Braunschweig Municipal Hospital and Siemens Healthineers are breaking new ground through an innovative medical technology partnership. Together, they have entered into a long-term Asset Management Services (AMS) contract. Braunschweig Municipal Hospital is one of the largest hospitals in northern Germany, with 1,499 beds and 38 clinics and institutes. Siemens Healthineers will assume responsibility for supplying and maintaining all initial and replacement equipment in the areas of radiology, radiotherapy and nuclear medicine. The partnership also includes strategic and operational consulting services to drive continuous improvement initiatives over time. On October 23, in Braunschweig, the parties signed a ten-year contract with a five-year extension option.
“The primary goal of this technology partnership is to assure high-quality and cost-effective medical care for our patients through first-class diagnostic radiological, surgical and radiotherapy services”, explains Ulrich Markurth, mayor of Braunschweig and chairman of the hospital’s supervisory board.
“We are very pleased to be able to contribute as a technology partner in the coming years to further improve the quality of patient care at the Braunschweig Municipal Hospital and its performance capability,” says Dr. Stefan Schaller, head of Siemens Healthineers in Germany. “In addition to the provision of innovative medical technology systems, we support the Braunschweig Municipal Hospital in planning new buildings and optimizing workflows in radiology, cardiology and the emergency department as well as in all steps towards the digitization of healthcare. This holistic package provides the hospital with security of planning, budget certainty and future reliability over the entire duration of the project.”
Matthias Platsch, President of Siemens Healthineers Services adds: “We are delighted to have been chosen as a technology partner for the Braunschweig Municipal Hospital and we are both proud and humbled by the vote of confidence that this important healthcare provider has placed in our new services portfolio. In this, Siemens Healthineers’ first asset management services partnership in Germany, we will combine the strength of our innovative product portfolio with the forward-looking business approach of our enterprise services to help deliver best-value clinical outcomes for patients. Together with the Braunschweig Municipal Hospital, we will transform healthcare delivery by leveraging our combined expertise in established and new care models. With a fresh look at the design and operation of the facility we will significantly improve the patient experience, and the new technologies we will deploy will enable more efficient and more precise clinical diagnosis. We are very excited to play such a role in the future of healthcare in Braunschweig.”
Hospital CEO Dr. Andreas Goepfert explains that the award of the contract for this technology partnership, including the vendor-neutral procurement and management of around 50 new systems (ranging from magnetic resonance and computed tomography, to angiography, X-ray, nuclear medicine and radiotherapy machines) is the result of a Europe-wide call for tenders via an initial selection process and a competitive dialogue. The fundamental premise is that this innovative, end-to-end partnership model – for procurement and management, in particular – will generate savings for the hospital compared to a series of individual, reactive calls for tender.
As a consequence, Siemens Healthineers will be responsible for procurement, installation, maintenance, servicing, an innovation guarantee (through updates and upgrades), and an availability guarantee for all devices. The long-term technology roadmap takes into consideration the hospital’s strategic orientation, especially its current plan to concentrate the hospital at two locations. A Syngo.via Enterprise solution will also give the hospital access to all Siemens Healthineers’ software applications, enabling it to stay at the forefront of digital innovation.
 “The technology partnership in the area of radiology will bring together the heterogeneous imaging device landscape and IT in our radiology department at Braunschweig Municipal Hospital,” forecasts its medical director, Dr. Thomas Bartkiewicz. “That ensures we always stay at the forefront of innovation in diagnostic imaging and imaging-based treatment, while ensuring radiation exposure for patients and employees is kept to a minimum.” Complex interfaces will be removed and the clinical staff will find their day-to-day work routines become noticeably simpler. Nursing director Ulrich Heller adds: “Different operating processes from various device manufacturers will be reduced to a single standardized system.” This will speed up workflows and improve quality of care at the same time. In addition, maintenance plans and contracts that were not previously coordinated will be combined as part of an optimized programme in the future. The result will be a sustainable reduction in maintenance costs.
The ‘Braunschweig Model’ for a technology partnership enables the hospital to respond flexibly to changing requirements and future device needs due to a separate ‘innovation budget’. This includes possible changes in both the scope and the timing of procurement throughout the entire term of the partnership. The fixed quarterly payment fee also provides the hospital with budgetary certainty for the contract duration.
“The technology partnership guarantees predictability of costs whilst providing security of investments in the fields of radiology, radiotherapy and nuclear medicine,” says hospital CEO Goepfert. The long-term technology partnership will enable the hospital to benefit from future technological advances in radiology, including innovative algorithms to improve image reading and computer-assisted diagnostic modules. This will ensure high-quality and cost-effective patient care for the long term.
The AMS also encompasses a number of flagship projects in which the two partners will work closely together in the future. For example, Siemens Healthineers will contribute the know-how in the area of molecular diagnostics built up by its company NEO New Oncology GmbH. Thanks to genome analyses of tumour tissue performed by NEO New Oncology, Braunschweig Municipal Hospital will be able to create customized, targeted treatment recommendations that will facilitate highly promising precision medical treatment for cancer patients. www.siemens.com/healthineers

Using a combination of DNA sequencing and computer science techniques, a team of researchers has developed a new method for monitoring the health of organ transplant patients – one that promises to provide life-saving clues to diagnose organ rejection at an early stage.
More than 180,000 people live with organ transplants in the U.S., and many undergo costly and risky biopsies to determine if their body is accepting or rejecting an organ. An alternate method demonstrated by Iwijn De Vlaminck, who is also a senior author of the current study, found that cell-free DNA (cfDNA), essentially fragments of dead cells derived from an organ, can be detected in a patient’s bloodstream and used as a proxy for the organ’s health. The more cfDNA that is discovered, the greater the likelihood the organ is failing. But without knowing the donor’s DNA – which is often the case – doctors have no reference to identify the cfDNA.
But now a research team from Cornell and Stanford University has demonstrated a method for identifying cfDNA without the donor. To address the issue, Eilon Sharon, postdoctoral researcher with Jonathan Pritchard, and colleagues worked to develop a computer algorithm that estimates the donor-derived cfDNA and can predict heart and lung rejection with an accuracy similar to that in cases where donor information is available. Their work also details a refined algorithm to address closely related recipients and donors, a scenario that is common in bone marrow and kidney transplantations.
The algorithm uses publicly available genotypes and techniques of relationship inference to model which cfDNA fragments are most likely from the organ. "Specifically, the model infers the donor’s most probable ancestral population and accounts for close relationship by detecting DNA segments that are identical due to close descent," said Sharon, adding that the phenomenon is known as "identity by descent."
The findings alleviate a major barrier to using cfDNA detection – also known as genome transplant dynamics – instead of biopsies, and researchers hope the computer science-based method will help save lives. Accurate monitoring of organ health is essential to a patient’s long-term survival; currently, the median life expectancy for a heart transplant patient is around 11 years, and only 5.3 years for recipients of lungs.

EurekAlert
www.eurekalert.org/pub_releases/2017-08/p-nmf072717.php

Fast, accurate and inexpensive medical tests in a doctor’s office are only possible for some conditions. To create new in-office diagnostics for additional diseases, researchers report a new technique that uses ultrasound to concentrate fluorescently-labelled disease biomarkers otherwise impossible to detect with current equipment in an office setting. The markers’ signal could someday be analysed via a smartphone app.
Ultrasound is a safe, non-invasive, inexpensive and portable technique best known for monitoring pregnancies. But these high-frequency acoustic waves can also be used to gently handle blood components, cells and protein crystals at the microscopic level. With an eye toward point-of-care diagnostic applications, Tony Huang, Zhangming Mao and colleagues wanted to harness these sound waves to help detect even smaller particles and biomarkers for diseases such as cancer that often require special laboratory equipment to detect.
The researchers developed an acoustofluidic chip that, though vibrations, can form a streaming vortex inside a tiny glass capillary tube using a minimal amount of energy. Testing showed that the vortex could force nanoparticles ranging in diameter from 80 to 500 nanometers to swirl into the centre of the capillary. The nanoparticles captured biomarkers labelled with a fluorescent tag, concentrating them in the capillary to boost their signal. This increased brightness could make the signal readable with a smartphone camera.

American Chemical Societyhttp://tinyurl.com/yd5ltoul

Continuously recording the brain’s electrical signals and examining how those impulses evolve over time is a more reliable way to identify infants at risk for brain injury, compared with doing snapshot evaluations, according to a prospective cohort study led by Children’s National Health System research-clinicians.
Amplitude-integrated electroencephalogram (aEEG) is a bedside tool that involves attaching tiny electrodes to the newborn’s scalp to permit clinicians to monitor the complex electrical activity of the child’s brain over time. It’s a positive sign when an aEEG shows babies beginning to sleep and wake normally by the time they are 3 days old. Conversely, severely abnormal aEEG readings in the first days of life predict poor outcomes.
The Children’s team used aEEG with infants born with hypoxic-ischemic encephalopathy (HIE), one of the most severe complications that can affect full-term infants. During pregnancy, birth or shortly after birth, a hypoxic-ischemic event can occur that impedes blood flow and oxygen delivery to the brain, resulting in destruction of brain tissue. Cooling (therapeutic hypothermia) is now standard for newborns with HIE in order to stave off life-long consequences, but deaths and neurodevelopmental disability still can occur.
“We know whole-body cooling─or lowering the body’s temperature by about 3 degrees Celsius─can help vulnerable newborns survive and can protect their brains from suffering profound injuries,” says An N. Massaro, M.D., a Children’s National neonatologist and senior author of the study. “What we were trying to determine with this study is whether evaluating the pattern of evolution of the aEEG as a whole provides more information compared with looking at snapshots in time.”
Eighty infants undergoing therapeutic cooling who met the inclusion criteria were enrolled in the five-year study, one of the largest such studies to date. The babies weighed more than 1,800 grams and were older than 35 weeks’ gestational age at birth, and either needed prolonged resuscitation after birth or had low APGAR scores─ a measure of how well newborns fare outside the womb. Continuous recordings of EEG data occurred from the time of admission up to 12 hours after the infants temperatures were raised to normal and aEEG tracings were calculated.
After the therapeutic cooling blankets were removed, the infants underwent at least one magnetic resonance imaging (MRI) scan prior to discharge. During the routine follow-up check at about 18 months of age, the HIE survivors’ cognitive and motor skills were assessed using validated instruments.
Fifty-six of the infants in the study had favourable outcomes. Twenty-four infants had adverse outcomes, including 15 with severe brain injury detected by MRI and nine infants who died. These children had lower APGAR scores at five minutes, and were more likely to have severe HIE and to have experienced more frequent seizures.
“Infants whose aEEG abnormalities do not improve were at increased risk: Infants who do not reach a discontinuous background pattern by 15.5 hours of life, achieve cycling by 45.5 hours after birth and who fail to achieve continuous normal voltage by 78 hours after birth are most at risk for adverse outcomes,” Dr. Massaro says. “In addition to defining worrisome trends, we found that overall assessment of continuous aEEG readings through the course of hypothermia treatment provide the most meaningful predictive power. This means we can speak with families at the bedside with more confidence about their child’s outcomes after the infant undergoes cooling therapy.”
Children’s National Health System
childrensnational.org/news-and-events/childrens-newsroom/2017/continuous-eeg-better-at-identifying-oxygen-deprived-newborns-most-at-risk

Doctors are often deluged by signals from charts, test results, and other metrics to keep track of. It can be difficult to integrate and monitor all of these data for multiple patients while making real-time treatment decisions, especially when data is documented inconsistently across hospitals.
In a new pair of papers, researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) explore ways for computers to help doctors make better medical decisions.
One team created a machine-learning approach called “ICU Intervene” that takes large amounts of intensive-care-unit (ICU) data, from vitals and labs to notes and demographics, to determine what kinds of treatments are needed for different symptoms. The system uses “deep learning” to make real-time predictions, learning from past ICU cases to make suggestions for critical care, while also explaining the reasoning behind these decisions.
“The system could potentially be an aid for doctors in the ICU, which is a high-stress, high-demand environment,” says PhD student Harini Suresh, lead author on the paper about ICU Intervene. “The goal is to leverage data from medical records to improve health care and predict actionable interventions.”
Another team developed an approach called “EHR Model Transfer” that can facilitate the application of predictive models on an electronic health record (EHR) system, despite being trained on data from a different EHR system. Specifically, using this approach the team showed that predictive models for mortality and prolonged length of stay can be trained on one EHR system and used to make predictions in another.
ICU Intervene was co-developed by Suresh, undergraduate student Nathan Hunt, postdoc Alistair Johnson, researcher Leo Anthony Celi, MIT Professor Peter Szolovits, and PhD student Marzyeh Ghassemi. It was presented this month at the Machine Learning for Healthcare Conference in Boston.
EHR Model Transfer was co-developed by lead authors Jen Gong and Tristan Naumann, both PhD students at CSAIL, as well as Szolovits and John Guttag, who is the Dugald C. Jackson Professor in Electrical Engineering. It was presented at the ACM’s Special Interest Group on Knowledge Discovery and Data Mining in Halifax, Canada.
Both models were trained using data from the critical care database MIMIC, which includes de-identified data from roughly 40,000 critical care patients and was developed by the MIT Lab for Computational Physiology.


MIT CSAIL
www.csail.mit.edu/using_machine_learning_to_improve_patient_care%20