Israreli big data and intensive care analytics startup Intensix has announced a research collaboration with Sourasky Medical Center (Ichilov) in Tel Aviv.
The Herzliya based company has developed an analytic engine to improve critical decision making in intensive care units. The collaboration is for the development of a ground-breaking system to enable the early detection of complications or deterioration for patients hospitalized in intensive care units, in order to assist the staff in making effective treatment decisions at the very early stages - long before patients start to deteriorate.
As part of the collaboration, Intensix will conduct extensive research based on data of approximately 8,000 anonymous patients hospitalized in the ICU at the Tel Aviv Sourasky Medical Center between 2007 and 2014. The company has installed an innovative system at the hospital to alert the clinicians and notify them of possible life-threating complications for patients admitted for critical care.
Anonymized data obtained from the ICU at Tel Aviv Sourasky Medical Center was transferred to the Intensix database. The data was then cleaned, filtered and analyzed using advanced mathematical algorithms to create models for early predictions of deterioration and/or complications for patients in the ICU. Accurate models for predicting the clinical outcomes will enable the medical staff to improve care and provide tailored treatment to each patient based on their individual needs. This capability is absolutely vital in intensive care units. Early detection, even within hours of possible complications, can actually save the patient from death and significantly reduce morbidity that could influence the clinical outcome of the patient long after they are discharged from the ICU. Among others, these complications include: sepsis, physical shock, respiratory failure, as well as cardiac or renal and systemic failure ‒ all of which could result in serious disability or death. In the coming weeks, the system installed at the hospital by Intensix will commence its second phase of prospective study. During this phase, the system will analyze real-time data streams emerging from the medical bedside devices and the electronic health record in order to provide immediate insights regarding the patient's condition. In the first stage, the system will provide quiet alerts to calibrate the models, and during the second stage, the system will be installed at the bedside in order to provide real-time alerts to the clinical team.
Prof. Idit Matot, Head of the Anesthesia, Pain & Intensive Care Division at the Tel Aviv Sourasky Medical Center said, "Patients in intensive care units are the most complex, and therefore they are the most actively monitored in the hospital. A system that recognizes the development of complications or deterioration, hours before they occur, will enable effective assessments and early treatment that will actually reduce mortality and morbidity. A classic example is in the development of sepsis, where taking a culture, and subsequently providing antibiotics and liquids at the critical early stages, will effectively save lives. In addition, and equally essential in such a prediction system, is the ability to identify patients that are not likely to deteriorate. This feature of the system eliminates the need for costly and time-consuming unnecessary tests, treatments, and days of hospitalization in the intensive care unit. Extensive information is collected on patients in the intensive care unit and the nursing staff is required to perform unrealistic tasks. There is an unrealistic need to simultaneously analyze all of the information, process monitored data that is not necessarily available in real-time (e.g., laboratory tests or images), follow changes in treatment suggested by other nurses or doctors (a change in the provision of drugs, a ventilator, etc.) and subsequently integrate all of this critical information. The staff is then required to base their decision of continued treatment on an analysis of the aggregated data. Moreover, these decisions must be made in a multi patient-environment while being concurrently engaged with other critical needs in the unit. Existing monitoring systems are unable to analyze and notify doctors on cross-link data between parameters or report actively on trends. In the world of big data, it is our responsibility to take advantage of the numerous data points collected by the monitoring systems in order to decide which of the patients should be treated “aggressively” in order to determine an accurate diagnosis, and when this treatment can be avoided.”
Intensix VP Business Development Izik Itzhakov said, "More than 5 million patients are hospitalized in intensive care units in the US annually, and up to approximately 30% of these patients will not survive. Early diagnosis enables the improvement of quality care, the increase in efficiency that could translate to reduction in morbidity and mortality, the earlier release of patients, and most significantly, the minimization of long-term damages that may affect patients long after they are discharged."
It is estimated that in the US alone, annual expenditure on critical care is $290 billion. Although the number of beds in intensive care units is approximately 10% of the hospital beds, critical care actually represents 30% of the hospital cost.
Intensix was established in 2015 by co-founder Gal Salomon, who served as a venture partner at Pitango Venture Capital and founded several technology companies including Discretix, recently sold for approximately - $90 million, together with Avigdor Faians, who held a number of management positions in development and architecture in the semiconductor sector and served as CTO of Mindspeed.
The Intensix mission is to provide healthcare providers and administrators with high-accuracy predictive clinical analytics that improve clinical outcomes and reduce hospital costs. Their innovative analytics engine detects deterioration in real-time and delivers predictive warnings during all phases of a patient’s ICU stay. Driven by innovative prediction models derived from Big Data analysis and an advanced high-dimensional analytics technique, the Intensix predictive platform has the flexibility to manage large patient populations without losing individualized treatment needs. The Intensix team represents decades of success in assisting healthcare institutions and other enterprises achieve their goals by exploiting breakthrough research and technologies.
Published by Globes [online], Israel business news - www.globes-online.com - on February 15, 2016
© Copyright of Globes Publisher Itonut (1983) Ltd. 2016