RESUMO
MOTIVATION: Resistance co-occurrence within first-line anti-tuberculosis (TB) drugs is a common phenomenon. Existing methods based on genetic data analysis of Mycobacterium tuberculosis (MTB) have been able to predict resistance of MTB to individual drugs, but have not considered the resistance co-occurrence and cannot capture latent structure of genomic data that corresponds to lineages. RESULTS: We used a large cohort of TB patients from 16 countries across six continents where whole-genome sequences for each isolate and associated phenotype to anti-TB drugs were obtained using drug susceptibility testing recommended by the World Health Organization. We then proposed an end-to-end multi-task model with deep denoising auto-encoder (DeepAMR) for multiple drug classification and developed DeepAMR_cluster, a clustering variant based on DeepAMR, for learning clusters in latent space of the data. The results showed that DeepAMR outperformed baseline model and four machine learning models with mean AUROC from 94.4% to 98.7% for predicting resistance to four first-line drugs [i.e. isoniazid (INH), ethambutol (EMB), rifampicin (RIF), pyrazinamide (PZA)], multi-drug resistant TB (MDR-TB) and pan-susceptible TB (PANS-TB: MTB that is susceptible to all four first-line anti-TB drugs). In the case of INH, EMB, PZA and MDR-TB, DeepAMR achieved its best mean sensitivity of 94.3%, 91.5%, 87.3% and 96.3%, respectively. While in the case of RIF and PANS-TB, it generated 94.2% and 92.2% sensitivity, which were lower than baseline model by 0.7% and 1.9%, respectively. t-SNE visualization shows that DeepAMR_cluster captures lineage-related clusters in the latent space. AVAILABILITY AND IMPLEMENTATION: The details of source code are provided at http://www.robots.ox.ac.uk/â¼davidc/code.php. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Assuntos
Mycobacterium tuberculosis , Antituberculosos , Testes de Sensibilidade Microbiana , PirazinamidaRESUMO
Stroke is a life-threatening medical condition that could lead to mortality or significant sensorimotor deficits. Various machine learning techniques have been successfully used to detect and predict stroke-related outcomes. Considering the diversity in the type of clinical modalities involved during management of patients with stroke, such as medical images, bio-signals, and clinical data, multimodal machine learning has become increasingly popular. Thus, we conducted a systematic literature review to understand the current status of state-of-the-art multimodal machine learning methods for stroke prognosis and diagnosis. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines during literature search and selection, our results show that the most dominant techniques are related to the fusion paradigm, specifically early, joint and late fusion. We discuss opportunities to leverage other multimodal learning paradigms, such as multimodal translation and alignment, which are generally less explored. We also discuss the scale of datasets and types of modalities used to develop existing models, highlighting opportunities for the creation of more diverse multimodal datasets. Finally, we present ongoing challenges and provide a set of recommendations to drive the next generation of multimodal learning methods for improved prognosis and diagnosis of patients with stroke.
RESUMO
Unrecognized deterioration of COVID-19 patients can lead to high morbidity and mortality. Most existing deterioration prediction models require a large number of clinical information, typically collected in hospital settings, such as medical images or comprehensive laboratory tests. This is infeasible for telehealth solutions and highlights a gap in deterioration prediction models based on minimal data, which can be recorded at a large scale in any clinic, nursing home, or even at the patient's home. In this study, we develop and compare two prognostic models that predict if a patient will experience deterioration in the forthcoming 3 to 24 h. The models sequentially process routine triadic vital signs: (a) oxygen saturation, (b) heart rate, and (c) temperature. These models are also provided with basic patient information, including sex, age, vaccination status, vaccination date, and status of obesity, hypertension, or diabetes. The difference between the two models is the way that the temporal dynamics of the vital signs are processed. Model #1 utilizes a temporally-dilated version of the Long-Short Term Memory model (LSTM) for temporal processes, and Model #2 utilizes a residual temporal convolutional network (TCN) for this purpose. We train and evaluate the models using data collected from 37,006 COVID-19 patients at NYU Langone Health in New York, USA. The convolution-based model outperforms the LSTM based model, achieving a high AUROC of 0.8844-0.9336 for 3 to 24 h deterioration prediction on a held-out test set. We also conduct occlusion experiments to evaluate the importance of each input feature, which reveals the significance of continuously monitoring the variation of the vital signs. Our results show the prospect for accurate deterioration forecast using a minimum feature set that can be relatively easily obtained using wearable devices and self-reported patient information.
Assuntos
COVID-19 , Aprendizado Profundo , Humanos , COVID-19/diagnóstico , Frequência Cardíaca , Instituições de Assistência Ambulatorial , HospitaisRESUMO
BACKGROUND: Early warning score systems are widely used for identifying patients who are at the highest risk of deterioration to assist clinical decision-making. This could facilitate early intervention and consequently improve patient outcomes; for example, the National Early Warning Score (NEWS) system, which is recommended by the Royal College of Physicians in the United Kingdom, uses predefined alerting thresholds to assign scores to patients based on their vital signs. However, there is limited evidence of the reliability of such scores across patient cohorts in the United Arab Emirates. OBJECTIVE: Our aim in this study was to propose a data-driven model that accurately predicts in-hospital deterioration in an inpatient cohort in the United Arab Emirates. METHODS: We conducted a retrospective cohort study using a real-world data set that consisted of 16,901 unique patients associated with 26,073 inpatient emergency encounters and 951,591 observation sets collected between April 2015 and August 2021 at a large multispecialty hospital in Abu Dhabi, United Arab Emirates. The observation sets included routine measurements of heart rate, respiratory rate, systolic blood pressure, level of consciousness, temperature, and oxygen saturation, as well as whether the patient was receiving supplementary oxygen. We divided the data set of 16,901 unique patients into training, validation, and test sets consisting of 11,830 (70%; 18,319/26,073, 70.26% emergency encounters), 3397 (20.1%; 5206/26,073, 19.97% emergency encounters), and 1674 (9.9%; 2548/26,073, 9.77% emergency encounters) patients, respectively. We defined an adverse event as the occurrence of admission to the intensive care unit, mortality, or both if the patient was admitted to the intensive care unit first. On the basis of 7 routine vital signs measurements, we assessed the performance of the NEWS system in detecting deterioration within 24 hours using the area under the receiver operating characteristic curve (AUROC). We also developed and evaluated several machine learning models, including logistic regression, a gradient-boosting model, and a feed-forward neural network. RESULTS: In a holdout test set of 2548 encounters with 95,755 observation sets, the NEWS system achieved an overall AUROC value of 0.682 (95% CI 0.673-0.690). In comparison, the best-performing machine learning models, which were the gradient-boosting model and the neural network, achieved AUROC values of 0.778 (95% CI 0.770-0.785) and 0.756 (95% CI 0.749-0.764), respectively. Our interpretability results highlight the importance of temperature and respiratory rate in predicting patient deterioration. CONCLUSIONS: Although traditional early warning score systems are the dominant form of deterioration prediction models in clinical practice today, we strongly recommend the development and use of cohort-specific machine learning models as an alternative. This is especially important in external patient cohorts that were unseen during model development.
RESUMO
Urine culture is often considered the gold standard for detecting the presence of bacteria in the urine. Since culture is expensive and often requires 24-48 hours, clinicians often rely on urine dipstick test, which is considerably cheaper than culture and provides instant results. Despite its ease of use, urine dipstick test may lack sensitivity and specificity. In this paper, we use a real-world dataset consisting of 17,572 outpatient encounters who underwent urine cultures, collected between 2015 and 2021 at a large multi-specialty hospital in Abu Dhabi, United Arab Emirates. We develop and evaluate a simple parsimonious prediction model for positive urine cultures based on a minimal input set of ten features selected from the patient's presenting vital signs, history, and dipstick results. In a test set of 5,339 encounters, the parsimonious model achieves an area under the receiver operating characteristic curve (AUROC) of 0.828 (95% CI: 0.810-0.844) for predicting a bacterial count ≥ 105 CFU/ml, outperforming a model that uses dipstick features only that achieves an AUROC of 0.786 (95% CI: 0.769-0.806). Our proposed model can be easily deployed at point-of-care, highlighting its value in improving the efficiency of clinical workflows, especially in low-resource settings.
RESUMO
Pathology reports are considered the gold standard in medical research due to their comprehensive and accurate diagnostic information. Natural language processing (NLP) techniques have been developed to automate information extraction from pathology reports. However, existing studies suffer from two significant limitations. First, they typically frame their tasks as report classification, which restricts the granularity of extracted information. Second, they often fail to generalize to unseen reports due to variations in language, negation, and human error. To overcome these challenges, we propose a BERT (bidirectional encoder representations from transformers) named entity recognition (NER) system to extract key diagnostic elements from pathology reports. We also introduce four data augmentation methods to improve the robustness of our model. Trained and evaluated on 1438 annotated breast pathology reports, acquired from a large medical center in the United States, our BERT model trained with data augmentation achieves an entity F1-score of 0.916 on an internal test set, surpassing the BERT baseline (0.843). We further assessed the model's generalizability using an external validation dataset from the United Arab Emirates, where our model maintained satisfactory performance (F1-score 0.860). Our findings demonstrate that our NER systems can effectively extract fine-grained information from widely diverse medical reports, offering the potential for large-scale information extraction in a wide range of medical and AI research. We publish our code at https://github.com/nyukat/pathology_extraction.
RESUMO
Clinical time-series data retrieved from electronic medical records are widely used to build predictive models of adverse events to support resource management. Such data is often sparse and irregularly-sampled, which makes it challenging to use many common machine learning methods. Missing values may be interpolated by carrying the last value forward, or through linear regression. Gaussian process (GP) regression is also used for performing imputation, and often re-sampling of time-series at regular intervals. The use of GPs can require extensive, and likely adhoc, investigation to determine model structure, such as an appropriate covariance function. This can be challenging for multivariate real-world clinical data, in which time-series variables exhibit different dynamics to one another. In this work, we construct generative models to estimate missing values in clinical time-series data using a neural latent variable model, known as a Neural Process (NP). The NP model employs a conditional prior distribution in the latent space to learn global uncertainty in the data by modelling variations at a local level. In contrast to conventional generative modelling, this prior is not fixed and is itself learned during the training process. Thus, NP model provides the flexibility to adapt to the dynamics of the available clinical data. We propose a variant of the NP framework for efficient modelling of the mutual information between the latent and input spaces, ensuring meaningful learned priors. Experiments using the MIMIC III dataset demonstrate the effectiveness of the proposed approach as compared to conventional methods.
Assuntos
Aprendizado de Máquina , Modelos Teóricos , Registros Eletrônicos de Saúde , Humanos , Distribuição Normal , Fatores de TempoRESUMO
Clinical evidence suggests that some patients diagnosed with coronavirus disease 2019 (COVID-19) experience a variety of complications associated with significant morbidity, especially in severe cases during the initial spread of the pandemic. To support early interventions, we propose a machine learning system that predicts the risk of developing multiple complications. We processed data collected from 3,352 patient encounters admitted to 18 facilities between April 1 and April 30, 2020, in Abu Dhabi (AD), United Arab Emirates. Using data collected during the first 24 h of admission, we trained machine learning models to predict the risk of developing any of three complications after 24 h of admission. The complications include Secondary Bacterial Infection (SBI), Acute Kidney Injury (AKI), and Acute Respiratory Distress Syndrome (ARDS). The hospitals were grouped based on geographical proximity to assess the proposed system's learning generalizability, AD Middle region and AD Western & Eastern regions, A and B, respectively. The overall system includes a data filtering criterion, hyperparameter tuning, and model selection. In test set A, consisting of 587 patient encounters (mean age: 45.5), the system achieved a good area under the receiver operating curve (AUROC) for the prediction of SBI (0.902 AUROC), AKI (0.906 AUROC), and ARDS (0.854 AUROC). Similarly, in test set B, consisting of 225 patient encounters (mean age: 42.7), the system performed well for the prediction of SBI (0.859 AUROC), AKI (0.891 AUROC), and ARDS (0.827 AUROC). The performance results and feature importance analysis highlight the system's generalizability and interpretability. The findings illustrate how machine learning models can achieve a strong performance even when using a limited set of routine input variables. Since our proposed system is data-driven, we believe it can be easily repurposed for different outcomes considering the changes in COVID-19 variants over time.
RESUMO
Clinical decision-making in healthcare is already being influenced by predictions or recommendations made by data-driven machines. Numerous machine learning applications have appeared in the latest clinical literature, especially for outcome prediction models, with outcomes ranging from mortality and cardiac arrest to acute kidney injury and arrhythmia. In this review article, we summarize the state-of-the-art in related works covering data processing, inference, and model evaluation, in the context of outcome prediction models developed using data extracted from electronic health records. We also discuss limitations of prominent modeling assumptions and highlight opportunities for future research.
Assuntos
Tomada de Decisões Assistida por Computador , Técnicas de Apoio para a Decisão , Registros Eletrônicos de Saúde , Aprendizado de Máquina , Big Data , Humanos , Resultado do TratamentoRESUMO
The rapid spread of COVID-19 cases in recent months has strained hospital resources, making rapid and accurate triage of patients presenting to emergency departments a necessity. Machine learning techniques using clinical data such as chest X-rays have been used to predict which patients are most at risk of deterioration. We consider the task of predicting two types of patient deterioration based on chest X-rays: adverse event deterioration (i.e., transfer to the intensive care unit, intubation, or mortality) and increased oxygen requirements beyond 6 L per day. Due to the relative scarcity of COVID-19 patient data, existing solutions leverage supervised pretraining on related non-COVID images, but this is limited by the differences between the pretraining data and the target COVID-19 patient data. In this paper, we use self-supervised learning based on the momentum contrast (MoCo) method in the pretraining phase to learn more general image representations to use for downstream tasks. We present three results. The first is deterioration prediction from a single image, where our model achieves an area under receiver operating characteristic curve (AUC) of 0.742 for predicting an adverse event within 96 hours (compared to 0.703 with supervised pretraining) and an AUC of 0.765 for predicting oxygen requirements greater than 6 L a day at 24 hours (compared to 0.749 with supervised pretraining). We then propose a new transformer-based architecture that can process sequences of multiple images for prediction and show that this model can achieve an improved AUC of 0.786 for predicting an adverse event at 96 hours and an AUC of 0.848 for predicting mortalities at 96 hours. A small pilot clinical study suggested that the prediction accuracy of our model is comparable to that of experienced radiologists analyzing the same information.
RESUMO
COVID-19 is a major, urgent, and ongoing threat to global health. Globally more than 24 million have been infected and the disease has claimed more than a million lives as of November 2020. Predicting which patients will need respiratory support is important to guiding individual patient treatment and also to ensuring sufficient resources are available. The ability of six common Early Warning Scores (EWS) to identify respiratory deterioration defined as the need for advanced respiratory support (high-flow nasal oxygen, continuous positive airways pressure, non-invasive ventilation, intubation) within a prediction window of 24 h is evaluated. It is shown that these scores perform sub-optimally at this specific task. Therefore, an alternative EWS based on the Gradient Boosting Trees (GBT) algorithm is developed that is able to predict deterioration within the next 24 h with high AUROC 94% and an accuracy, sensitivity, and specificity of 70%, 96%, 70%, respectively. The GBT model outperformed the best EWS (LDTEWS:NEWS), increasing the AUROC by 14%. Our GBT model makes the prediction based on the current and baseline measures of routinely available vital signs and blood tests.
RESUMO
During the coronavirus disease 2019 (COVID-19) pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3661 patients, achieves an area under the receiver operating characteristic curve (AUC) of 0.786 (95% CI: 0.745-0.830) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.
RESUMO
Though consistently shown to detect mammographically occult cancers, breast ultrasound has been noted to have high false-positive rates. In this work, we present an AI system that achieves radiologist-level accuracy in identifying breast cancer in ultrasound images. Developed on 288,767 exams, consisting of 5,442,907 B-mode and Color Doppler images, the AI achieves an area under the receiver operating characteristic curve (AUROC) of 0.976 on a test set consisting of 44,755 exams. In a retrospective reader study, the AI achieves a higher AUROC than the average of ten board-certified breast radiologists (AUROC: 0.962 AI, 0.924 ± 0.02 radiologists). With the help of the AI, radiologists decrease their false positive rates by 37.3% and reduce requested biopsies by 27.8%, while maintaining the same level of sensitivity. This highlights the potential of AI in improving the accuracy, consistency, and efficiency of breast ultrasound diagnosis.
Assuntos
Algoritmos , Inteligência Artificial , Neoplasias da Mama/diagnóstico por imagem , Mama/diagnóstico por imagem , Detecção Precoce de Câncer , Ultrassonografia/métodos , Adulto , Idoso , Neoplasias da Mama/diagnóstico , Feminino , Humanos , Mamografia/métodos , Pessoa de Meia-Idade , Curva ROC , Radiologistas/estatística & dados numéricos , Reprodutibilidade dos Testes , Estudos RetrospectivosRESUMO
Assessment of physiological instability preceding adverse events on hospital wards has been previously investigated through clinical early warning score systems. Early warning scores are simple to use yet they consider data as independent and identically distributed random variables. Deep learning applications are able to learn from sequential data, however they lack interpretability and are thus difficult to deploy in clinical settings. We propose the 'Deep Early Warning System' (DEWS), an interpretable end-to-end deep learning model that interpolates temporal data and predicts the probability of an adverse event, defined as the composite outcome of cardiac arrest, mortality or unplanned ICU admission. The model was developed and validated using routinely collected vital signs of patients admitted to the the Oxford University Hospitals between 21st March 2014 and 31st March 2018. We extracted 45 314 vital-sign measurements as a balanced training set and 359 481 vital-sign measurements as an imbalanced testing set to mimic a real-life setting of emergency admissions. DEWS achieved superior accuracy than the state-of-the-art that is currently implemented in clinical settings, the National Early Warning Score, in terms of the overall area under the receiver operating characteristic curve (AUROC) (0.880 vs. 0.866) and when evaluated independently for each of the three outcomes. Our attention-based architecture was able to recognize 'historical' trends in the data that are most correlated with the predicted probability. With high sensitivity, improved clinical utility and increased interpretability, our model can be easily deployed in clinical settings to supplement existing EWS systems.
Assuntos
Deterioração Clínica , Aprendizado Profundo , Escore de Alerta Precoce , Hospitalização , Humanos , Unidades de Terapia Intensiva , ProbabilidadeRESUMO
OBJECTIVES: National guidelines for identifying physiological deterioration and sepsis in hospitals depend on thresholds for blood pressure that do not account for age or sex. In populations outside hospital, differences in blood pressure are known to occur with both variables. Whether these differences remain in the hospitalised population is unknown. This database analysis study aims to generate representative centiles to quantify variations in blood pressure by age and sex in hospitalised patients. DESIGN: Retrospective cross-sectional observational database analysis. SETTING: Four near-sea-level hospitals between April 2015 and April 2017 PARTICIPANTS: 75 342 adult patients who were admitted to the hospitals and had at least one set of documented vital sign observations within 24 hours before discharge were eligible for inclusion. Patients were excluded if they died in hospital, had no vital signs 24 hours prior to discharge, were readmitted within 7 days of discharge, had missing age or sex or had no blood pressure recorded. RESULTS: Systolic blood pressure (SBP) for hospitalised patients increases with age for both sexes. Median SBP increases from 122 (CI: 121.1 to 122.1) mm Hg to 132 (CI: 130.9 to 132.2) mm Hg in men, and 114 (CI: 113.1 to 114.4) mm Hg to 135 (CI: 134.5 to 136.2) mm Hg in women, between the ages of 20 and 90 years. Diastolic blood pressure peaked around 50 years for men 76 (CI: 75.5 to 75.9) mm Hg and women 69 (CI: 69.0 to 69.4) mm Hg. The blood pressure criterion for sepsis, systolic <100 mm Hg, was met by 2.3% of younger (20-30 years) men and 3.5% of older men (81-90 years). In comparison, the criterion was met by 9.7% of younger women and 2.6% of older women. CONCLUSION: We have quantified variations in blood pressure by age and sex in hospitalised patients that have implications for recognition of deterioration. Nearly 10% of younger women met the blood pressure criterion for sepsis at hospital discharge.
Assuntos
Pressão Sanguínea/fisiologia , Adulto , Fatores Etários , Idoso , Idoso de 80 Anos ou mais , Estudos Transversais , Inglaterra , Feminino , Hospitalização , Humanos , Masculino , Pessoa de Meia-Idade , Estudos Retrospectivos , Fatores SexuaisRESUMO
During the coronavirus disease 2019 (COVID-19) pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3,661 patients, achieves an area under the receiver operating characteristic curve (AUC) of 0.786 (95% CI: 0.745-0.830) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.
RESUMO
OBJECTIVES: Early warning scores (EWS) alerting for in-hospital deterioration are commonly developed using routinely collected vital-sign data from the whole in-hospital population. As these in-hospital populations are dominated by those over the age of 45 years, resultant scores may perform less well in younger age groups. We developed and validated an age-specific early warning score (ASEWS) derived from statistical distributions of vital signs. DESIGN: Observational cohort study. SETTING: Oxford University Hospitals (OUH) July 2013 to March 2018 and Portsmouth Hospitals (PH) NHS Trust January 2010 to March 2017 within the Hospital Alerting Via Electronic Noticeboard database. PARTICIPANTS: Hospitalised patients with electronically documented vital-sign observations OUTCOME: Composite outcome of unplanned intensive care unit admission, mortality and cardiac arrest. METHODS AND RESULTS: Statistical distributions of vital signs were used to develop an ASEWS to predict the composite outcome within 24 hours. The OUH development set consisted of 2 538 099 vital-sign observation sets from 142 806 admissions (mean age (SD): 59.8 (20.3)). We compared the performance of ASEWS to the National Early Warning Score (NEWS) and our previous EWS (MCEWS) on an OUH validation set consisting of 581 571 observation sets from 25 407 emergency admissions (mean age (SD): 63.0 (21.4)) and a PH validation set consisting of 5 865 997 observation sets from 233 632 emergency admissions (mean age (SD): 64.3 (21.1)). ASEWS performed better in the 16-45 years age group in the OUH validation set (AUROC 0.820 (95% CI 0.815 to 0.824)) and PH validation set (AUROC 0.840 (95% CI 0.839 to 0.841)) than NEWS (AUROC 0.763 (95% CI 0.758 to 0.768) and AUROC 0.836 (95% CI 0.835 to 0.838) respectively) and MCEWS (AUROC 0.808 (95% CI 0.803 to 0.812) and AUROC 0.833 (95% CI 0.831 to 0.834) respectively). Differences in performance were not consistent in the elder age group. CONCLUSIONS: Accounting for age-related vital sign changes can more accurately detect deterioration in younger patients.
Assuntos
Escore de Alerta Precoce , Parada Cardíaca/mortalidade , Mortalidade Hospitalar , Hospitalização/estatística & dados numéricos , Unidades de Terapia Intensiva , Sinais Vitais , Idoso , Estudos de Coortes , Bases de Dados Factuais , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Curva ROC , Medição de Risco , Reino UnidoRESUMO
Sonoporation has been associated with drug delivery across cell membranes and into target cells, yet several limitations have prohibited further advancement of this technology. Higher delivery rates were associated with increased cellular death, thus implying a safety-efficacy trade-off. Meanwhile, there has been no reported study of safe in vitro sonoporation in a physiologically relevant flow environment. The objective of our study was not only to evaluate sonoporation under physiologically relevant flow conditions, such as fluid velocity, shear stress and temperature, but also to design ultrasound parameters that exploit the presence of flow to maximize sonoporation efficacy while minimizing or avoiding cellular damage. Human umbilical vein endothelial cells (EA.hy926) were seeded in flow chambers as a monolayer to mimic the endothelium. A peristaltic pump maintained a constant fluid velocity of 12.5 cm/s. A focused 0.5 MHz transducer was used to sonicate the cells, while an inserted focused 7.5 MHz passive cavitation detector monitored microbubble-seeded cavitation emissions. Under these conditions, propidium iodide, which is normally impermeable to the cell membrane, was traced to determine whether it could enter cells after sonication. Meanwhile, calcein-AM was used as a cell viability marker. A range of focused ultrasound parameters was explored, with several unique bioeffects observed: cell detachment, preservation of cell viability with no membrane penetration, cell death and preservation of cell viability with sonoporation. The parameters were then modified further to produce safe sonoporation with minimal cell death. To increase the number of favourable cavitation events, we lowered the ultrasound exposure pressure to 40 kPapk-neg and increased the number of cavitation nuclei by 50 times to produce a trans-membrane delivery rate of 62.6% ± 4.3% with a cell viability of 95% ± 4.2%. Furthermore, acoustic cavitation analysis showed that the low pressure sonication produced stable and non-inertial cavitation throughout the pulse sequence. To our knowledge, this is the first study to demonstrate a high drug delivery rate coupled with high cell viability in a physiologically relevant in vitro flow system.