COVID-19 mortality was 12.7%. Logistic regression identified older age (OR, 1.69 [95% CI 1.66–1.92]), male sex (OR, 1.57 [95% CI 1.30–1.90]), higher BMI (OR, 1.03 [95% CI 1.102–1.05]), higher heart rate (OR, 1.01 [95% CI 1.00–1.01]), higher respiratory rate (OR, 1.05 [95% CI 1.03–1.07]), lower oxygen saturation (OR, 0.94 [95% CI 0.93–0.96]), and chronic kidney disease (OR, 1.53 [95% CI 1.20–1.95]) were associated with COVID-19 mortality. Using gradient-boosting machine learning, these factors predicted COVID-19 related mortality (AUC = 0.86) following cross-validation in a training set. Immediate, objective and culturally generalizable measures accessible upon clinical presentation are effective predictors of COVID-19 outcome. These findings may inform rapid response strategies to optimize health care delivery in parts of the world who have not yet confronted this epidemic, as well as in those forecasting a possible second outbreak.

Download Full-text