Piyush Mathur

Cleveland Clinic · Department of General Anesthesiology

The rapid and nimble growth of artificial intelligence (AI) in healthcare has generated significant excitement among healthcare professionals. The most common question asked by clinicians about AI therefore is: “How do I get started?”. We outline a strategic approach for clinicians to integrate AI into their knowledge base, focusing on goal setting...

BACKGROUND The majority of published research suggests that anesthesia handovers during major surgical procedures are associated with unintended harmful consequences. It is still unclear if the number or quality of the transition of care is the main driver of the adverse outcomes. There is even less data if the timing of the anesthesiologist handov...

Background: The infodemic we are experiencing with AI related publications in healthcare is unparalleled. The excitement and fear surrounding the adoption of rapidly evolving AI in healthcare applications pose a real challenge. Collaborative learning from published research is one of the best ways to understand the associated opportunities and chal...

Large language models (LLMs) have caught the imagination of researchers,developers and public in general the world over with their potential for transformation. Vast amounts of research and development resources are being provided to implement these models in all facets of life. Trained using billions of parameters, various measures of their accura...

COVID-19 pandemic has taught us many lessons, including the need to manage the exponential growth of knowledge, fast-paced development or modification of existing AI models, limited opportunities to conduct extensive validation studies, the need to understand bias and mitigate it, and lastly, implementation challenges related to AI in healthcare. W...

The adoption of artificial intelligence (AI) algorithms is rapidly increasing in healthcare. Such algorithms may be shaped by various factors such as social determinants of health that can influence health outcomes. While AI algorithms have been proposed as a tool to expand the reach of quality healthcare to underserved communities and improve heal...

The purpose of this review is to provide a comprehensive review of publications related to artificial intelligence (AI) applications in healthcare for the year 2022. With an exponentially increasing number of publications related to AI in healthcare,there is a need to have a curated,timely and data driven review. This year's review provides a compr...

Unlabelled: Guidewire retention after intravascular catheter insertion is considered a "never event." Prior reports attribute this complication to various characteristics including uncooperative patients, operator inexperience, off-hour or emergent insertion, and underutilization of ultrasound guidance. In this descriptive analysis of consecutive...

Background: An ever increasing number of artificial intelligence (AI) models targeting healthcare applications are developed and published every day, but their use in real world decision making is limited. Beyond a quantitative assessment, it is important to have qualitative evaluation of the maturity of these publications with additional details r...

Objective Shock Index (SI) is widely used for prognosticating outcomes in ICU and emergency settings. We aimed to create a multi-modal early warning system (EWS) for development of abnormal shock index using routinely available vitals and clinical notes. Material and Methods 17,294 ICU-stays in MIMIC-III data were scored for SI. A new episode of a...

T he prospect of improved clinical outcomes and more efficient health systems has fueled a rapid rise in the development and evaluation of AI systems over the last decade. Because most AI systems within healthcare are complex interventions designed as clinical decision support systems, rather than autonomous agents, the interactions among the AI sy...

Introduction Postoperative respiratory failure (PRF) contributes significantly to morbidity and mortality. We sought to identify patient characteristics and perioperative risk factors associated with PRF in patients undergoing elective abdominal surgery to improve patient outcomes. Methods We retrospectively reviewed patients undergoing elective a...

A growing number of artificial intelligence (AI)-based clinical decision support systems are showing promising performance in preclinical, in silico, evaluation, but few have yet demonstrated real benefit to patient care. Early stage clinical evaluation is important to assess an AI system’s actual clinical performance at small scale, ensure its saf...

Introduction: Guidewire retention after intravascular catheter insertion is considered a “never event.” Prior reports attribute this complication to various characteristics including uncooperative patients, operator inexperience, off-hour or emergent insertion, and underutilization of ultrasound guidance. In this descriptive analysis of consecutive...

A growing number of artificial intelligence (AI)-based clinical decision support systems are showing promising performance in preclinical, in silico evaluation, but few have yet demonstrated real benefit to patient care. Early-stage clinical evaluation is important to assess an AI system's actual clinical performance at small scale, ensure its safe...

A review of over 4000+ articles published in 2021 related to artificial intelligence in healthcare.A BrainX Community exclusive, annual publication which has trends, specialist editorials and categorized references readily available to provide insights into related 2021 publications. Cite as: Mathur P, Mishra S, Awasthi R, Cywinski J, et al. (2022...

The anesthesiologist's role has expanded beyond the operating room, and anesthesiologist-led care teams can deliver coordinated care that spans the entire surgical experience, from preoperative optimization to long-term recovery of surgical patients. This expanded role can help reduce postoperative morbidity and mortality, which are regrettably com...

Question answering (QA) is one of the oldest research areas of AI and Compu- national Linguistics. QA has seen significant progress with the development of state-of-the-art models and benchmark datasets over the last few years. However, pre-trained QA models perform poorly for clinical QA tasks, presumably due to the complexity of electronic health...

Objectives: To date, many artificial intelligence (AI) systems have been developed in healthcare, but adoption has been limited. This may be due to inappropriate or incomplete evaluation and a lack of internationally recognised AI standards on evaluation. To have confidence in the generalisability of AI systems in healthcare and to enable their in...

Background Quality improvement in healthcare is limited by both the quality and quantity of data available in the electronic health records or self reported by clinicians. Appropriate and timely reporting can help identify opportunities for quality improvement and deployment of mitigation steps but many of these process remain manual. Negative pati...

A review of Artificial Intelligence in Healthcare publications for the year 2020. Overall, 3000+ references classified based various healthcare specialities with abstracts from leading clinician specialists.Reviews year over year trends for the last 3 years related to this field.

Albumin continues to be one of the options for colloid resuscitation in critically ill patients despite limited evidence for its use. It does seem to have an advantage over other colloids with a better side-effect profile. With it’s ability to increase intravascular oncotic pressure and other postulated metabolic benefits, albumin is preferred by m...

Septic shock represents a profound systemic inflammatory derangement with components of functional hypovolemia, altered oxygen delivery, myocardial dysfunction, peripheral vasoplegia, and diffuse capillary leak. In this case scenario, a patient exhibits all of the aforementioned findings with lactic acidosis, elevated troponin, persistent hypotensi...

Artificial Intelligence is an evolving area of computational science with increasing research and real-world applications in healthcare. In the perioperative patient population, increased use of AI is being found to improve quality of care and prevention of adverse events. One such area relates to prevention of hypotension and management of systemi...

In response to the COVID-19 pandemic, quality improvement teams at Cleveland Clinic initiated a number of measures to guide the care of patients with suspected or confirmed COVID-19 infection and protect care givers. This included increasing the frequency of team meetings from monthly to daily or weekly and creating task forces to create protocols...

Background COVID-19 is now one of the leading causes of mortality amongst adults in the United States for the year 2020. Multiple epidemiological models have been built, often based on limited data, to understand the spread and impact of the pandemic. However, many geographic and local factors may have played an important role in higher morbidity a...

The operating room environment is very dynamic with many unique challenges for anesthesia teams caring for patients with confirmed or suspected COVID-19. Specific recommendations by national organizations and institution specific step-by-step guidelines and education materials are required to maintain safety for both patients and caregivers periope...

UNSTRUCTURED Introduction The COVID-19 pandemic exhibits an uneven geographic spread which leads to a locational mismatch of testing, mitigation measures and allocation of healthcare resources (human, equipment, and infrastructure).(1) In the absence of effective treatment, understanding and predicting the spread of COVID-19 is unquestionably valua...

We present a synopsis of publications focused on machine learning (ML) or artificial intelligence (AI) applications in healthcare for the year 2019. We appreciate the work of researchers and authors who have contributed significantly to the advancement of science in this area.

Standardized clinical pathways are useful tool to reduce variation in clinical management and may improve quality of care. However the evidence supporting a specific clinical pathway for a patient or patient population is often imperfect limiting adoption and efficacy of clinical pathway. Machine intelligence can potentially identify clinical varia...

This study presents a multimodal machine learning model to predict ICD-10 diagnostic codes. We developed separate machine learning models that can handle data from different modalities, including unstructured text, semi-structured text and structured tabular data. We further employed an ensemble method to integrate all modality-specific models to g...

Non-physician advanced practice providers (APPs) such as nurse practitioners and physician assistants are being increasingly utilized as critical care providers in the United States. The objectives of this study were to determine the utilization of APPs in the intensive care units (ICU)s of academic medical centers (AMCs) and to assess the percepti...

Mechanical ventilation is required frequently for patients with neurologic disorders for airway protection, pulmonary insufficiency, or management of intracranial pressure. Patients with neurologic disease are prone to hypoventilation, hypoxia, aspiration, atelectasis, and lung collapse. This chapter presents a case study of a 55-year-old female wi...

The major factors in predicting neurologic dysfunction secondary to cardiac arrest involve the extent of brain insult as a function of time to return of circulation. The use of induced hypothermia has been studied as a way to combat neurologic injury for nearly five decades. This chapter presents a case study of a 37-year-old female with a history...

A circadian variation of the onset of almost all ischaemic heart disease (IHD) manifestations with an increased incidence between 6:00 a.m. to 12:00 noon has been reported in several publications during the last decade. This study included 605 patients of various IHD subgroups, i.e., acute Q-wave myocardial infarction (n = 174), unstable angina (n...