Medical Transcription Research Articles

Speech recognition technology in radiology

Speech recognition devices are promising tools for the healthcare system. Speech recognition technology has had a relatively long history of use in Western healthcare systems since the 1970s. However, it became widely used at the beginning of the 21st century, replacing medical transcriptionists. This technology is relatively new in home healthcare. Its active development began only in the early 2010s, and its implementation in healthcare started in late 2010. This delay is due to the idiosyncrasies of the Russian language and the limited computational power present at the beginning of the 21st century.
 Currently, complexes of devices and software for speech recognition are used in the voice filling of medical records and can reduce the time for preparing reports for radiological examinations compared with traditional (keyboard) text input.
 The literature review provides a brief history of speech recognition technology development and application in radiography. Key scientific studies showing its efficacy in Western healthcare systems are reflected. Voice recognition technology in the home is demonstrated, and its effectiveness is evaluated. The prospects for further development of this technology in Russian healthcare are described.

Extraction of Meaningful Information from Unstructured Clinical Notes Using Web Scraping

In the medical field, the clinical notes taken by the doctor, nurse, or medical practitioner are considered to be one of the most important medical documents. These documents hold information regarding the patient including the patient’s current condition, family history, disease, symptoms, medications, lab test reports, and other vital information. Despite these documents holding important information regarding the patients, they cannot be used as the data are unstructured. Organizing a huge amount of data without any mistakes is highly impossible for humans, so ignoring unstructured data is not advisable. Hence, to overcome this issue, the web scraping method is used to extract the clinical notes from the Medical Transcription (MT) samples which hold many transcripted clinical notes of various departments. In the proposed method, Natural Language Processing (NLP) is used to pre-process the data, and the variants of the Term Frequency-Inverse Document Frequency (TF-IDF)-based vector model are used for the feature selection, thus extracting the required data from the clinical notes. The performance measures including the accuracy, precision, recall and F1 score are used in the identification of disease, and the result obtained from the proposed system is compared with the best performing machine learning algorithms including the Logistic Regression, Multinomial Naive Bayes, Random Forest classifier and Linear SVC. The result obtained proves that the Random Forest Classifier obtained a higher accuracy of 90% when compared to the other algorithms.

Professional Certification and Earnings of Health Care Workers in Low Social Closure Occupations

There has been rapid growth in professional certifications in the health care sector, but little is known about the rewards to workers for attaining professional certifications, especially in low social closure occupations where the barriers to entry (e.g., higher education, degrees, licensure) are relatively limited. In this study, we focus on the attainment and rewards for professional certifications in four health care occupations – personal care aides, medical transcriptionists, medical assistants, and community health workers – where certification is generally not required by state or federal regulation but may be attractive to employers. Using the Current Population Survey (IPUMS CPS) between 2015 and 2020, we find that workers of color are less likely to attain a certification, while women are more likely than men to earn professional certifications. However, men experience the largest increase in weekly earnings (11.3%) when they have a professional certification as compared to those without, while women experience lower gains from professional certification (3.8%). Black and Hispanic workers experience modest rewards for certification (weekly earnings that are 1.2% and 5% higher, respectively) that are lower than the rewards gained by white workers (6% higher weekly earnings). Our findings suggest that professional certifications may have modest benefits for workers, but professional certifications often come with significant costs for individuals. Strategies for reducing inequality in the return to credentials and for improving job quality in the care sector are discussed.

Professional certification and earnings of health care workers in low social closure occupations

There has been rapid growth in professional certifications in the health care sector, but little is known about the rewards to workers for attaining professional certifications, especially in low social closure occupations where the barriers to entry (e.g., higher education, degrees, licensure) are relatively limited. In this study, we focus on the attainment and rewards for professional certifications in four health care occupations – personal care aides, medical transcriptionists, medical assistants, and community health workers – where certification is generally not required by state or federal regulation but may be attractive to employers. Using the Current Population Survey (IPUMS CPS) from 2015 to 2020, we find that workers of color have significantly lower odds of attaining a certification, while women are 1.2 times more likely than men to an earn a certification. On average, workers who have earned a professional certification have weekly earnings that are 4.8% higher than workers who do not have a certification. Men experience the largest increase in weekly earnings (11.3%) when they have a professional certification as compared to those without, while women experience lower gains from professional certification (3.8%). Black and Hispanic workers experience modest rewards for certification (weekly earnings that are 1.2% and 5% higher, respectively) that are lower than the rewards gained by white workers (6% higher weekly earnings). Our findings suggest that professional certifications may have modest benefits for workers, but professional certifications often come with significant costs for individuals. Strategies for reducing inequality in the return to credentials and for improving job quality in the care sector are discussed.

Minding the gap: Gynecologic oncology practices differ by gender.

11011 Background: Although most gynecologic oncologists (GOs) are now women, gender differences in clinical practice and compensation persist. Practice characteristics and infrastructural support that may influence gender-based differences were explored. Methods: Every 5 years, the Society of Gynecologic Oncology (SGO) conducts a member survey that provides details on member demographics, practice characteristics, activities, and revenue. Between 8/15-9/30/19 SGO members received a direct link to the survey. Gender was self-identified. Differences in responses were evaluated by gender. Results: Of 1425 surveys delivered, 690 were completed (48% response rate). 312 (45%) identified as male; 367 (53%) as female; 1 nonbinary; 1 other; 7 no response. Male GOs were more likely white (75 vs 68%, p=0.048), married (91 vs 81%, p<0.001), heterosexual (94 vs 90%, p=0.045), and hold an academic rank of professor (23 vs 12%, p<0.001). Practice setting and number of partners were similar. Chemotherapy prescribing was more common for females (82 vs 73%, p=0.004), but other clinical activities were similar (Table). Female GOs had lower clinical volumes than males for cervical, ovarian, vaginal/vulvar cancer and benign gynecologic procedures. Females reported fewer medical assistants and transcriptionists supporting their clinical activities. Overall and practice support was higher for male GOs although hospital support was similar for both genders. Female GOs reported more time spent on research (26 vs 19%, p=0.005), but the same research support. Conclusions: Clinical activities, specifically chemotherapy prescribing, and support differ for male and female GOs and may explain gender inequities. Clinical support should be equalized to maximize workplace productivity regardless of gender. Coordination of support between the practice and hospital and standard compensation for chemotherapy prescribing could decrease the large gender wage gap in this specialty.[Table: see text]

IMPROVING PATIENT PARTICIPATION IN LONGITUDINAL RESEARCH: AN INNOVATIVE PATIENT-LED PATIENT-ORIENTED QUALITATIVE RESEARCH PROJECT TO UNDERSTAND THE MOTIVATIONS AND BARRIERS TO GETTING AND STAYING INVOLVED IN THE IMAGINE SPOR STUDY

Abstract Background The Inflammation, Microbiome, & Alimentation, Gastro-Intestinal & Neuropsychiatric Effects (IMAGINE) Strategy for Patient-Oriented Research (SPOR) Network is conducting a large longitudinal research study to investigate the interactions between inflammation, microbiome, diet, and mental health in patients with inflammatory bowel disease (IBD) and irritable bowel syndrome (IBS). This study aims to recruit 2000 patients with Crohn’s disease, 2000 with ulcerative colitis, 2000 with IBS, and 2000 healthy controls. Each subject is assessed annually for 4 years and is asked to submit blood, urine, and stool samples, and complete online questionnaires on their health status. Given the ambitious recruitment target, a group of IMAGINE Patient Research Partners (PRPs) led a qualitative study to better understand the motivations and barriers of healthy controls to participating in this study to inform more effective recruitment and retention strategies. Methods This study has been co-led, co-designed, and executed by IMAGINE’s PRPs with support from academic researchers. PRPs were trained in qualitative research, co-designed the interview guide, and developed a semi-structured interview guide. Qualitative semi-structured interviews were conducted by 7 PRPs and were recorded electronically. All of the interviews were transcribed by a PRP, a trained medical transcriptionist. Five PRPs conducted data analysis and coded the interview content into common themes. Results A total of 27 interviews (13 male and 14 female) were conducted. Participants ranged from 20–75 years old. The top four themes of key motivators to study participation that emerged were Convenience, Experience, Communication, and Compensation. The interview participants identified Convenience as being low time commitment, the flexibility of scheduling, multiple recruitment locations, or using a courier for collecting samples. The Experience category reflects the desire to stay involved if their experience is relaxed, hassle-free, and fun, with emphasis on the study being well-organized. Participants stressed the importance of Communication such as reminders, annual updates, and newsletters. Compensation was important to some participants such as gift cards, parking reimbursement, or non-monetary items such as thank you cards and tokens of appreciation. Conclusions This study was co-created by PRPs who were actively involved throughout all stages of the project. The results from this patient-led study will help inform adaptations to recruitment and retention strategies for the national IMAGINE SPOR study.

Post-implementation Evaluation of a Digital Dictation System in a Large Health Service Using HOT-Fit Framework

Objective: The objective of this study was to evaluate a digital dictation system (DDS) that has been implemented in a large health service. The data collected in this study was used to understand the overall uptake and performance of the system and consequently improve the quality of care delivered by the organisation. Methods: A mixed method research design was used in this study. Clinicians and Medical Transcriptionists using the DDS across the two campuses of the health service over a period of four months, were surveyed to assess the extent to which the implementation of the DDS is fulfilling its purpose. In addition, system usage statistics, project implementation documents and user support emails were also analysed. Results: This study utilised an existing comprehensive and validated evaluation framework, the Human, Organisation and Technology Fit (HOT-Fit) framework. Human fit: 79.55% (n=35) of Clinicians and 33.33% (n=2) of MTs reported an overall satisfaction with the DDS. Organisation fit: The document analysis revealed that the DDS selected aligned best with current organizational IT strategies and was an easy fit with existing practices. Technology fit: An overall satisfaction of 53.49% (n=23) from the Clinicians and 16.67% (n=1) from the MTs was reported on the DDS. Out of 22 issues lodged regarding the system, 77.27% (n=17) issues met the Service Level Agreement (SLA). Conclusions: The overall findings of the study suggest that, the DDS was a good fit within the organisation in terms of Human fit and Organisation fit. In terms of Technology fit there existed some technical issues on the end-user level due to the system being new to the end users. To overcome this and facilitate the smooth functioning of the DDS, effective communication with the vendor and other relevant stakeholders was recommended so that end users i.e. the Clinicians and MTs understand the system, its functionality and their role in providing timely and high-quality information for clinical care.

The Adjunct of Voice Recognition to Medical Transcriptionist in Asian Countries–The Pros and Cons

Voice recognition software (VRS) is a form of Artificial intelligence; it’s a phenomenon of converting or transcribing acoustic human speech (i.e. sound waves) into a symbolic form of a human language such as English whereas Dictaphone (DP) is an electronic voice recorder analogous to cell phone that saves and records voice files. The Radiologists believe that Report generation in Radiology is a daunting task, including reading scans, requiring analytical and observational skills, interpretation of findings, dictating cases, proof reading, re analyzing cases and signing off after corrections, especially when the case list is long. In solving this multi-step process, VRS and DP have emerged as handy tech savvy equipments for “automatic typing” of scans, with the involvement of Medical transcriptionist (MT) for timely generation of reports. In the past few decades, there has been considerable transition from manual hand signed reports to electronically generated reports. MT has been a closed companion of Radiologist, even in manually generated reports. There has been a threat to MT being replaced by VRS at tertiary care hospitals, because of its low economic impact. The pros and cons of tool are elaborated in this article with the survey of Radiology Institutes of Pakistan.

The Adjunct of Voice Recognition to Medical Transcriptionist in Asian Countries–The Pros and Cons

Voice recognition software (VRS) is a form of Artificial intelligence; it’s a phenomenon of converting or transcribing acoustic human speech (i.e. sound waves) into a symbolic form of a human language such as English whereas Dictaphone (DP) is an electronic voice recorder analogous to cell phone that saves and records voice files. The Radiologists believe that Report generation in Radiology is a daunting task, including reading scans, requiring analytical and observational skills, interpretation of findings, dictating cases, proof reading, re analyzing cases and signing off after corrections, especially when the case list is long. In solving this multi-step process, VRS and DP have emerged as handy tech savvy equipments for “automatic typing” of scans, with the involvement of Medical transcriptionist (MT) for timely generation of reports. In the past few decades, there has been considerable transition from manual hand signed reports to electronically generated reports. MT has been a closed companion of Radiologist, even in manually generated reports. There has been a threat to MT being replaced by VRS at tertiary care hospitals, because of its low economic impact. The pros and cons of tool are elaborated in this article with the survey of Radiology Institutes of Pakistan.

Analysis of Errors in Dictated Clinical Documents Assisted by Speech Recognition Software and Professional Transcriptionists

Accurate clinical documentation is critical to health care quality and safety. Dictation services supported by speech recognition (SR) technology and professional medical transcriptionists are widely used by US clinicians. However, the quality of SR-assisted documentation has not been thoroughly studied. To identify and analyze errors at each stage of the SR-assisted dictation process. This cross-sectional study collected a stratified random sample of 217 notes (83 office notes, 75 discharge summaries, and 59 operative notes) dictated by 144 physicians between January 1 and December 31, 2016, at 2 health care organizations using Dragon Medical 360 | eScription (Nuance). Errors were annotated in the SR engine-generated document (SR), the medical transcriptionist-edited document (MT), and the physician's signed note (SN). Each document was compared with a criterion standard created from the original audio recordings and medical record review. Error rate; mean errors per document; error frequency by general type (eg, deletion), semantic type (eg, medication), and clinical significance; and variations by physician characteristics, note type, and institution. Among the 217 notes, there were 144 unique dictating physicians: 44 female (30.6%) and 10 unknown sex (6.9%). Mean (SD) physician age was 52 (12.5) years (median [range] age, 54 [28-80] years). Among 121 physicians for whom specialty information was available (84.0%), 35 specialties were represented, including 45 surgeons (37.2%), 30 internists (24.8%), and 46 others (38.0%). The error rate in SR notes was 7.4% (ie, 7.4 errors per 100 words). It decreased to 0.4% after transcriptionist review and 0.3% in SNs. Overall, 96.3% of SR notes, 58.1% of MT notes, and 42.4% of SNs contained errors. Deletions were most common (34.7%), then insertions (27.0%). Among errors at the SR, MT, and SN stages, 15.8%, 26.9%, and 25.9%, respectively, involved clinical information, and 5.7%, 8.9%, and 6.4%, respectively, were clinically significant. Discharge summaries had higher mean SR error rates than other types (8.9% vs 6.6%; difference, 2.3%; 95% CI, 1.0%-3.6%; P < .001). Surgeons' SR notes had lower mean error rates than other physicians' (6.0% vs 8.1%; difference, 2.2%; 95% CI, 0.8%-3.5%; P = .002). One institution had a higher mean SR error rate (7.6% vs 6.6%; difference, 1.0%; 95% CI, -0.2% to 2.8%; P = .10) but lower mean MT and SN error rates (0.3% vs 0.7%; difference, -0.3%; 95% CI, -0.63% to -0.04%; P = .03 and 0.2% vs 0.6%; difference, -0.4%; 95% CI, -0.7% to -0.2%; P = .003). Seven in 100 words in SR-generated documents contain errors; many errors involve clinical information. That most errors are corrected before notes are signed demonstrates the importance of manual review, quality assurance, and auditing.

Syntactic and Semantic Errors in Radiology Reports Associated With Speech Recognition Software.

Speech recognition software (SRS) has many benefits, but also increases the frequency of errors in radiology reports, which could impact patient care. As part of a quality control project, 13 trained medical transcriptionists proofread 213,977 SRS-generated signed reports from 147 different radiologists over a 40 month time interval. Errors were classified as "material" if they were believed to alter interpretation of the report. "Immaterial" errors were subclassified as intrusion/omission or spelling errors. The proportion of errors and error type were compared among individual radiologists, imaging subspecialty, and time periods using .2 analysis and multiple logistic regression, as appropriate. 20,759 (9.7%) reports contained errors; 3,992 (1.9%) contained material errors. Among immaterial errors, spelling errors were more common than intrusion/omission errors (P&lt;.001). Error proportion varied significantly among radiologists and between imaging subspecialties (P&lt;.001). Errors were more common in cross-sectional reports (vs. plain radiography) (OR, 3.72), reports reinterpreting results of outside examinations (vs. in-house) (OR, 1.55), and procedural studies (vs. diagnostic) (OR, 1.91) (all P&lt;.001). Dictation microphone upgrade did not affect error rate (P=.06). Error rate decreased over time (P&lt;.001).

Error rates in physician dictation: quality assurance and medical record production.

The purpose of the paper is to determine the instance of errors made in physician dictation of medical records. Purposive sampling method was employed to select medical transcriptionists (MTs) as "experts" to identify the frequency and types of medical errors in dictation files. Seventy-nine MTs examined 2,391 dictation files during one standard work day, and used a common template to record errors. The results demonstrated that on the average, on the order of 315,000 errors in one million dictations were surfaced. This shows that medical errors occur in dictation, and quality assurance measures are needed in dealing with those errors. There was no potential for inter-coder reliability and confirming the error codes assigned by individual MTs. This study only examined the presence of errors in the dictation-transcription model. Finally, the project was done with the cooperation of MTSOs and transcription industry organizations. Anecdotal evidence points to the belief that records created directly by physicians alone will have fewer errors and thus be more accurate. This research demonstrates this is not necessarily the case when it comes to physician dictation. As a result, the place of quality assurance in the medical record production workflow needs to be carefully considered before implementing a "once-and-done" (i.e. physician-based) model of record creation. No other research has been published on the presence of errors or classification of errors in physician dictation. The paper questions the assumption that direct physician creation of medical records in the absence of secondary QA processes will result in higher quality documentation and fewer medical errors.

Cost-Benefit Analysis of Electronic Medical Record System at a Tertiary Care Hospital

ObjectivesAlthough Electronic Medical Record (EMR) systems provide various benefits, there are both advantages and disadvantages regarding its cost-effectiveness. This study analyzed the economic effects of EMR systems using a cost-benefit analysis based on the differential costs of managerial accounting.MethodsSamsung Medical Center (SMC) is a general hospital in Korea that developed an EMR system for outpatients from 2006 to 2008. This study measured the total costs and benefits during an 8-year period after EMR adoption. The costs include the system costs of building the EMR and the costs incurred in smoothing its adoption. The benefits included cost reductions after its adoption and additional revenues from both remodeling of paper-chart storage areas and medical transcriptionists' contribution. The measured amounts were discounted by SMC's expected interest rate to calculate the net present value (NPV), benefit-cost ratio (BCR), and discounted payback period (DPP).ResultsDuring the analysis period, the cumulative NPV and the BCR were US$3,617 thousand and 1.23, respectively. The DPP was about 6.18 years.ConclusionsAlthough the adoption of an EMR resulted in overall growth in administrative costs, it is cost-effective since the cumulative NPV was positive. The positive NPV was attributed to both cost reductions and additional revenues. EMR adoption is not so attractive to management in that the DPP is longer than 5 years at 6.18 and the BCR is near 1 at 1.23. However, an EMR is a worthwhile investment, seeing that this study did not include any qualitative benefits and that the paper-chart system was cost-centric.

Level of Billing as a Function of Resident Documentation and Orthopedic Subspecialty at an Academic Multispecialty Orthopedic Surgery Practice

Documentation, coding, and billing for physician-patient encounters have evolved over time and have significant variability. Appropriate and complete documentation of these encounters can contribute to the financial viability of private and academic medical centers. The objectives of this study were to assess the financial effect of documentation on billing and to compare the authors' institution's distribution of billing level compared with Medicare normative data. Four orthopedic surgery subspecialty clinics were evaluated at a university outpatient clinic over a 1-year period. A single full-day clinic per week was used for each subspecialty. Residents dictated the majority of the reports. All reports were transcribed by medical transcriptionists and coded by certified professional coders. The sports medicine subspecialty generated the highest volume of patient clinic visits, followed by foot and ankle, trauma, and spine (P<.01). The majority of the reports were billed at level 3 (P<.05). Significant differences existed between subspecialty and percentage distribution of billing level (P<.05). Compared with Medicare normative data, a significantly greater percentage of level 3 reports and a lower percentage of level 2 and 4 reports existed in the orthopedic practice (P<.01). The estimated loss of revenue from the fewer level 4 reports was $81,281.11 for 1 year. These findings highlight the need for greater educational interventions to improve provider documentation, coding, and billing. The effect of new electronic medical record systems that prompt providers to include key evaluation and management components will likely affect practices and warrant further analysis.

Factors affecting adherence to osteoporosis medications: a focus group approach examining viewpoints of patients and providers.

This qualitative study uses a focus group approach to determine factors influencing adherence to osteoporosis medications among older adults. Thirty-two patients aged 65 to 85 years from the Greater Boston area who were prescribed an osteoporosis medication, 11 general medicine physicians, and 1 nurse practitioner were recruited from Boston-based hospitals affiliated with a large health care system. Focus groups consisting of 6 to 8 subjects including men and women were held separately for providers and patients and conducted until thematic saturation was reached. Responses were obtained from patients and providers during the focus group interviews conducted by a trained focus group moderator. All interviews were audio taped and transcribed by a medical transcriptionist. According to patients, factors affecting adherence to osteoporosis drugs included lack of knowledge about osteoporosis, dissatisfaction with their doctor visits, side effects, and difficulty or failure to remember instructions for taking medications. Physicians reported lack of patient knowledge, structural barriers, medication side effects, and the inability to track patients' adherence to their medications as barriers to adherence. This study identifies the extent of and reasons for nonadherence as perceived by patients and providers and provides insights into strategies to modify treatment plans to address nonadherence. The results from this study were used to develop a randomized controlled trial to conduct and evaluate patient- and physician-targeted interventions to improve adherence to osteoporosis medications and to examine cost-effectiveness of alternative strategies.

Productivity of transcriptionists using a treadmill desk

Time spent sitting increases all-cause mortality. Sedentary occupations are a major contributor to the obesity epidemic. A treadmill desk offers the potential to increase activity while working; however, it is important to make sure that productivity does not decline. The purpose of this study is to evaluate productivity while using a treadmill desk. Eleven experienced medical transcriptionists participated in the study. Transcriptionists were given 4 hours training in the use of a treadmill desk. They were asked to transcribe tapes for 8 hours both while sitting and while using the treadmill desk. Speed and accuracy of transcription were compared as were the average expended calories per hour. The accuracy of transcription did not differ between sitting and walking transcriptions. The speed of transcription was 16% slower while walking than while sitting (p < 0.001). The transcriptionists expended 100 calories per hour more when they transcribed while walking than when they transcribed while sitting (p < 0.001). The treadmill desk offers a way to reduce sedentariness in the workplace and has potential to reduce employee obesity and health care costs. However, more than 4 hours of training will be necessary to prevent a significant drop in employee productivity.

A Study on Job Satisfaction Among Medical Transcriptionists

A Study on Job Satisfaction Among Medical Transcriptionists

A CAD Paradigm to Produce Zillij Style of Geometrical Patterns for Wooden Carvings

Speech recognition is a vital part in medical transciription. The existing speech recognition systems, that run as standalone desktop applications, fall short in many cases due to low accuracy rates and high processing time. The bottleneck in these systems, is the lack of computation power (in terms of processing power and memory) made accessible to them. This paper proposes a mobile-cloud collaborative approach for the automation of speech to text conversion. The model proposed leverages the power of cloud computing and the ubiquitous nature of mobile computing. Computing resthisces can be scaled up/down in the cloud (Elastic Computing) depending on the usage of the system. This kind of speech recognition framework has many real time applications such as IVR systems, Medical Transcription systems, Railway Enquiries, Jthisnalism, Interactive User Interfaces, etc. A generic framework is advantageous, because the speech models in the Automatic Speech Recognizer (ASR) could be trained according to the specific domain required, allowing wide usability. The proposed speech framework is used for medical transcription process. Medical transcription process involves a medical transcriptionist who listens to the recorded speech of a doctor and manually types a transcript file. This process is automated by using the proposed speech framework. With this system, the work of the medical transcriptionist is reduced to error checking in the auto generated transcript file. The entire model is developed for a mobile cloud environment considering the characteristics of cloud delivery models.

Understanding the work of medical transcriptionists in the production of medical records

Efforts to improve healthcare by reducing medical errors often center on the accuracy of medical records. At the same time, the impact of new technologies such as speech recognition technology on the process of producing medical records has not been sufficiently examined. In this article we analyzed interview data from medical transcriptionists (MTs) describing how they do the work of transcription to produce accurate medical records from doctors' dictation. We found that medical transcriptionists rely on several types of skills that current speech recognition technology lacks. We conclude with a discussion of the implications of these findings for the design and implementation of SRT systems for the production of medical records and for how the work of MTs can help reduce medical errors.

Correlates of Upper Extremity Disability in Medical Transcriptionists

To investigate the association between disability and personal/lifestyle, medical, and psychosocial risk factors for upper extremity musculoskeletal symptoms and disorders (UEMSDs) in medical transcriptionists. A web-based survey involving the Disabilities of the Arm, Shoulder and Hand (DASH), Perceived Stress Scale (PSS) and Overall Job Satisfaction (OJS) questionnaires of all medical transcriptionists working at a large healthcare facility. Responses were received from 80% (251 of 314) possible participants. Mean DASH, PSS, and OJS scores for those working at their current position for at least 1 year were 8.5 +/- 10.1, 14.3 +/- 6.7 and 5.3 +/- 0.9. Personal/lifestyle factors including age (P < 0.001), lower educational level (P = 0.014), current or previous smoking (P = 0.012), and limited exercise (P = 0.013); medical conditions including diabetes mellitus (P = 0.015), carpal tunnel syndrome (P < 0.001), prior treatment for upper extremity symptoms (P < 0.001); prior workstation evaluation (P < 0.001) and psychosocial factors of perceived stress (P < 0.001), are associated with increased DASH scores. In these workers, multivariate analysis suggests that medical conditions (finger or other upper extremity symptoms requiring treatment or workstation evaluation; and diabetes mellitus) have a larger effect on the DASH than personal/lifestyle or psychosocial factors (age; previous or current smoking; and perceived stress). Prior upper extremity musculoskeletal symptoms requiring treatment or ergonomic assessment, high perceived stress and a history of smoking are associated with self-reported disability. Diabetics have significantly higher levels of upper extremity disability than non-diabetics. Prospective studies are needed to see if interventions addressing these factors will prevent future work disability.