Marcel Wassink, 42, joined Philips Speech Recognition Systems in 1999 as Sales and Marketing Director and has been managing the company since 2002. He has expanded the business scope from developing technology to providing industrial grade solutions for efficient information capturing in the healthcare sector. Building a global partner network of more than 200 companies, Mr. Wassink has strengthened Philips Speech Recognition Systems continuous growth, which is reflected in Frost & Sullivan's Global Excellence 2007 Award. Prior to joining Philips, Mr. Wassink held several sales and marketing positions at Fujitsu in Benelux and the UK, working as European Business Manager for over three years. Mr. Wassink holds an M.Sc. in Computer Science from the Technical University of Delft, The Netherlands.

The following interview with Marcel Wassink was conducted by HealthTech Wire's editor Armin Scheuer (www.healthtechwire.com) on behalf of Frost & Sullivan.

Marcel Wassink

MW (Marcel Wassink): Our particular focus on the healthcare market, complemented by a solid clinical understanding allows us to create solutions that lead to higher accuracy, convenience and efficiency in clinical documentation. This has been achieved in close partnership with healthcare IT providers who provided us with direct input from the end users to consequently advance the technology to industrial grade levels.

The challenges in our field are indeed immense. We are expecting technology to cope with two highly complex issues: first, it has to capture and understand unstructured spoken information. Secondly, it has to turn this information into structured text, which takes into account that this is going to be used for sensitive healthcare purposes and life-affecting decisions. This requires in-depth expertise, plus detailed customer and clinical insight in order to achieve the accuracy, convenience and efficiency levels required in the healthcare industry. This focus has lead to the current massive adoption of speech recognition throughout healthcare sectors all over the world.

MW: In our market, radiologists are clearly the trend-setters. Plagued by an increasing documentation volume and scarce resources, they need new solutions to uphold service levels. At Aberdeen Royal Infirmary in Scotland they put 60 users in the radiology department in full control of their medical reporting. The radiologists can now create reports instantly. They no longer spend time waiting for reports to return from transcription sometimes weeks after the consultation, verify them and in between answer phone calls about unfinished reports.

Once radiology is up to speed, the entire hospital starts realizing the change which usually generates direct user demand for our technologies and services. Another trend that benefits our business is the introduction of electronic health record systems. They are seen as a key component to raise patient safety and reduce medical errors. However, physicians' resistance is still high because of inflexible and inconvenient data capturing. Enabling verbal interaction between physicians and EHR is expected to eliminate adoption barriers, which is why we are especially active in EHR-friendly markets, such as the US, Scandinavia or Germany.

In Belgium, the hospital AZ Sint-Jan integrated SpeechMagic with their electronic health record system and report turnaround time has been reduced by up to 60%. With speech recognition-based transcription being at least twice as fast as manual transcription, physicians at the hospital say they are now able to provide better care.

A development that took us almost by surprise is to see entire cities and regional healthcare services setting out to optimize information capturing. Things are changing in healthcare; providers and governments are ready to face the demographic challenge and to cut down on the extremely high error rates.

MW: Medical errors occur in all areas of the treatment process and typically involve the wrong medication, improper treatment, or incorrect or delayed test results. The European Commission observed that the health sector lags behind other industries and services that have introduced systematic safety processes and recommended to optimise the use of new technologies, for example, by introducing EHRs.

In another survey, almost four in five EU citizens classified medical errors as an important problem in their country. 850,000 medical errors are reported from the UK each year, and 98,000 deadly incidents per year are estimated to occur in the United States according to the Institute of Medicine.

The current level of medical errors is not acceptable. These numbers are a clear call to action for governments, healthcare organizations and technology providers. And current market developments show that the call has been heard.

MW: The largest healthcare speech recognition site in the world serves more than 60,000 US physicians. Adoption rates among radiologists have reached levels between 50% and 80% in many European countries. Regional public healthcare sectors in Spain, Italy, Norway, Denmark and the UK have implemented the technology on an unprecedented scale. In Paris, all 12,000 physicians and 3,000 transcriptionists of the city's public hospitals are set to switch to speech recognition by 2010. Some of our clients classify the benefits brought by our technologies and services as "the most successful IT project ever", that has shown a raise of overall hospital productivity by 5-7%.

MW: Already today we are working on taking speech recognition beyond recognizing words. We have released a bundle of intelligent features called Intelligent Speech Interpretation. They enable medical documents to be generated with a minimum of human intervention. Currently, we are researching solutions that integrate third-party applications, such as medical databases, diagnostic reference systems or coding applications – all of which aim to make healthcare documentation more accurate, convenient and efficient. We are looking at systems that increase patient safety during the process of capturing information in EHR systems, for example, by issuing a warning if physicians prescribe medication to a pregnant patient that is forbidden during pregnancy.

We are also working on standardizing language to support the interoperability of information systems. All healthcare applications must have a common, standardized language that allows them to share information among each other, thus giving access to critical information at the point-of–care: because knowledge is safety – in healthcare even more so than in any other field.

MW: We are currently providing recognition for 25 languages and the fact that we started out in such a linguistically diverse continent as Europe left us no choice but to become extremely good in handling the "Babylonian challenge". It made us fast and strong at expanding into new markets and today we are the only ones to provide speech recognition for smaller markets such as Slovenia, Hungary or Denmark – because patient safety is not only a concern in larger countries. However, the language I was referring to before is the ability to turn voice into structured information that is sharable and searchable and therefore a key management tool in the healthcare process – from treatment to administration. We call this clinically actionable information – and we see it as a key element in preparing the healthcare sector for the challenges of the future.

MW: Definitely not, medical transcriptionists are indispensable for the healthcare market and our Chief Medical Officer has been elected to the board of directors for the American Medical Transcription Industry Association. However, the industry will change and we will see transcriptionists moving into the role of medical editors. Philips therefore provides a unique feature that allows seamlessly switching between backend and front-end speech recognition for optimal workflows between physicians and transcriptionists.

MW: Backend speech recognition is ideal for hospitals that don't want to involve physicians in the report transcription process. Doctors continue to work the same way as before, while the transcription office experiences an increase in productivity. Backend is often implemented as a transitory solution to facilitate a smoother introduction of front-end speech recognition as the process builds individual customized profiles for each of the clinician users who, when switched to front-end, are already fine tuned and producing highly accurate results.

With the improvement of speech recognition technology, physicians can now be given full control over the reporting process – and many hospitals do this. Although it is true, that initially physicians have to invest more time to produce a report, the overall process has proven more time efficient and in fact it saves physician time, because it eliminates the "back and forward" between transcriptionist, physician, patient and referring physician, making critical clinical information immediately available for clinical decision making.

The ideal situation is to let physicians use whichever method they prefer depending on the individual circumstances at the time the clinician is dictating – which we do with SpeechMagic.

The method which succeeds varies by country: In Spain, front-end speech recognition integrated with the EHR is very popular: 50% of the country's radiologists dictate this way. In Germany, backend is often the preferred method, to help secretaries cope with increasing documentation requirements. In the US, the situation is mixed. Backend speech recognition is very successful as it allows hospitals to dramatically improve turnaround times, reduce outsourcing and decrease costs. However, in high-volume areas, such as emergency medicine or radiology, front-end workflows are picking up even though more clinician involvement is required.

MW: I am proud that we have managed to turn an administrative technology into a widely adopted tool for information capturing in healthcare with respective benefits for patient safety and treatment outcomes. To do so, we had to raise awareness about the role of accurate and complete information capturing and we continuously kept working at this. Above all, we have developed from a technology provider into a team of globally recognized experts on accurate, convenient and efficient information capturing. The joint commitment to making a difference in patient care is what motivates us and I am happy to see these efforts recognized by our partners, customers and now by Frost & Sullivan.

HealthTech Wire

Name: Armin Scheuer
Tel: +49 30 36448271
Email: newsroom@healthtechwire.com
Website URL: www.healthtechwire.com

Philips Speech Recognition Systems

Name: Anne Durand-Badel
Tel: +43 1 60101 1048
Email: anne.durand-badel@philips.com
Website URL: www.philips.com/speechrecognition