Category: Blog

Featuring healthcare industry experts, the program will show how critical care units are using AI-Machine Learning to deliver true patient value

An upcoming episode of the award-winning program “Information Matrix” hosted by successful actor and philanthropist Laurence Fishburne, will feature new content on the use of AI-Machine Learning in the treatment of critically ill patients.

In recent years, healthcare providers have made massive investments in electronic medical records. These databases hold vital information that can be used to improve patient outcomes and lower costs, yet their complexity and sheer volume makes them unusable for clinicians. Nowhere is this need more pressing than in the understaffed critical care units, where every second counts.

New AI-Machine Learning tools being developed by Israeli startup CLEW – are converting this data to life-saving medical knowledge that can be used to reduce costs and improve outcomes.

One of earliest adopters of AI-Machine Learning technology are TeleICUs – centralized care teams that manage large numbers of geographically dispersed ICU locations. Having delivered significant improvements in patient care over the past two decades, the TeleICU care model requires new advanced technologies to identify high-risk patients or physiological instability in time for early intervention to prevent a critical event or deterioration.

With the optimal integration of CLEW’s machine learning predictive technology in TeleICUs, clinicians can benefit from proactive, predictive assessment, a more collaborative team approach and efficient clinical resource allocation.

“Information Matrix,” hosted by Laurence Fishburne, is a program tackling stories and concepts that are influencing our modern-day society. Each episode breaks down things happening in today’s society, culture, and business through a long-form documentary presentation. Shared by a diverse audience, “Information Matrix” is a leading television series focusing on society, education, and industries.

Acuity is a general reference to the level of care required by a patient, and not the unit or department in which the patient is being treated. The level of care can be a function of the personnel resources (medical or nursing) required, the extent of patient monitoring necessary or budgetary resources allocated to the specific patient.

Generally speaking, up to 40% of all patient admissions involve some form of high acuity care. High acuity care patients often present with various acute life threatening conditions. Typically one thinks of high-acuity as being limited to adult, pediatric or neo-natal patients in ICU or critical care units, however, high acuity also includes patients in surgical units, post-anesthesia care units (PACU) and progressive care units (also termed step-down, telemetry, intermediate care, and transitional care).

One major aspect of high acuity care is the use of multi-parameter patient monitoring systems. These monitors provide a comprehensive set of clinical parameters, and assist physicians and medical personnel in monitoring the patient’s health and progress during treatment.

During high acuity care, the continuous monitoring results in the accumulation of vast amounts of multidimensional data. However, sufficient automated advanced processing solutions are not in place to take full advantage of these data stores. Without predictive analytics, floor management and discharge decisions are determined based on the patient’s current state of health – decisions which may not be optimal for either the healthcare facility or the patient.

High velocity and large volumes of patient data provide a unique opportunity to detect and predict life treating complications. The sheer quantity of data, coupled with limited critical care resources, makes data exploitation almost impossible. Yet this data holds the key to a myriad of clinical and resource allocation decisions.

Analytical tools can exploit this data to provide operational, financial and clinical benefits to all layers of high acuity management and staff. These platforms can harness the vast amount of available data to deliver highly accurate predictive clinical analytics that provide hospital management and medical personnel with the preemptive information they require to better manage their resources.

Correctly integrated into the clinical workflow, such platforms will deliver massive benefits, reducing the length of stay, lowering treatment costs and freeing up revenue-producing high acuity beds for other patients. Most importantly, these platforms can provide indications of life threatening complications. Without predictive analytics, floor management and discharge decisions are determined based on patients’ current state of health – decisions which may not be optimal for either the healthcare facility or the patient.

In short, YES, predictive analytics can indeed save lives.

The CLEW (previously known as Intensix) platform utilizes innovative prediction models derived from Big Data analysis and advanced high-dimensional analytics techniques. Deployed as a standalone app or integrated into an existing solution, the platform continuously processes a wide range of clinical data, including the patient’s medical background from the EHR, prior hospitalizations, vital signs, laboratory results, medications, procedures, etc. CLEW’s analytics engine identifies relationships between real-time physiological data and latent medical conditions, which is vital for the predictive early warnings generated by the system. The analytical engine identifies changes in the patient’s condition in real-time and indicates the possibility for life-threatening situations.

The sounds made by the heart and lungs provide important diagnostic information during an examination. Before the invention of the stethoscope, auscultation – the action of listening to sounds from the heart, lungs, or other organs – was performed by physicians by placing their ear directly on the patient.

In the early 1800’s, a French doctor, René Laënnec, felt it was inappropriate to rest his ear against the chest of the young female patient complaining of heart problems. Revered as an excellent student, the young doctor rolled a piece of paper into a tube and pressed it to her chest. To his surprised, he was able hear the sounds of her heart more clearly and distinctly than had he placed his ear to her chest.

In his preface to the classic treatise De l’Auscultation Médiate, published in August 1819, Dr. Laënnec wrote, “I happened to recollect a simple and well-known fact in acoustics, … the great distinctness with which we hear the scratch of a pin at one end of a piece of wood on applying our ear to the other. Immediately, on this suggestion, I rolled a quire of paper into a kind of cylinder and applied one end of it to the region of the heart and the other to my ear, and was not a little surprised and pleased to find that I could thereby perceive the action of the heart in a manner much more clear and distinct than I had ever been able to do by the immediate application of my ear.”

Fast forward almost 200 years. Patient monitoring has evolved to such a degree that the typical high-acuity patient is connected to multiple monitoring devices, generating innumerable data points per second. Add to this the lab results and physician’s notes and a treasure chest of information that holds valuable information about the patients’ health is created. Unfortunately, the quantity of the data has far outstripped the physician’s ability to process it.

Predictive analytics holds the key to unlocking this immense data. By analyzing high-volume and high-velocity data in real-time, predictive analytics can identify patterns in physiological data that predict a deterioration in the patient’s condition. Ultimately, predictive analytics enables physicians to intervene in a timely manner, significantly improving the clinical outcome and substantially reducing the cost of treatment.

CLEW (previously known as Intensix) is excited to participate in HIMSS 2017, perhaps the most important industry event on the healthcare IT calendar. At the show CLEW will be exhibiting its lifesaving predictive analytics solution for high acuity care. CLEW’s booth is located at the Innovation Zone, (#7785). Machine learning is playing an increasingly important role in high acuity care. The ability to analyze massive amounts of high velocity data combined with advanced modelling significantly improves detection and prediction. Already validated in several studies, CLEW is actively seeking to partner with healthcare IT and medical device vendors to deliver patient-level detection and prediction.

We are also very much looking forward to a presentation by Dr. Mohamed Seisa, a Postdoctoral Research Fellow in Anesthesia at Mayo Clinic. Dr. Seisa’s presentation entitled – Improving Sepsis Prediction by Developing Advanced Model – will showcase the results of real-time validation of CLEW’s platform conducted by Mayo Clinic in a MICU. Additional information about the Mayo Clinic presentation can be found here: http://www.himssconference.org/session/improving-sepsis-prediction-developing-advanced-model

We recently announced the closing of a Series A financing round. The funds will be used to grow our operational and sales footprint in North America and to accelerate the development of our predictive analytics platform.

The round was led by Pitango Venture Capital, and the fund’s Managing General Partner Ittai Harel, is joining the company company’s Board of Directors.

Our platform uses predictive analytics and machine learning for the early detection of life-threatening complications in critical care. We provide accurate predictive clinical analytics that staff and management can use to avoid deteriorations, save lives as well as lock-in operational and financial benefits.

Studies like the one recently announced at HIMSS to date show that the CLEW (previously known as Intensix)solution has the potential to significantly improve clinical outcomes and reduce the average length of hospital stay.

We just returned from an action packed HIMSS, a great opportunity to meet with industry leaders and partners. Earlier we announced a presentation entitled Improving Sepsis Prediction by Developing Advanced Model, showcasing the positive results of real-time validation of CLEW (previously known as Intensix) platform conducted by Mayo Clinic in a MICU.

The study was conducted by Brian Pickering M.D. and Vitaly Herasevich M.D., of the Mayo Clinic’s Multidisciplinary Epidemiology Translational Research Intensive Care (METRIC) Group. It included 782 patients, with a median age of 65 years. Median ICU length of stay was 35.5 hours.

The CLEW platform showed a sensitivity of 90.5% and specificity of 88.5%. The Positive Predictive Value of the CLEW system was 71.5%. The Negative Predictive Value of the system was 96.7%.

The poster can be downloaded here

Serial entrepreneur Gal Salomon to share how data is changing healthcare today

Gal will be a featured speaker at the Imec Technology Forum (ITF) at the David InterContinental, Tel Aviv, on March 8, 2017. His presentation, entitled Predictive Critical Care: Using Big Data in Healthcare, will address the use of analytics for the early detection of life threatening patient deterioration in the ICU and high acuity departments. In addition, Gal will share the lessons learned in previous startups and in the venture capital industry, and explain how they are being applied today.

Gal is one of Israel’s best known serial entrepreneurs, having repeatedly shepherded technology from the concept phase to mass deployment, and successfully guided companies from the seed stage through M&A with large multi-nationals. He is the founder of Sansa Security (formerly Discretix), where he served as CEO until he joined Pitango Venture Capital as a Venture Partner. During this time, he also continued as the active Chairman at Discretix, until it was acquired by ARM in 2015. Prior to founding Discretix, he served in multiple positions at DSP Communications and at Intel.

The Imec Technology Forum (ITF) is an initiative of Imec, the world-leading R&D and innovation hub in nanoelectronics and digital technology. Committed to drive disruptive innovation, Imec leverages the expertise of nearly 3,500 top scientists and engineers, as well as a partner network including the world’s leading companies in ICT, communication and healthcare.

Dr. Itai Pessach, Medical Director at CLEW (previously known as Intensix) presented at Big Data in Healthcare event, hosted by the Israeli Association for Medical Informatics (ILAMI).

Dr. Pessach is an assistant Professor of pediatrics at the Tel-Aviv University and a senior pediatric critical care physician at Sheba Medical Center. He is certified in allergy immunology and in pediatric critical care. He has a broad background in basic and clinical research and has published extensively in the fields of pediatric immunology and critical care. Dr. Pessach holds an MD, PhD degree from the Ben-Gurion University and has trained both at Sheba medical center as well as at Children’s Hospital Boston, Harvard Medical School.

ILAMI was founded in 1984 with approximately 600 members from all aspects of the Healthcare and Medical Informatics community in Israel. The association aims to promote information exchange concerning the development and the use of Information Systems in the Israeli Health Care System. ILAMI covers all aspects of Healthcare Information Technology with a focus on what works in Israel. This includes, information technology, digital health, eHealth, mHealth, national programs and initiatives, the integration of medicine and IT, clinical applications, information security, medical devices and their connection to IT.

For more information about the event can be found here: https://www.meetup.com/ILAMI-Israel-Association-of-Medical-Informatics-Meetup/events/237396113/

On May 19-24, 2017, Dr. Itai Pessach, Medical Director of CLEW (previously known as Intensix), will be at the American Thoracic Society’s Conference in Washington DC to present the company’s latest results in the development of prediction models for early detection of significant deterioration events.

The study focuses on Inensix’s use of machine learning algorithms combined with processing and analysis of large quantities of data automatically acquired in real-time from the electronic medical record (EMR). This tool alerts the physician that life-threatening events – such as sepsis, shock and respiratory failure – are in progress, leading to the rapid initiation of appropriate care. Interventions at this level reduce morbidity, mortality and length of stay in the Intensive Care Unit (ICU).

Dr. Pessach is an assistant Professor of pediatrics at the Tel-Aviv University and a senior pediatric critical care physician at Sheba Medical Center. He is certified in allergy immunology and in pediatric critical care. He has a broad background in basic and clinical research and has published extensively in the fields of pediatric immunology and critical care. Dr. Pessach holds an MD, PhD degree from the Ben-Gurion University and has trained both at Sheba medical center as well as at Children’s Hospital Boston, Harvard Medical School.