Improving patient care by bridging the divide between doctors and data scientists

Curated on Posted on by Stefaan Verhulst

 at the Conversation: “While wonderful new medical discoveries and innovations are in the news every day, doctors struggle daily with using information and techniques available right now while carefully adopting new concepts and treatments. As a practicing doctor, I deal with uncertainties and unanswered clinical questions all the time….At the moment, a report from the National Academy of Medicine tells us, most doctors base most of their everyday decisions on guidelines from (sometimes biased) expert opinions or small clinical trials. It would be better if they were from multicenter, large, randomized controlled studies, with tightly controlled conditions ensuring the results are as reliable as possible. However, those are expensive and difficult to perform, and even then often exclude a number of important patient groups on the basis of age, disease and sociological factors.

Part of the problem is that health records are traditionally kept on paper, making them hard to analyze en masse. As a result, most of what medical professionals might have learned from experiences was lost – or at least was inaccessible to another doctor meeting with a similar patient.

A digital system would collect and store as much clinical data as possible from as many patients as possible. It could then use information from the past – such as blood pressure, blood sugar levels, heart rate and other measurements of patients’ body functions – to guide future doctors to the best diagnosis and treatment of similar patients.

Industrial giants such as Google, IBM, SAP and Hewlett-Packard have also recognized the potential for this kind of approach, and are now working on how to leverage population data for the precise medical care of individuals.

Collaborating on data and medicine

At the Laboratory of Computational Physiology at the Massachusetts Institute of Technology, we have begun to collect large amounts of detailed patient data in the Medical Information Mart in Intensive Care (MIMIC). It is a database containing information from 60,000 patient admissions to the intensive care units of the Beth Israel Deaconess Medical Center, a Boston teaching hospital affiliated with Harvard Medical School. The data in MIMIC has been meticulously scoured so individual patients cannot be recognized, and is freely shared online with the research community.

But the database itself is not enough. We bring together front-line clinicians (such as nurses, pharmacists and doctors) to identify questions they want to investigate, and data scientists to conduct the appropriate analyses of the MIMIC records. This gives caregivers and patients the best individualized treatment options in the absence of a randomized controlled trial.

Bringing data analysis to the world

At the same time we are working to bring these data-enabled systems to assist with medical decisions to countries with limited health care resources, where research is considered an expensive luxury. Often these countries have few or no medical records – even on paper – to analyze. We can help them collect health data digitally, creating the potential to significantly improve medical care for their populations.

This task is the focus of Sana, a collection of technical, medical and community experts from across the globe that is also based in our group at MIT. Sana has designed a digital health information system specifically for use by health providers and patients in rural and underserved areas.

At its core is an open-source system that uses cellphones – common even in poor and rural nations – to collect, transmit and store all sorts of medical data. It can handle not only basic patient data such as height and weight, but also photos and X-rays, ultrasound videos, and electrical signals from a patient’s brain (EEG) and heart (ECG).

Partnering with universities and health organizations, Sana organizes training sessions (which we call “bootcamps”) and collaborative workshops (called “hackathons”) to connect nurses, doctors and community health workers at the front lines of care with technology experts in or near their communities. In 2015, we held bootcamps and hackathons in Colombia, Uganda, Greece and Mexico. The bootcamps teach students in technical fields like computer science and engineering how to design and develop health apps that can run on cellphones. Immediately following the bootcamp, the medical providers join the group and the hackathon begins…At the end of the day, though, the purpose is not the apps….(More)

Smart crowds in smart cities: real life, city scale deployments of a smartphone based participatory crowd management platform

Curated on Posted on by Stefaan Verhulst

Tobias Franke, Paul Lukowicz and Ulf Blanke at the Journal of Internet Services and Applications: “Pedestrian crowds are an integral part of cities. Planning for crowds, monitoring crowds and managing crowds, are fundamental tasks in city management. As a consequence, crowd management is a sprawling R&D area (see related work) that includes theoretical models, simulation tools, as well as various support systems. There has also been significant interest in using computer vision techniques to monitor crowds. However, overall, the topic of crowd management has been given only little attention within the smart city domain. In this paper we report on a platform for smart, city-wide crowd management based on a participatory mobile phone sensing platform. Originally, the apps based on this platform have been conceived as a technology validation tool for crowd based sensing within a basic research project. However, the initial deployments at the Notte Bianca Festival1 in Malta and at the Lord Mayor’s Show in London2 generated so much interest within the civil protection community that it has gradually evolved into a full-blown participatory crowd management system and is now in the process of being commercialized through a startup company. Until today it has been deployed at 14 events in three European countries (UK, Netherlands, Switzerland) and used by well over 100,000 people….

Obtaining knowledge about the current size and density of a crowd is one of the central aspects of crowd monitoring . For the last decades, automatic crowd monitoring in urban areas has mainly been performed by means of image processing . One use case for such video-based applications can be found in, where a CCTV camera-based system is presented that automatically alerts the staff of subway stations when the waiting platform is congested. However, one of the downsides of video-based crowd monitoring is the fact that video cameras tend to be considered as privacy invading. Therefore,  presents a privacy preserving approach to video-based crowd monitoring where crowd sizes are estimated without people models or object tracking.

With respect to the mitigation of catastrophes induced by panicking crowds (e.g. during an evacuation), city planners and architects increasingly rely on tools simulating crowd behaviors in order to optimize infrastructures. Murakami et al. presents an agent based simulation for evacuation scenarios. Shendarkar et al. presents a work that is also based on BSI (believe, desire, intent) agents – those agents however are trained in a virtual reality environment thereby giving greater flexibility to the modeling. Kluepfel et al. on the other hand uses a cellular automaton model for the simulation of crowd movement and egress behavior.

With smartphones becoming everyday items, the concept of crowd sourcing information from users of mobile application has significantly gained traction. Roitman et al. presents a smart city system where the crowd can send eye witness reports thereby creating deeper insights for city officials. Szabo et al. takes this approach one step further and employs the sensors built into smartphones for gathering data for city services such as live transit information. Ghose et al. utilizes the same principle for gathering information on road conditions. Pan et al. uses a combination of crowd sourcing and social media analysis for identifying traffic anomalies….(More)”.

Evaluating e-Participation: Frameworks, Practice, Evidence

Curated on Posted on by Stefaan Verhulst

Book edited by Georg Aichholzer, Herbert Kubicek and Lourdes Torres: “There is a widely acknowledged evaluation gap in the field of e-participation practice and research, a lack of systematic evaluation with regard to process organization, outcome and impacts. This book addresses the state of the art of e-participation research and the existing evaluation gap by reviewing various evaluation approaches and providing a multidisciplinary concept for evaluating the output, outcome and impact of citizen participation via the Internet as well as via traditional media. It offers new knowledge based on empirical results of its application (tailored to different forms and levels of e-participation) in an international comparative perspective. The book will advance the academic study and practical application of e-participation through fresh insights, largely drawing on theoretical arguments and empirical research results gained in the European collaborative project “e2democracy”. It applies the same research instruments to a set of similar citizen participation processes in seven local communities in three countries (Austria, Germany and Spain). The generic evaluation framework has been tailored to a tested toolset, and the presentation and discussion of related evaluation results aims at clarifying to what extent these tools can be applied to other consultation and collaboration processes, making the book of interest to policymakers and scholars alike….(More)”

Dive Against Debris: Employing 25,600 scuba divers to collect data

Curated on Posted on by Stefaan Verhulst

DataDrivenJournalism: “In 2011, the team at Project AWARE launched the Dive Against Debris program with the objective of better documenting the amount of marine debris found in the world’s oceans. This global citizen science program trains volunteer scuba divers from across the globe to conduct underwater surveys, generating quantitative data on the debris they see. After cleaning this data for quality assurance, it is then published on their interactive Dive Against Debris Map. This data and visualization informs the team’s advocacy work, ultimately seeking to generate changes in policy.

The impact of marine debris is devastating, killing marine life and changing their habitats and ecosystems. Animals are extremely vulnerable to ingestion or entanglement which leads to death, as they are unable to distinguish between what is trash and what is not.

Beyond this, as microscopic pieces of plastic enter the food chain, most seafood ingested by humans also likely contains marine debris.

Project AWARE is a growing movement of scuba divers protecting the ocean, with a long history of working on the marine debris issue. Through its work, the Project AWARE team found that there was a significant lack of data available regarding underwater marine debris.

To remedy this, the Dive Against Debris program was launched in 2011. The programs seeks to collect and visualise data generated by their volunteers, then use this data to influence policy changes and raise social awareness around the world. This data collection is unique in that it focuses exclusively on yielding data about the types and quantities of marine debris items found beneath in the ocean, an issue Hannah Pragnell-Raasch, a Program Specialist with Project AWARE, told us “has previously been disregarded as out of sight, out of mind, as the everyday person is not exposed to the harmful impacts.”

To date, Dive Against Debris surveys have been conducted in over 50 countries, with the top reporting countries being the United States, Thailand and Greece. As more divers get involved with Dive Against Debris, Project AWARE continues to bring visibility to the problem of marine debris and helps to identify target areas for waste prevention efforts.

datadebrismap.png

 

….

Anyone can take part in a Dive Against Debris survey, as long as they are a certified diver. As described in their “Action Zone”, scuba divers can either “join” or “create” an action. To further support the program, Project AWARE launched the Dive Against Debris Distinctive Specialty, a course of divers, which “aims to equip students (scuba divers) with the skills and knowledge necessary to conduct their own Dive Against Debris Surveys.”

Before the data appears on the interactive Dive Against Debris Map, it goes through a quality review in order to ensure data integrity. The survey leader at Project AWARE corrects any data inconsistencies. Then, as the focus is exclusively on what is found underwater, all land data is removed. Project AWARE Aware aims to create “an accurate perspective about underwater marine debris, that policy-makers simply cannot ignore”…. Explore the Dive Against Debris project here…. (More)

Crowdfunded Journalism: A Small but Growing Addition to Publicly Driven Journalism

Curated on Posted on by Stefaan Verhulst

Nancy Vogt and Amy Mitchell at PewResearchCenter: “Projects funded through Kickstarter cut across more than 60 countries

Over the past several years, crowdfunding via the internet has become a popular way to engage public support – and financial backing – for all kinds of projects, from the Coolest Cooler to a virtual reality gaming headset to a prototype of a sailing spacecraft and a bailout fund for Greece.

From April 28, 2009 to September 15, 2015, 658 journalism-related projects proposed on Kickstarter, one of the largest single hubs for crowdfunding journalism, received full – or more than full – funding, to the tune of nearly $6.3 million.These totals – both in terms of number of projects and funds raised – trail nearly all of Kickstarter’s other funding categories, from music, theater and film to technology and games. Nevertheless, the number of funded journalism projects has seen an ongoing increase over time and includes a growing number of proposals from established media organizations.

These totals – both in terms of number of projects and funds raised – trail nearly all of Kickstarter’s other funding categories, from music, theater and film to technology and games. Nevertheless, the number of funded journalism projects has seen an ongoing increase over time and includes a growing number of proposals from established media organizations….(More)

Open Data as Open Educational Resources: Case studies of emerging practice

Curated on Posted on by Stefaan Verhulst

Book edited by Javiera Atenas and Leo Havemann: “…is the outcome of a collective effort that has its origins in the 5th Open Knowledge Open Education Working Group call, in which the idea of using Open Data in schools was mentioned. It occurred to us that Open Data and open educational resources seemed to us almost to exist in separate open worlds.

We decided to seek out evidence in the use of open data as OER, initially by conducting a bibliographical search. As we could not find published evidence, we decided to ask educators if they were in fact, using open data in this way, and wrote a post for this blog (with Ernesto Priego) explaining our perspective, called The 21st Century’s Raw Material: Using Open Data as Open Educational Resources. We ended the post with a link to an exploratory survey, the results of which indicated a need for more awareness of the existence and potential value of Open Data amongst educators…..

the case studies themselves. They have been provided by scholars and practitioners from different disciplines and countries, and they reflect different approaches to the use of open data. The first case study presents an approach to educating both teachers and students in the use of open data for civil monitoring via Scuola di OpenCoesione in Italy, and has been written by Chiara Ciociola and Luigi Reggi. The second case, by Tim Coughlan from the Open University, UK, showcases practical applications in the use of local and contextualised open data for the development of apps. The third case, written by Katie Shamash, Juan Pablo Alperin & Alessandra Bordini from Simon Fraser University, Canada, demonstrates how publishing students can engage, through data analysis, in very current debates around scholarly communications and be encouraged to publish their own findings. The fourth case by Alan Dix from Talis and University of Birmingham, UK, and Geoffrey Ellis from University of Konstanz, Germany, is unique because the data discussed in this case is self-produced, indeed ‘quantified self’ data, which was used with students as material for class discussion and, separately, as source data for another student’s dissertation project. Finally, the fifth case, presented by Virginia Power from University of the West of England, UK, examines strategies to develop data and statistical literacies in future librarians and knowledge managers, aiming to support and extend their theoretical understanding of the concept of the ‘knowledge society’ through the use of Open Data….(More)

The book can be downloaded here Open Data as Open Educational Resources

Web design plays a role in how much we reveal online

Curated on Posted on by Stefaan Verhulst

European Commission: “A JRC study, “Nudges to Privacy Behaviour: Exploring an Alternative Approach to Privacy Notices“, used behavioural sciences to look at how individuals react to different types of privacy notices. Specifically, the authors analysed users’ reactions to modified choice architecture (i.e. the environment in which decisions take place) of web interfaces.

Two types of privacy behaviour were measured: passive disclosure, when people unwittingly disclose personal information, and direct disclosure, when people make an active choice to reveal personal information. After testing different designs with over 3 000 users from the UK, Italy, Germany and Poland, results show web interface affects decisions on disclosing personal information. The study also explored differences related to country of origin, gender, education level and age.

A depiction of a person’s face on the website led people to reveal more personal information. Also, this design choice and the visualisation of the user’s IP or browsing history had an impact on people’s awareness of a privacy notice. If confirmed, these features are particularly relevant for habitual and instinctive online behaviour.

With regard to education, users who had attended (though not necessarily graduated from) college felt significantly less observed or monitored and more comfortable answering questions than those who never went to college. This result challenges the assumption that the better educated are more aware of information tracking practices. Further investigation, perhaps of a qualitative nature, could help dig deeper into this issue. On the other hand, people with a lower level of education were more likely to reveal personal information unwittingly. This behaviour appeared to be due to the fact that non-college attendees were simply less aware that some online behaviour revealed personal information about themselves.

Strong differences between countries were noticed, indicating a relation between cultures and information disclosure. Even though participants in Italy revealed the most personal information in passive disclosure, in direct disclosure they revealed less than in other countries. Approximately 75% of participants in Italy chose to answer positively to at least one stigmatised question, compared to 81% in Poland, 83% in Germany and 92% in the UK.

Approximately 73% of women answered ‘never’ to the questions asking whether they had ever engaged in socially stigmatised behaviour, compared to 27% of males. This large difference could be due to the nature of the questions (e.g. about alcohol consumption, which might be more acceptable for males). It could also suggest women feel under greater social scrutiny or are simply more cautious when disclosing personal information.

These results could offer valuable insights to inform European policy decisions, despite the fact that the study has targeted a sample of users in four countries in an experimental setting. Major web service providers are likely to have extensive amounts of data on how slight changes to their services’ privacy controls affect users’ privacy behaviour. The authors of the study suggest that collaboration between web providers and policy-makers can lead to recommendations for web interface design that allow for conscientious disclosure of privacy information….(More)”

Crowdsourcing a solution works best if some don’t help

Curated on Posted on by Stefaan Verhulst

Sarah Scoles at the New Scientist: “There are those who edit Wikipedia entries for accuracy – and those who use the online encyclopaedia daily without ever contributing. A new mathematical model says that’s probably as it should be: crowdsourcing a problem works best when a certain subset of the population chooses not to participate.

“In most social undertakings, there is a group that actually joins forces and works,” says Zoran Levnajic at the University of Ljubljana, Slovenia. “And there is a group of free-riders that typically benefits from work being done, without contributing much.”

Levnajic and his colleagues simulated this scenario. Digital people in a virtual population each had a randomly assigned tendency to collaborate on a problem or “freeload” – working alone and not sharing their findings. The team ran simulations to see whether there was an optimum crowdsource size for problem-solving.

It turned out there was – and surprisingly, the most effective crowd was not the largest possible. In fact, the simulated society was at its problem-solving best when just half the population worked together.

Smaller crowds contained too few willing collaborators with contrasting but complementary perspectives to effectively solve a problem. But if the researchers ran simulations with larger crowds, the freeloaders it contained naturally “defected” to working alone – knowing that they could benefit from any solutions the crowd reached, while also potentially reaping huge benefits if they could solve the problem without sharing the result (arxiv.org/abs/1506.09155)….(More)”

Revolution Delayed: The Impact of Open Data on the Fight against Corruption

Curated on Posted on by Stefaan Verhulst

Report by RiSSC – Research Centre on Security and Crime (Italy): “In the recent years, the demand for Open Data picked up stream among stakeholders to increasing transparency and accountability of the Public Sector. Governments are supporting Open Data supply, to achieve social and economic benefits, return on investments, and political consensus.

While it is self-evident that Open Data contributes to greater transparency – as it makes data more available and easy to use by the public and governments, its impact on fighting corruption largely depends on the ability to analyse it and develop initiatives that trigger both social accountability mechanisms, and government responsiveness against illicit or inappropriate behaviours.

To date, Open Data Revolution against corruption is delayed. The impact of Open Data on the prevention and repression of corruption, and on the development of anti- corruption tools, appears to be limited, and the return on investments not yet forthcoming. Evidence remains anecdotal, and a better understanding on the mechanisms and dynamics of using Open Data against corruption is needed.

The overall objective of this exploratory study is to provide evidence on the results achieved by Open Data, and recommendations for the European Commission and Member States’ authorities, for the implementation of effective anti-corruption strategies based on transparency and openness, to unlock the potential impact of “Open Data revolution” against Corruption.

The project has explored the legal framework and the status of implementation of Open Data policies in four EU Countries – Italy, United Kingdom, Spain, and Austria. TACOD project has searched for evidence on Open Data role on law enforcement cooperation, anti-corruption initiatives, public campaigns, and investigative journalism against corruption.

RiSSC – Research Centre on Security and Crime (Italy), the University of Oxford and the University of Nottingham (United Kingdom), Transparency International (Italy and United Kingdom), the Institute for Conflict Resolution (Austria), and Blomeyer&Sanz (Spain), have carried out the research between January 2014 and February 2015, under an agreement with the European Commission – DH Migration and Home Affairs. The project has been coordinated by RiSSC, with the support of a European Working Group of Experts, chaired by prof. Richard Rose, and an external evaluator, Mr. Andrea Menapace, and it has benefited from the contribution of many experts, activists, representatives of Institutions in the four Countries….(More)

Syria refugees tap in to legal advice by text

Curated on Posted on by Stefaan Verhulst

Hannah Kuchler in the Financial Times: “Syrian refugees can now access free legal advice by text message after a Palestinian start-up launched a service in Turkey, which it hopes to expand to reach refugees across Europe.

Refugees fleeing the conflict in Syria can receive legal guidance via their mobile phones on everything from whether they have the right to work to education services available for their children, after Souktel, a small start-up partnered with the American Bar Association.

The 30-person start-up employs both former humanitarian workers from Oxfam and USAID, who understand the problems faced by refugees, and software engineers who tackle the challenge of sorting, tagging and translating enquiries which are then sent to a team of Turkish lawyers.

Jacob Korenblum, president and chief executive of Souktel, said more than 10,000 individuals have used the service since it launched less than three weeks ago, with lawyers busy answering a steady stream of questions.

“Given the strength and rapid interest in this service and the uptake since its launch, we want to scale into Greece and other European countries to meet the same need,” he said. “This is very much becoming a pan-European problem at the very least.”…

The American Bar Association approached Souktel and asked them to build a service that could offer remote legal support and uses funds from international donors to pay the company….

Smartphones — or even basic mobile phones — have fast become one of the easiest ways of communicating for the poor or dispossessed. Even when basic infrastructure has failed, people are able to access information and connect with relatives abroad via their devices.

Mr Korenblum, a Canadian former aid worker, helped found Souktel after he saw young people in Palestine relying on their mobile devices when working there 10 years ago. The company has built similar services on behalf of humanitarian organisations working in other areas — including the UK’s department for international development in Gaza, Iraq and Somalia, among other places…(More)”