Skip to main content

Improved decision-making support could save lives

Thursday, March 22, 2018

The first Metis Forum of the year once again gathered some 50 participants from the industry to discuss areas where ICT and eHealth have great potential for enhancing efficiency and improving prehospital care in a broad sense. This time, the focus was on sepsis and various types of support for assessment and prioritizing.







Normal
0


21


false
false
false

SV
X-NONE
X-NONE

























DefSemiHidden="false" DefQFormat="false" DefPriority="99"
LatentStyleCount="382">


UnhideWhenUsed="true" QFormat="true" Name="heading 2"/>
UnhideWhenUsed="true" QFormat="true" Name="heading 3"/>
UnhideWhenUsed="true" QFormat="true" Name="heading 4"/>
UnhideWhenUsed="true" QFormat="true" Name="heading 5"/>
UnhideWhenUsed="true" QFormat="true" Name="heading 6"/>
UnhideWhenUsed="true" QFormat="true" Name="heading 7"/>
UnhideWhenUsed="true" QFormat="true" Name="heading 8"/>
UnhideWhenUsed="true" QFormat="true" Name="heading 9"/>
Name="index 1"/>
Name="index 2"/>
Name="index 3"/>
Name="index 4"/>
Name="index 5"/>
Name="index 6"/>
Name="index 7"/>
Name="index 8"/>
Name="index 9"/>
UnhideWhenUsed="true" Name="toc 1"/>
UnhideWhenUsed="true" Name="toc 2"/>
UnhideWhenUsed="true" Name="toc 3"/>
UnhideWhenUsed="true" Name="toc 4"/>
UnhideWhenUsed="true" Name="toc 5"/>
UnhideWhenUsed="true" Name="toc 6"/>
UnhideWhenUsed="true" Name="toc 7"/>
UnhideWhenUsed="true" Name="toc 8"/>
UnhideWhenUsed="true" Name="toc 9"/>
Name="Normal Indent"/>
Name="footnote text"/>
Name="annotation text"/>
Name="header"/>
Name="footer"/>
Name="index heading"/>
UnhideWhenUsed="true" QFormat="true" Name="caption"/>
Name="table of figures"/>
Name="envelope address"/>
Name="envelope return"/>
Name="footnote reference"/>
Name="annotation reference"/>
Name="line number"/>
Name="page number"/>
Name="endnote reference"/>
Name="endnote text"/>
Name="table of authorities"/>
Name="macro"/>
Name="toa heading"/>
Name="List"/>
Name="List Bullet"/>
Name="List Number"/>
Name="List 2"/>
Name="List 3"/>
Name="List 4"/>
Name="List 5"/>
Name="List Bullet 2"/>
Name="List Bullet 3"/>
Name="List Bullet 4"/>
Name="List Bullet 5"/>
Name="List Number 2"/>
Name="List Number 3"/>
Name="List Number 4"/>
Name="List Number 5"/>

Name="Closing"/>
Name="Signature"/>
UnhideWhenUsed="true" Name="Default Paragraph Font"/>
Name="Body Text"/>
Name="Body Text Indent"/>
Name="List Continue"/>
Name="List Continue 2"/>
Name="List Continue 3"/>
Name="List Continue 4"/>
Name="List Continue 5"/>
Name="Message Header"/>

Name="Salutation"/>
Name="Date"/>
Name="Body Text First Indent"/>
Name="Body Text First Indent 2"/>
Name="Note Heading"/>
Name="Body Text 2"/>
Name="Body Text 3"/>
Name="Body Text Indent 2"/>
Name="Body Text Indent 3"/>
Name="Block Text"/>
Name="Hyperlink"/>
Name="FollowedHyperlink"/>


Name="Document Map"/>
Name="Plain Text"/>
Name="E-mail Signature"/>
Name="HTML Top of Form"/>
Name="HTML Bottom of Form"/>
Name="Normal (Web)"/>
Name="HTML Acronym"/>
Name="HTML Address"/>
Name="HTML Cite"/>
Name="HTML Code"/>
Name="HTML Definition"/>
Name="HTML Keyboard"/>
Name="HTML Preformatted"/>
Name="HTML Sample"/>
Name="HTML Typewriter"/>
Name="HTML Variable"/>
Name="Normal Table"/>
Name="annotation subject"/>
Name="No List"/>
Name="Outline List 1"/>
Name="Outline List 2"/>
Name="Outline List 3"/>
Name="Table Simple 1"/>
Name="Table Simple 2"/>
Name="Table Simple 3"/>
Name="Table Classic 1"/>
Name="Table Classic 2"/>
Name="Table Classic 3"/>
Name="Table Classic 4"/>
Name="Table Colorful 1"/>
Name="Table Colorful 2"/>
Name="Table Colorful 3"/>
Name="Table Columns 1"/>
Name="Table Columns 2"/>
Name="Table Columns 3"/>
Name="Table Columns 4"/>
Name="Table Columns 5"/>
Name="Table Grid 1"/>
Name="Table Grid 2"/>
Name="Table Grid 3"/>
Name="Table Grid 4"/>
Name="Table Grid 5"/>
Name="Table Grid 6"/>
Name="Table Grid 7"/>
Name="Table Grid 8"/>
Name="Table List 1"/>
Name="Table List 2"/>
Name="Table List 3"/>
Name="Table List 4"/>
Name="Table List 5"/>
Name="Table List 6"/>
Name="Table List 7"/>
Name="Table List 8"/>
Name="Table 3D effects 1"/>
Name="Table 3D effects 2"/>
Name="Table 3D effects 3"/>
Name="Table Contemporary"/>
Name="Table Elegant"/>
Name="Table Professional"/>
Name="Table Subtle 1"/>
Name="Table Subtle 2"/>
Name="Table Web 1"/>
Name="Table Web 2"/>
Name="Table Web 3"/>
Name="Balloon Text"/>

Name="Table Theme"/>
Name="Note Level 1"/>
Name="Note Level 2"/>
Name="Note Level 3"/>
Name="Note Level 4"/>
Name="Note Level 5"/>
Name="Note Level 6"/>
Name="Note Level 7"/>
Name="Note Level 8"/>
Name="Note Level 9"/>























Name="List Paragraph"/>

Name="Intense Quote"/>














































































Name="Subtle Emphasis"/>
Name="Intense Emphasis"/>
Name="Subtle Reference"/>
Name="Intense Reference"/>

UnhideWhenUsed="true" Name="Bibliography"/>
UnhideWhenUsed="true" QFormat="true" Name="TOC Heading"/>













Name="Grid Table 1 Light Accent 1"/>




Name="Grid Table 6 Colorful Accent 1"/>
Name="Grid Table 7 Colorful Accent 1"/>
Name="Grid Table 1 Light Accent 2"/>




Name="Grid Table 6 Colorful Accent 2"/>
Name="Grid Table 7 Colorful Accent 2"/>
Name="Grid Table 1 Light Accent 3"/>




Name="Grid Table 6 Colorful Accent 3"/>
Name="Grid Table 7 Colorful Accent 3"/>
Name="Grid Table 1 Light Accent 4"/>




Name="Grid Table 6 Colorful Accent 4"/>
Name="Grid Table 7 Colorful Accent 4"/>
Name="Grid Table 1 Light Accent 5"/>




Name="Grid Table 6 Colorful Accent 5"/>
Name="Grid Table 7 Colorful Accent 5"/>
Name="Grid Table 1 Light Accent 6"/>




Name="Grid Table 6 Colorful Accent 6"/>
Name="Grid Table 7 Colorful Accent 6"/>







Name="List Table 1 Light Accent 1"/>




Name="List Table 6 Colorful Accent 1"/>
Name="List Table 7 Colorful Accent 1"/>
Name="List Table 1 Light Accent 2"/>




Name="List Table 6 Colorful Accent 2"/>
Name="List Table 7 Colorful Accent 2"/>
Name="List Table 1 Light Accent 3"/>




Name="List Table 6 Colorful Accent 3"/>
Name="List Table 7 Colorful Accent 3"/>
Name="List Table 1 Light Accent 4"/>




Name="List Table 6 Colorful Accent 4"/>
Name="List Table 7 Colorful Accent 4"/>
Name="List Table 1 Light Accent 5"/>




Name="List Table 6 Colorful Accent 5"/>
Name="List Table 7 Colorful Accent 5"/>
Name="List Table 1 Light Accent 6"/>




Name="List Table 6 Colorful Accent 6"/>
Name="List Table 7 Colorful Accent 6"/>
Name="Mention"/>
Name="Smart Hyperlink"/>

/* Style Definitions */ table.MsoNormalTable {mso-style-name:"Normal tabell"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin:0cm; mso-para-margin-bottom:.0001pt; mso-pagination:widow-orphan; font-size:12.0pt; font-family:"Calibri",sans-serif; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin; mso-fareast-language:EN-US;}

Bengt Arne Sjöqvist, programming head for Prehospital ICT Arena (PICTA) at Lindholmen Science Park, welcomed participants and spoke about recent developments, including the fact that PICTA was now part of an expanded collaboration with FLISA (the Federation of Leaders in Swedish Ambulance and Emergency Services).

“Together, we can pursue ICT issues in prehospital care even more effectively. We see that there are many areas we can develop, for the benefit of both patients and staff. Prehospital care must also properly be part of the healthcare digitalization map.”

Per Örninge, Deputy Chairman of FLISA and former chief ambulance physician, emphasized the importance of the collaboration.

“Since FLISA is represented in all county councils and regions, we see it as our gathering Swedish ambulance care and PICTA gathering groups like Swedish technology and universities. This way, we can be reached from many aspects. The purpose is to improve healthcare by combining medical science, technology and research, ultimately so that patients will receive the best treatment possible.”

One of the main themes was sepsis, and many attendees involved in the field gave their views on the problems associated with this hard-to-assess illness. The participants were provided with results from clinical studies, comparisons of screening tools in different regions and examples of how decision-making support can improve the possibility of a correct diagnosis.

Lars Ljungström, an MD and chief physician for infections at Skaraborg Hospital Skövde, spoke about the problems of sepsis as regards different definitions and criteria for the illness, which has a mortality rate of 12 to 25 percent.

“There is a significant confusion of terms – but the illness gives rise to ‘life-threatening organ dysfunctionality’ and is sometimes very difficult to ascertain. The challenge is in recognizing patterns, identifying early on, and administering antibiotics.” 

Johanna Bergman, Project Manager at PICTA, has conducted a preliminary study of sepsis in a prehospital context.

“Sepsis can produce many diffuse symptoms. If it can be identified while still in the ambulance and treatment can be administered in order to later administer antibiotics at the hospital, the patient has a much better chance,” she commented. There is no really good way of assessing – there’s a lot to do! An assessment beyond the vital signs needs to be developed.”

Johanna Bergman, Project Manager at PICTA

Ulrika Wallgren, a physician at Karolinska Institutet researching sepsis, emphasized Johanna’s conclusions regarding improved assessment.
“By and large, sepsis can resemble every other condition – often stomach flu. The patients themselves often feel they are extremely sick. So a structured diagnostic process is needed.”

The day continued with a focus on artificial intelligence (AI), and whether it is a possible path to better assessments in prehospital care, not only of sepsis but also other illnesses.

“A great deal of the hype today is around ‘deep learning.’ It works, because we have fast computers now and a tremendous amount of data to use to obtain deeper knowledge,” said Robert Feldt, a professor from Chalmers who is focusing on applied AI.

At the same time, he emphasized that AI not only involves neural networks but that there are also many different branches, as well as the importance of how the results are presented to the user. 

In connection with AI and sepsis, PICTA’s ambition is to initiate a new project and to apply for funds to inaugurate it by this spring.

“We want to gradually develop decision-making support in prehospital care in order to identify risks for sepsis, moving from checklists and memorized rules to using AI,” Bengt Arne told his listeners.

The project is in progress under the name “PreSISe” – Prehospital Decision Support for Identification of Sepsis.

“There is enough data today from various county councils to start the first part of the project. As for partners, we have several stakeholders but if you want to be part of it, you just have to get in touch,” Bengt Arne said. “This project requires national cooperation among partners from academia, healthcare, the business sector and government authorities.”

At Uppsala University Hospital, Douglas Spangler – who has experience in US ambulance care, including IT issues – is running a project to develop clinical decision-making support at the Sjukvårdens Larmcentral emergency service center, and Vinnova has come on board with 4 million SEK in funding. There is a great amount of data to be had from the emergency center, ambulances – and now even hospitals. How can it best be used?

“We need to be able to make more nuanced assessments of the patient’s need for care, not just whether or not to send an ambulance. We want to collect a wealth of different proxy measurements, vital signs, drugs and so on that are of interest to health care staff. We will use this data for machine learning,” Douglas told us. “What we create in this project – all these modelling tools and such – will be released under open source licensing so that it will be available. Then it will be up to the industry to take it further!”

The day’s agenda also included presentations on sepsis solutions in the UK, an evaluation of different forms of decision-making support in emergency service centers, translation into different languages and AI as decision-making support in connection with prehospital trauma.

The material from the presentations is being published on the PICTA web site under Metis Forum.