Building predictive disease models using extracellular vesicle microscale flow cytometry and machine learning

Paproski, Robert J.; Pink, Desmond; Sosnowski, Deborah; Vásquez, Catalina; Lewis, John D.

doi:10.1002/1878-0261.13362

Cited by 6 publications

(6 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using only probabilities from the held‐out group, each patient had 100 different probabilities of GG ≥3 cancer which was averaged into one probability represented as the EVMAP predictive model. Then the EVMAP predictive model and six clinical features (age, ethnicity, family history of any prostate cancer, previous negative prostate biopsy, PSA levels, and DRE) were used as inputs for logistic regression models and evaluated using 5‐fold cross‐validation to generate the patients' EV‐Fingerprint Score 17 . Prior to model training, missing clinical data was imputed with the median value from the training data.…”

Section: Methodsmentioning

confidence: 99%

“…The EVMAP machine learning model was created with the XGBoost algorithm using R version 3.4.1 software. 17 , 24 ROIs with minimal clinical value were removed via recursive feature elimination which used 10 repeats of 5‐fold cross‐validation (where all patients were divided into 5 different subgroups) using the caret package. Recursive feature elimination removed 10% (GG ≥2 and GG ≥3 cancers) or 25% (GG ≥1 cancer) of features in each iteration.…”

Section: Methodsmentioning

confidence: 99%

“…Then the EVMAP predictive model and six clinical features (age, ethnicity, family history of any prostate cancer, previous negative prostate biopsy, PSA levels, and DRE) were used as inputs for logistic regression models and evaluated using 5‐fold cross‐validation to generate the patients' EV‐Fingerprint Score. 17 Prior to model training, missing clinical data was imputed with the median value from the training data.…”

Section: Methodsmentioning

confidence: 99%

“…16 We recently reported the development of an EV machine learning platform (EVMAP) that can be used to generate risk scores for cancers and other diseases. 17 In this study we hypothesized that augmenting the predictive power of PSA with other clinically useful data, such as a risk score calculator or another liquid sample test, may be highly effective at increasing GG ≥3 prostate cancer sensitivity and specificity and reducing unnecessary biopsies. We used our EVMAP technology to create an accurate diagnostic blood test for GG ≥3 prostate cancer, called the EV-Fingerprint test.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Clinical analysis of EV‐Fingerprint to predict grade group 3 and above prostate cancer and avoid prostate biopsy

Fairey¹,

Paproski

Pink

et al. 2023

Cancer Medicine

Self Cite

View full text Add to dashboard Cite

BackgroundThere is an unmet clinical need for minimally invasive diagnostic tests to improve the detection of grade group (GG) ≥3 prostate cancer relative to prostate antigen‐specific risk calculators. We determined the accuracy of the blood‐based extracellular vesicle (EV) biomarker assay (EV Fingerprint test) at the point of a prostate biopsy decision to predict GG ≥3 from GG ≤2 and avoid unnecessary biopsies.MethodsThis study analyzed 415 men referred to urology clinics and scheduled for a prostate biopsy, were recruited to the APCaRI 01 prospective cohort study. The EV machine learning analysis platform was used to generate predictive EV models from microflow data. Logistic regression was then used to analyze the combined EV models and patient clinical data and generate the patients' risk score for GG ≥3 prostate cancer.ResultsThe EV‐Fingerprint test was evaluated using the area under the curve (AUC) in discrimination of GG ≥3 from GG ≤2 and benign disease on initial biopsy. EV‐Fingerprint identified GG ≥3 cancer patients with high accuracy (0.81 AUC) at 95% sensitivity and 97% negative predictive value. Using a 7.85% probability cutoff, 95% of men with GG ≥3 would have been recommended a biopsy while avoiding 144 unnecessary biopsies (35%) and missing four GG ≥3 cancers (5%). Conversely, a 5% cutoff would have avoided 31 unnecessary biopsies (7%), missing no GG ≥3 cancers (0%).ConclusionsEV‐Fingerprint accurately predicted GG ≥3 prostate cancer and would have significantly reduced unnecessary prostate biopsies.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Clinical analysis of EV‐Fingerprint to predict grade group 3 and above prostate cancer and avoid prostate biopsy

Fairey¹,

Paproski

Pink

et al. 2023

Cancer Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…An emerging field of EV studies is EV microscale cytometry using tissue and distinct biomarkers for the disease, with the goal being to perform a complex analysis and extract predictive models. The aforementioned ML analysis is the so-called extracellular vesicle machine learning analysis platform (EVMAP), which constitutes a useful tool for prediction, by using blood samples [ 230 ].…”

Section: Future Perspectives Of Ev-based Machine Learning-based Algor...mentioning

confidence: 99%

A Current Synopsis of the Emerging Role of Extracellular Vesicles and Micro-RNAs in Pancreatic Cancer: A Forward-Looking Plan for Diagnosis and Treatment

Trifylli,

Kriebardis,

Koustas

et al. 2024

IJMS

View full text Add to dashboard Cite

Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest malignancies worldwide, while it persists as the fourth most prevalent cause of cancer-related death in the United States of America. Although there are several novel therapeutic strategies for the approach of this intensely aggressive tumor, it remains a clinical challenge, as it is hard to identify in early stages, due to its asymptomatic course. A diagnosis is usually established when the disease is already in its late stages, while its chemoresistance constitutes an obstacle to the optimal management of this malignancy. The discovery of novel diagnostic and therapeutic tools is considered a necessity for this tumor, due to its low survival rates and treatment failures. One of the most extensively investigated potential diagnostic and therapeutic modalities is extracellular vesicles (EVs). These vesicles constitute nanosized double-lipid membraned particles that are characterized by a high heterogeneity that emerges from their distinct biogenesis route, their multi-variable sizes, and the particular cargoes that are embedded into these particles. Their pivotal role in cell-to-cell communication via their cargo and their implication in the pathophysiology of several diseases, including pancreatic cancer, opens new horizons in the management of this malignancy. Meanwhile, the interplay between pancreatic carcinogenesis and short non-coding RNA molecules (micro-RNAs or miRs) is in the spotlight of current studies, as they can have either a role as tumor suppressors or promoters. The deregulation of both of the aforementioned molecules leads to several aberrations in the function of pancreatic cells, leading to carcinogenesis. In this review, we will explore the role of extracellular vesicles and miRNAs in pancreatic cancer, as well as their potent utilization as diagnostic and therapeutic tools.

show abstract

Towards the Clinical Implementation of Extracellular Vesicle-Based Biomarker Assays for Cancer

Van Dorpe,

Tummers,

Denys

et al. 2024

Clinical Chemistry

View full text Add to dashboard Cite

Background Substantial research has been devoted to elucidating the role of extracellular vesicles (EVs) in the different hallmarks of cancer. Consequently, EVs are increasingly explored as a source of cancer biomarkers in body fluids. However, the heterogeneity in EVs, the complexity of body fluids, and the diversity in methods available for EV analysis, challenge the development and translation of EV-based biomarker assays. Content Essential steps in EV-associated biomarker development are emphasized covering biobanking, biomarker discovery, verification and validation, and clinical implementation. A meticulous study design is essential and ideally results from close interactions between clinicians and EV researchers. A plethora of different EV preparation protocols exists which warrants quality control and transparency to ensure reproducibility and thus enable verification of EV-associated biomarker candidates identified in the discovery phase in subsequent independent cohorts. The development of an EV-associated biomarker assay requires thorough analytical and clinical validation. Finally, regulatory affairs must be considered for clinical implementation of EV-based biomarker assays. Summary In this review, the current challenges that prevent us from exploiting the full potential of EV-based biomarker assays are identified. Guidelines and tools to overcome these hurdles are highlighted and are crucial to advance EV-based biomarker assays into clinical use.

show abstract

Building predictive disease models using extracellular vesicle microscale flow cytometry and machine learning

Cited by 6 publications

References 46 publications

Clinical analysis of EV‐Fingerprint to predict grade group 3 and above prostate cancer and avoid prostate biopsy

Clinical analysis of EV‐Fingerprint to predict grade group 3 and above prostate cancer and avoid prostate biopsy

A Current Synopsis of the Emerging Role of Extracellular Vesicles and Micro-RNAs in Pancreatic Cancer: A Forward-Looking Plan for Diagnosis and Treatment

Towards the Clinical Implementation of Extracellular Vesicle-Based Biomarker Assays for Cancer

Contact Info

Product

Resources

About