Whenever a patient undergoes medical imaging there is a wealth of information that must be added to their case file. Complete and accurate diagnostic reports are essential for physicians to be able to make the best decisions about future patient care and to spot problems early so as to know when further examinations and investigations are needed. Diagnostic reports come from all areas of medical specialty, including radiology, obstetrics, cardiology, psychiatry, and surgery so it is vital that reports are clear, well formatted according to appropriate guidelines, and are as complete as possible so as to facilitate an easier diagnostic process and improve patient care.
Examples of the kinds of things requiring diagnostic reports include x-ray, ultrasound, computerized tomography (CT), magnetic resonance imaging (MRI), and nuclear medicine, among other tests. Each has its own transcription guidelines and each enters into the Radiology Information System (RIS) and the Picture Archival Communication System (PACS) so that referring physicians are able to instantly access the patient’s results following the procedure. Referring physicians are not, however, specialists in every aspect of radiology and rely on precise diagnostic reports to aid them in their diagnoses.
Even minor errors on diagnostic reports can adversely influence diagnosis by confusing physicians as to what the images actually show. Providing such diagnostic reports promptly whilst maintaining accuracy and including sufficient information can be a challenge; doing this well is, however, extremely important in helping physicians make fast and effective choices for patient care. Quality diagnostic imaging is a remarkable tool for improving the prognosis of patients but it is only as good as the radiologists and physicians using such a resource and only works when the diagnostic report produced after such imaging is complete, accurate, precise and quickly disseminated through the right channels.
Clearly, a major goal for radiologists and those producing diagnostic reports is to find ways to streamline the diagnostic report process and reduce errors in reporting. This is vital for every radiology department so as to improve their value to patients and physicians and help enhance revenue and reputation. increasingly, radiologists are realizing the potential application of medical speech-to-text voice recognition technology when compiling reports but there are still issues relating to formatting and compliance. Whether the report is for pain management, mammography screening, bone mineral density tracking or other purpose, a clear and quickly available diagnostic report gets patients on the right track faster.
Turnaround time from image acquisition to a full and accurate diagnostic report can be just a day when processes are finely tuned. Patients do not, and should not have to wait for weeks while dictated notes are sent to transcribers and then returned for review before being sent manually to a physician. The use of voice recognition software embedded in the RIS saves time and has the further advantages of producing clear, functional reports that automatically adhere to formatting guidelines and compliance requirements. A diagnostic report can easily be completed using CaseReader embedded with M*Modal Fluency voice recognition technology with key images included in the report for the physician’s convenience. Radiologists can feel more secure in the accuracy of their reports and can, quite substantially, cut the time it takes to produce such reports. Storing diagnostic reports on the cloud means that the radiologist and colleagues, the referring physicians and other relevant medical personnel can all access the patient’s medical information whenever necessary.
Implementing a system to separate out the clinical information from the procedural information also makes it easier to find the details relevant to each query whilst keeping the report uncluttered and organized. The technologist will provide details on the scanning process itself, such as the dose amount, specialized equipment used, any problems with the procedure and so forth, while clinical information can be entered courtesy of RIS, PACS and other sources. This diagnostic report system also includes ICD/CPT codes for quick use by radiologists, as well as allowing for extra information to be added should the radiologist have specific comments that need recording. Using smart links connecting images to their origin makes for a streamlined response when assessing such diagnostic reports. Such a customizable structure for the production of superior quality diagnostic reports makes it extremely useful across a variety of clinics and applications.
Voice recognition software allows physicians to convert medical speech to text and even to give commands to prompt specific actions on a computer. The vast improvements in the ability of computer software to recognize speech have led to increased use in education and in the assistance of those with disabilities, allowing for more independence and better quality of life. Voice recognition software also helps those who struggle to commit thoughts to paper and allows for improved multitasking, often being used to document progress during a task.
Not all applications are equal, however, and the complexities of medical vernacular necessitate the use of specific programs to improve accuracy. Physicians and surgeons will likely need to spend some time getting to know their chosen software and ensure that their software also gets to know them.
Luckily, the clumsy, error-riddled, voice recognition software of the nineties has been vastly improved and a number of surgeons are finding a place for these programs even during operations. The necessity of enunciating each word separately and providing pauses between every word is long gone and continuous speech recognition software has largely replaced discrete speech software. Many of the new programs can recognize speech at a rate of 160 words a minute, with the average speech pattern estimated at around 110-150 words per minute when someone is speaking in their native language during a friendly and relaxed conversation.
As well as providing a useful notation service during procedures or consultations, medical speech-to-text applications give physicians the opportunity to verbalize commands to open specific computer programs or files for handy reference and even to capture images during surgery or diagnostic procedures, given the right equipment set-up. Users of medical speech-to-text software will go through an initial exercise to train the application to recognize their pattern of speech and this specific information will be added to the general patterns of speech included in the program in order to provide a best-guess for every word.
Good medical speech-to-text software also accounts for usual grammar and relationships between words to improve results. Some users of voice recognition software do encounter issues where they have a complex or unusual speaking style. Many types of speech-to-text program include a dictation service so that the transcript can be compared to a recording in order to clarify the script at a later date.
Those looking into using medical speech-to-text software will want to consider the compatibility of any such program with their existing computer and platform, the languages included in the software, how easy it is to train the application and the potential for integration with other software, such as Word or Excel. Other things to think about before choosing speech-to-text software include:
- The ability to use wireless dictation, i.e. a Bluetooth headset
- The ability to transcribe from a digital recording
- Whether existing word lists and user profiles can be imported or exported.
Specific applications available for converting medical speech to text include Nuance (MacSpeech Dictate Medical), Trigram Technology, and M*Modal from the DrChrono platform. Open source voice recognition software for Linux includes Gnome Voice Control, Open Mind Speech and Perlbox.
DrChrono’s M*Modal’s Speech Understanding technology is part of a package for the iPad that collates electronic health records (EHR). Physicians can use the software to access EHRs on the iPad, or through a web browser or Android device. A Bluetooth headset can be used to dictate medical notes for immediate additions to patients’ medical records and the physician can also record notes in the clinical practice setting. Many US physicians are already using an iPad to augment their work and many more are considering the use of such a device.
A survey by Manhattan Research found some 30% of physicians already had an iPad for work and another 28% were thinking of purchasing one soon. The ability to access patients’ records through the handheld device was seen as particularly attractive amongst survey respondents and so many developers of software to convert medical speech to text are ensuring iPad compatibility for their programs.
Minimizing the energy expended on manually updating patients’ medical files, as well as reducing the risks of sloppy typing can be beneficial to both patient and physician in terms of cost, time and money. Digitizing such records also provides better accountability than current paper methods or localized record-keeping.
There are some potential downsides to the voice recognition software currently available, however, such as poor performance with ambient noise, lengthy load time, difficulty discriminating some common words and problems using a microphone, keyboard and mouse during procedures. Many programs are overcoming these issues but the problem recurs as they are translated to other devices, such as the iPad, making many medical speech-to-text devices and applications prohibitively expensive for most general practitioners.
Structured radiology reporting encompasses a variety of report generation techniques and data entry. Given the primary role that information technology will take part in the future of health care providing, the clear benefit of structured radiology reporting systems is evident. These systems can potentially lead to a rapid turnaround time of reports, a reduction of reporting costs, improved communication, boost in satisfied referring providers, as well as a simplified quality and reporting compliance.
The general format of reports remains unchanged. Radiologists comment on this technique, state our findings, list several limitations, and give a summary. The format and structure vary from each individual, group, and study. If this already works, why is there a need to change it?
For the purpose of having a more consistent method of patient care, practitioners must adapt to changes and improvements in their traditional practices. Summarily, through structured radiology reporting, it is easier to utilize a dictation phone and craft a report using free association. In a few seconds, the reports will emerge from a transcription box.
Advantages of Structured Reporting
Structured radiology reporting may provide the following improvements as compared to conventional reporting, depending on the degree of the structure and the usability interface:
* Save time spent on dictating – routine reports are made faster than via conventional dictation
* Save time on editing reports – compared to human-generated reports, those made with a computer have less errors than speech recognition
* Prompt turn-around reports – reports can be approved as well as sent at any time
* Receive help with difficult cases – gamut, templates and other forms of decision support are available in real-time
* Cost savings – transcription expenses are eliminated from the budget of operations
Accurate, complete and appealing reports – the physicians will better appreciate focused, multi-media and clear reports
These advantages are very important, especially for practitioners and hospital administrators who continue to seek ways to improve their services and offer help to more patients.
Challenges of Structured Reporting
Meanwhile, structured radiology reporting also has its share of challenges that potentially slows down user’s adoption of this reporting system. As we have pointed out earlier, this integration will not be a smooth and quick one. We list here some of the challenges:
* Potential for an increase in “look-away time”
Like other speech recognition systems, some of the structured reporting systems may cause the user to monitor the report while it is being produced. This added task could reduce the time spent by the radiologist in examining the images. Although literature on the relationship between interpretation accuracy and time is variable, the higher look-away time can affect the accuracy.
* Imaging lexicons are currently not routinely available
Although some imaging lexicons like Breast Imaging Reporting and Data System (BIRADS) from the American College of Radiology have been adopted widely, and others are currently being developed for cross-sectional breast imaging and chest imaging, the wide adoption of the structured reporting systems require the availability of lexicons for the entire imaging disciplines.
* Converts production task to a search task
Structured radiology reporting derives many of its benefits from using consistent imaging term, requiring radiologists using structured reporting systems to be familiar with the preferred terms used in imaging findings. For unfamiliar findings, the user needs to initiate a search using the proper term instead of improvising with an approximate synonym.
* Challenge in integrating the report along with the image
A majority of structured reporting systems provide for the link creations between locations on an image and imaging findings. However, these efforts are still in the early stages of creating this integration routine.
Overall, structured radiology reporting holds a lot of potential for its users and will provide great benefit after it has ironed out integration issues.
Medical transcription is the art (and science) of capturing physicians’ dictated words in a report accurately, an increasingly important task when considering the growth of electronic health records across all medical practices in recent years. The production of medical transcripts is a time-consuming task but accuracy in a patient’s history is paramount, especially when more medical professionals across a variety of specialties will access the same report during their interactions with a patient. No longer are medical records simply tied to a single practice and, therefore, medical transcription services are increasingly overwhelmed with requests for clear and accurate medical transcript production. Many practices outsource this work to those trained as medical language experts but this field of medical administration is also the focus of innovative voice recognition technology to aid in producing these medical transcripts.
A patient’s medical transcript will contain a wealth of information, including their symptoms, medical history, family history, test results, details of prescriptions and procedures and a diagnosis. Whenever a patient visits their physician and undergoes an examination or spends time talking through their symptoms and/or progress the physician will make a record of the outcome of the visit. Oftentimes, a physician uses a handheld voice recorder to dictate notes after the patient has left and these will be then be passed on to a medical transcriptionist. Producing a medical transcript is not as simple as typing out the words spoken by the physician as a patient’s report is considered a legal document and requires specific formatting. Once the transcript is complete it is entered into the patient’s file and can be called on in the future by the physician themselves or by another specialist treating the patient.
The correct formatting, review and editing of a medical transcript is important as this not only makes it much faster for physicians reviewing the patient’s history, it also means that an improperly recorded medication is identified quickly and can be corrected to avert risk. The physician providing the dictated notes is supposed to review the transcript upon completion but, in practice, some physicians do not review these transcripts and they are marked instead as “dictated but not read” to signal that there may still be potential accuracy issues. Medical transcribers can also flag a transcript if they spot inconsistencies in the report or if the words captured by the recorder were unrecognizable. Slow, precise and concise speech is vital to helping a transcriber produce accurate work and the same is true for voice recognition technology when dictating the names of medications, the procedure undertaken and the diagnosis.
Medical transcribers have to contend with regional and even national accents, rushed speech (particularly from Emergency Department physicians physician), mispronunciations and abbreviations of medical terminology, disordered speech when a physician recalls something out of the context of the current sentence, and even incorrect dosages or other errors. The transcriber must also make sure to check references and the proper spelling of medical terminology and highlight any problems they see in the report for the physicians review. Medical transcriptionists need to constantly be updating their database of new medical equipment, drugs, devices and nomenclature in order to produce accurate reports and this is just one area where a centralized database available with voice recognition software is helpful.
Physicians looking for efficiencies can also improve the accuracy of their own dictation, produce clearer medical transcripts that are properly formatted and easy to review while reducing wait-times for outsourced medical transcription services by using medical speech-to-text voice recognition technology such as M*Modal Fluency. One solution CaseReader™ by DPR has embedded M*Modal voice recognition technology. Within CaseReader™ Fluency is utilized for navigation and dictation in a templated environment to produce timely and accurate clinical documentation. The all-software solution enhances productivity and may increase revenue by ensuring accuracy and safety in patients’ medical transcripts. Its seamless integration with the ability to embedded images in the final report make CaseReader™ a valuable tool for radiologists and referring physicians.
Volumetric imaging may be a staple concept in science fiction but this field of imaging, which first appeared in the early part of the twentieth century, is still in its infancy and is only just becoming accessible. Volumetric display systems were, for a long time, confined to use in a small number of academic research laboratories and corporate facilities, and by some military scientists. Significant improvements in volumetric imaging in recent years have led to wider use of the technology, particularly in medicine. There are significant advantages to the use of volumetric imaging devices in this field, including improved visualisation of anatomical structures for surgical applications, research, diagnostic and educational purposes. Air traffic control and military operations also benefit from the volumetric imaging systems already available.
What Are Volumetric Images?
Volumetric imaging refers to the production of images with height, depth, and length, in contrast to the majority of images produced artificially as two dimensional representations. Viewers of volumetric images are able to view them from all angles and may even be able to interact with the image, depending on its characteristics. There is no clear consensus on taxonomy within the field of volumetric imaging displays, although attempts have been made to classify devices according to whether they produce an image viewable by the naked eye and whether an intermediate surface is required to house the image. When discussing volumetric imaging it is important to differentiate these types of displays from holograms.
Holograms and Volumetric Imaging
Holograms are stereoscopic, and may appear three-dimensional but are viewed on a two-dimensional surface such as glass or film. ‘True’ volumetric images have no need of this two-dimensional plane and can be projected, instead, into the air itself. Perhaps the most easily recognizable type of volumetric imaging is that used in Star Trek, where the ‘Holo Deck’ allowed crew members to enter into a virtual reality viewable from all angles and with which they could interact. Such images are not yet able to be produced, however, and the majority of existing volumetric imaging systems continue to use holographic technology.
‘True’ Volumetric Imaging
‘True’ volumetric images appear to float in the air but remain the purview of a small number of scientists and engineers. One device that is capable of producing these types of images is the fluorescent vapor imaging device. This volumetric imaging device uses a combination of mercury vapors and infrared light beams bounced off chemically-coated surfaces to alter their wavelengths. At the crossing point of two beams of light, the mercury vapors glow, making the image visible in the darkness. Clearly, there are some drawbacks with such a complex device designed to be used in the dark but other researchers are working on developing less problematic volumetric imaging devices.
Static and Swept Volume Displays
Swept volume displays are particularly useful in oncology imaging as they change with the movement of the surface on which they are formed. Such images are produced through the projection of computationally decomposed slices onto a spinning surface, creating a 3D image on a 2D surface, through embedded light-emitting diodes (LEDs), or by using other techniques.
Static volume 3D displays are also increasingly being used in the field of volumetric imaging as these create volume images without any macroscopic moving parts. Instead, most static volume imaging systems use intersecting beams of laser light combined with a solid, liquid, or gas to create visible radiation. Newer devices are able to create the floating types of images mentioned above by using a rapidly pulsing infrared laser to create glowing focal points in the air, removing the need for a projection surface.
Tissue-Volume Images – Volumetric Imaging in Action
Developments in volumetric imaging have also resulted in three-dimensional (3D) fluorescence images of organic tissue as an alternative to the ‘stacked’ two-dimensional images normally acquired from confocal or light-sheet microscopy. These imaging techniques are costly and take a long time to produce, making them unsuitable for visualising brief biological occurrences. The development of scanless volumetric imaging systems means that a single shot can capture an entire three-dimensional object using an adapted epifluorescence microscope. A key device in this field is the light-field microscope, developed at Stanford University, which produces 3D videos by recording the different points at which light rays pass through a microlens and the main lens of the sensor plane of the optical microscope.
A secondary approach to volumetric imaging involves an adapted multifocus fluorescence microscope that captures the full focal stack all at once on a single camera. This type of volumetric imaging system is fast, similar in quality to that of a wide-field microscope, and can be used for imaging of small organisms and single molecules, giving it a wide range of applications.
Freehand Volumetric Imaging Systems
Freehand volumetric imaging systems are particularly helpful in visualising musculoskeletal, gynaecological, and cardiac structures and tissues and include the xMATRIC electronic array, manufactured by Philips. This is an ultrasound system that provides a clear, live image while capturing quantifiable data, making it well-suited to endometrial evaluation, fetal cardiac examination and so forth. Another device on the market, the iSlice, automatically updates the given 2D projection as the volume view is rotated and allows physicians to select 4, 9, 16 or 25 2D image slices from the volume set for improved decision-making during diagnosis.
4D Volumetric Imaging
Volumetric imaging tools can allow physicians to visualize directional blood flow, measure specific hypoechoic structures such as the bladder, follicles, and gallbladder, and even create a 4D representation of fetal heart movement. This is facilitated by Spatio-Temporal Image Correlation (STIC) which pairs a calculated heart rate with the captured volumes in order to display and examine the image in real time, allowing for the detection of abnormalities in fetal heart rhythm.
Advantages of Volumetric Imaging
Advanced volumetric imaging systems provide a significant amount of information in a short space of time that is able to be interrogated for rapid diagnosis and patient management. Volumetric imaging displays rely on the emission, scattering, or relay of light in clearly described regions of space in order to create these incredibly useful images, with a variety of devices now available and an increasing appreciation of their value in numerous fields, especially medicine.
DataPhysics Research, Inc. introduces CaseReader™ v1.1, the next generation technology that “Improves Diagnostic Confidence” by reducing errors in the diagnostic report while increasing efficiencies through a reduction in report turnaround time. CaseReader™ displays image data in the same format radiologists are accustomed to viewing today. All hanging protocols currently in use are available resulting in little alteration to the radiologists’ current workflow. CaseReader™ aggregates information from decentralized sources in a seamless and organized manner making it available at the start of the study enabling the radiologist to focus more effort on image data and less on editing the report.