Clinical applications of AI in MSK imaging: a liability perspective.

Artificial intelligence (AI) applications have been gaining traction across the radiology space, promising to redefine its workflow and delivery. However, they enter into an uncertain legal environment. This piece examines the nature, exposure, and theories of liability relevant to musculoskeletal radiologist practice. More specifically, it explores the negligence, vicarious liability, and product liability frameworks by way of illustrative vignettes.

Safeguarding Data Security in the Era of Imaging mHealth.

Mobile health (mHealth) technologies stand poised to find broad application in the radiology space. They hold considerable promise for millions of patients in the United States, enabling at-home imaging and augmenting clinical decision-making. However, they often lie outside the ambit of FDA regulation and process vast quantities of data largely unprotected by HIPAA. This article explores features of federal mHealth policy relevant to imaging practice and advocates for greater regulatory clarity to assist radiologists, developers, and ultimately, patients.

ACR Appropriateness Criteria® Movement Disorders and Neurodegenerative Diseases.

Movement disorders and neurodegenerative diseases are a variety of conditions that involve progressive neuronal degeneration, injury, or death. Establishing the correct diagnosis of a movement disorder or neurodegenerative process can be difficult due to the variable features of these conditions, unusual clinical presentations, and overlapping symptoms and characteristics. MRI has an important role in the initial assessment of these patients, although a combination of imaging and laboratory and genetic tests is often needed for complete evaluation and management. This document summarizes the imaging appropriateness data for rapidly progressive dementia, chorea, Parkinsonian syndromes, suspected neurodegeneration with brain iron accumulation, and suspected motor neuron disease. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

How the FDA Regulates AI.

Recent years have seen digital technologies increasingly leveraged to multiply conventional imaging modalities' diagnostic power. Artificial intelligence (AI) is most prominent among these in the radiology space, touted as the "stethoscope of the 21st century" for its potential to revolutionize diagnostic precision, provider workflow, and healthcare expenditure. Partially owing to AI's unique characteristics, and partially due to its novelty, existing regulatory paradigms are not well suited to balancing patient safety with furthering the growth of this new sector. The current review examines the historic, current, and proposed regulatory treatment of AI-empowered medical devices by the US Food and Drug Administration (FDA). An innovative framework proposed by the FDA seeks to address these issues by looking to current good manufacturing practices (cGMP) and adopting a total product lifecycle (TPLC) approach. If brought into force, this may reduce the regulatory burden incumbent on developers, while holding them to rigorous quality standards, maximizing safety, and permitting the field to mature.

Characteristics of Paid Malpractice Claims Among Resident Physicians From 2001 to 2015 in the United States.

PURPOSE: Limited information exists about medical malpractice claims against physicians-in-training. Data on residents' involvement in malpractice actions may inform perceptions about medicolegal liability and influence clinical decision-making at a formative stage. This study aimed to characterize rates and payment amounts of paid malpractice claims on behalf of resident physicians in the United States. METHOD: Using data from the National Practitioner Data Bank, 1,248 paid malpractice claims against resident physicians (interns, residents, and fellows) from 2001 to 2015, representing 1,632,471 residents-years, were analyzed. Temporal trends in overall and specialty-specific paid claim rates, payment amounts, catastrophic (> $1 million) and small (< $100,000) payments, and other claim characteristics were assessed. Payment amounts were compared with attending physicians during the same time period. RESULTS: The overall paid malpractice claim rate was 0.76 per 1,000 resident-years from 2001 to 2015. Among 1,194 unique residents with paid claims, 95.7% had exactly 1 claim, while 4.3% had 2-4 claims during training. Specialty-specific paid claim rates ranged from 0.12 per 1,000 resident-years (pathology) to 2.96 (obstetrics and gynecology). Overall paid claim rates decreased by 52% from 2001-2005 to 2011-2015 (95% confidence interval [CI]: 0.45, 0.59). Median inflation-adjusted payment amount was $199,024 (2015 dollars), not significantly different from payments made on behalf of attending physicians during the same period. Proportions of catastrophic (11.2%) and small (33.1%) claims did not significantly change over the study period. CONCLUSIONS: From 2001 to 2015, paid malpractice claim rates on behalf of resident physicians decreased by 52%, while median payment amounts were stable. Resident paid claim rates were lower than attending physicians, while payment amounts were similar.

Gadolinium Deposition Disease: A New Risk Management Threat.

Gadolinium-based contrast agents (GBCAs) have enjoyed wide use since their introduction some 30 years ago. Used in as many as 30% of MRIs performed in the United States, GBCAs have generally been associated with low rates of adverse events. However, the safety profile and attendant medicolegal liability associated with GBCAs changed in 2016 with the description of gadolinium deposition disease (GDD). Despite being unproven scientifically, a groundswell of GDD-related litigation and personal injury advertising targeting potential GDD patients has occurred. In this article, we describe what GDD is, why GDD has created medicolegal risk, and how this risk might be mitigated. This article advocates using a risk mitigation strategy focused on reducing brain gadolinium retention during the period of purported GDD development. As such, based on the currently available data, the authors recommend the preferential use of gadoteridol as the default GBCA for MRI imaging.

ACR Appropriateness Criteria® Thyroid Disease.

There are a wide variety of diseases that affect the thyroid gland ranging from hyperplastic to neoplastic, autoimmune, or inflammatory. They can present with functional abnormality or a palpable structural change. Imaging has a key role in diagnosing and characterizing the thyroid finding for management. Imaging is also essential in the management of thyroid cancer. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

ACR Appropriateness Criteria® Ataxia.

Ataxia can result from an abnormality in the cerebellum, spinal cord, peripheral nerves, and/or vestibular system. Pathology involving the brain, such as infarct or hydrocephalus, can also present with ataxia as part of the symptom constitution, or result in symptoms that mimic ataxia. Clinical evaluation by history and careful neurological examination is important to help with lesion localization, and helps determine where imaging should be focused. In the setting of trauma with the area of suspicion in the brain, a head CT without intravenous contrast is the preferred initial imaging choice. If vascular injury is suspected, CTA of the neck can be helpful. When the area of suspicion is in the spine, CT or MRI of the spine can be considered to assess for bony or soft-tissue injury, respectively. In the setting of ataxia unrelated to recent trauma, MRI is the preferred imaging modality, tailored to assess the brain or spine depending on the area of suspected pathology. The use of intravenous contrast is generally helpful. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

Impact of Primary Care Physician Interaction on Longitudinal Adherence to Screening Mammography Across Different Racial/Ethnic Groups.

PURPOSE: Regular contact with a primary care physician (PCP) is associated with increased participation in screening mammography. Older studies suggested that PCP interaction may have a smaller effect on screening mammography uptake among racial and ethnic minorities compared with whites, but there is limited contemporary evidence about the effect of PCP interaction on screening mammography uptake across different racial and ethnic groups. The purpose of this study was to evaluate the association between PCP contact and longitudinal adherence with screening mammography guidelines over a 10-year period across different racial/ethnic groups. METHODS: This HIPAA-compliant and institutional review board-approved retrospective single-institution study included women between the ages of 50 and 64 years who underwent screening mammography in the calendar year of 2005. The primary outcome of interest was adherence to recommended screening mammography guidelines (yes or no) at each 2-year interval from their index screening mammographic examination in 2005 until 2015. Patients were defined as having a high level of PCP interaction if their PCPs were listed in the electronic medical record within the top three providers with whom the patients had the most visits during the study period. Generalized estimating equation models were used to estimate the effect of high PCP interaction on screening mammography adherence while adjusting for correlated observations and patient characteristics. RESULTS: Patients in the high PCP interaction group had increased longitudinal adherence to recommended screening mammography (adjusted odds ratio [OR], 1.51; 95% confidence interval [CI], 1.42-1.73; P < .001). This was observed in stratified analyses for all self-reported racial groups, including white (adjusted OR, 1.51; 95% CI, 1.36-1.68; P < .001), black (adjusted OR, 1.93; 95% CI, 1.31-2.86; P = .001), Hispanic (adjusted OR, 1.92; 95% CI, 1.27-2.87; P = .002), Asian (adjusted OR, 1.55; 95% CI, 1.01-2.39; P = .045), and other (adjusted OR, 2.18; 95% CI, 1.32-3.56; P = .002), with no evidence of effect modification by race/ethnicity (P = .342). Medicaid (adjusted OR, 0.41; 95% CI, 0.31-0.53) and self-pay or other (adjusted OR, 0.39; 95% CI, 0.27-0.56) insurance categories were associated with decreased longitudinal adherence to recommended screening mammography (P < .001 for both). CONCLUSIONS: High levels of PCP interaction result in similar improvements in longitudinal screening mammography adherence for all racial/ethnic minority groups. Future efforts will require targeted outreach to assist Medicaid and uninsured patient populations overcome barriers to screening mammography adherence.

Curbing Inappropriate Usage of STAT Imaging at a Large Academic Medical Center.

PURPOSE: To evaluate a new system for processing and performing inpatient STAT diagnostic imaging with respect to utilization and time-based performance metrics. MATERIALS AND METHODS: This HIPAA-compliant study had institutional review board approval; informed consent was not required. The radiology information system of a large academic medical center was queried for all inpatient diagnostic imaging exams performed and interpreted from August 1, 2010, to October 31, 2012. Using customized software, data were evaluated based on order priority (non-STAT or STAT) and exam modality with respect to exam volume and time-based performance metrics (time-to-performance and preliminary interpretation time). Data were compared over 3 periods: August 1, 2010, to October 31, 2010 (preimplementation period); November 1, 2010, to October 31, 2011 (year 1 postimplementation); and November 1, 2011, to October 31, 2012 (year 2 postimplementation). RESULTS: In the first year after implementation of the new STAT policy, the percentage of inpatient exams ordered STAT significantly decreased from 22.1% to 5.4% (P < 0.001). This represented a proportional decrease of 26% (CT), 16% (MRI), 20% (US), and 24% (radiographs) relative to pre-STAT policy levels. The median time-to-performance and median preliminary interpretation time significantly decreased for all modalities after implementation of the policy (P < 0.05 for all modalities), decreasing by an average of 104 and 162 minutes, respectively. These changes persisted throughout year 2 postimplementation. CONCLUSION: A new institutional system for handling inpatient STAT diagnostic imaging results in a decreased number of STAT exams ordered and improved time-based performance metrics, thereby increasing workflow efficiency.

Chronic Medical Illness as a Risk Factor for Poor Mammography Screening Adherence.

Objective: The aim of this study was to determine the association between the presence of chronic medical disease and mammography screening adherence. Materials and Methods: We performed a retrospective study on women between the ages of 50 and 64 who received screening mammography in 2005 and had at least 8 years of follow-up. Demographic and clinical information was obtained from our centralized patient data registry. Women diagnosed with one or more of the following diseases for at least 3 months before their index mammogram were considered to have a chronic disease, including atrial fibrillation, congestive heart failure, Chronic Obstructive Pulmonary Disease (COPD), diabetes mellitus type II, heart disease, and/or peripheral vascular disease. Generalized estimating equations were used to evaluate for correlated observations. Multivariable regression analyses were used to evaluate the effects of selected chronic medical diseases on longitudinal engagement with routine mammography. Results: Of 9575 women identified, 1669 (17.7%) had one or more of the selected chronic medical diseases. The presence of one or more of these diseases was associated with reduced mammography screening (-0.29; confidence interval [CI] = -0.36 to -0.14; p < 0.01) compared with women without these diseases over the study period. Within this group, the presence of congestive heart failure (-0.88; CI = -0.84 to -0.45; p ≤ 0.01), COPD (-0.39; CI = -0.57 to -0.21; p ≤ 0.01), or diabetes mellitus type II (-0.37; CI = -0.57 to -0.17; p ≤ 0.01) was individually associated with reduced screening compared with women without the respective disease. Compared with women without chronic medical disease, women with multiple chronic medical diseases (-0.62; CI = -0.93 to -0.30; p ≤ 0.01) were significantly (p ≤ 0.05) less likely to receive routine screening, while no significant difference was seen in women with only one chronic medical disease (-0.18; CI = -0.39 to -0.02; p ≤ 0.08). Conclusion: Despite experiencing longer life expectancies, women with specific chronic diseases may experience additional barriers to uptake of mammography screening, which is likely compounded by the comorbidity burden of being simultaneously treated for multiple chronic conditions. Increased health care interactions seen in this group may represent missed opportunities to improve screening adherence.

Population-Based Health Engagement Opportunities Through Breast Imaging: A Population-Based Cross-Sectional Survey.

PURPOSE: As health care payment systems transition from fee-for-service to bundled payments, there is an increasing opportunity for radiologists to collaborate to improve population-based health care outcomes. Our purpose was to estimate the extent to which patients engaged in mammography underwent other additional imaging- and non-imaging-based preventative health services using Centers for Disease Control National Population Health Surveys. METHODS: Women aged 40 to 74 in the 2014 Behavioral Risk Factor Surveillance System cross-sectional survey without histories of breast cancer who reported having a mammogram within the past 2 years were included. Adherence to recommended preventative services was based on US Preventive Services Task Force Recommendations, relative to the time at which the survey participant responded to the survey. Among women reporting being engaged in mammography, proportions of eligible women obtaining recommended preventative health services were calculated and stratified by demographics. RESULTS: Of 172,245 women, 122,434 (71.1%) reported mammography within 2 years. The following percentages obtained recommended flu vaccines (49.2%), pneumococcal vaccines (69.5%), colorectal cancer screening (74.8%), and Papanicolaou test (93.2%). Women reporting mammography within the last 2 years with lower levels of education and income and who lacked health insurance or personal doctors were less likely to report receiving recommended preventative services (P < .001). CONCLUSIONS: National population-based survey results suggest that large proportions of women engaged in mammography report are not up to date with a wide variety of recommended preventative health services, suggesting ample opportunities for radiology practices to partner with providers to improve population-based health outcomes and add value to health care systems.

ACR Appropriateness Criteria® Orbits Vision and Visual Loss.

Visual loss can be the result of an abnormality anywhere along the visual pathway including the globe, optic nerve, optic chiasm, optic tract, thalamus, optic radiations or primary visual cortex. Appropriate imaging analysis of visual loss is facilitated by a compartmental approach that establishes a differential diagnosis on the basis of suspected lesion location and specific clinical features. CT and MRI are the primary imaging modalities used to evaluate patients with visual loss and are often complementary in evaluating these patients. One modality may be preferred over the other depending on the specific clinical scenario. Depending on the pattern of visual loss and differential diagnosis, imaging coverage may require targeted evaluation of the orbits and/or assessment of the brain. Contrast is preferred when masses and inflammatory processes are differential considerations. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

Impact of Delayed Time to Advanced Imaging on Missed Appointments Across Different Demographic and Socioeconomic Factors.

PURPOSE: The aim of this study was to investigate the impact of wait days (WDs) on missed outpatient MRI appointments across different demographic and socioeconomic factors. METHODS: An institutional review board-approved retrospective study was conducted among adult patients scheduled for outpatient MRI during a 12-month period. Scheduling data and demographic information were obtained. Imaging missed appointments were defined as missed scheduled imaging encounters. WDs were defined as the number of days from study order to appointment. Multivariate logistic regression was applied to assess the contribution of race and socioeconomic factors to missed appointments. Linear regression was performed to assess the relationship between missed appointment rates and WDs stratified by race, income, and patient insurance groups with analysis of covariance statistics. RESULTS: A total of 42,727 patients met the inclusion criteria. Mean WDs were 7.95 days. Multivariate regression showed increased odds ratio for missed appointments for patients with increased WDs (7-21 days: odds ratio [OR], 1.39; >21 days: OR, 1.77), African American patients (OR, 1.71), Hispanic patients (OR, 1.30), patients with noncommercial insurance (OR, 2.00-2.55), and those with imaging performed at the main hospital campus (OR, 1.51). Missed appointment rate linearly increased with WDs, with analysis of covariance revealing underrepresented minorities and Medicaid insurance as significant effect modifiers. CONCLUSIONS: Increased WDs for advanced imaging significantly increases the likelihood of missed appointments. This effect is most pronounced among underrepresented minorities and patients with lower socioeconomic status. Efforts to reduce WDs may improve equity in access to and utilization of advanced diagnostic imaging for all patients.

The Effect of Computer-Assisted Reporting on Interreader Variability of Lumbar Spine MRI Degenerative Findings: Five Readers With 30 Disc Levels.

PURPOSE: The aim of this study was to assess differences in interreader variability among radiologists after the implementation of a computer-assisted reporting (CAR) tool for the interpretation of degenerative disc disease on lumbar spine MRI. METHODS: Thirty lumbar spine MRI examinations were selected from the radiology database. Five fellowship-trained musculoskeletal radiologists evaluated each L4-L5 disc in a blinded fashion and reported the findings using a traditional free dictation approach. One month later, they reinterpreted the same discs using a web browser-based CAR tool in the same blinded fashion. The degrees of central canal stenosis, neural foraminal stenosis, and facet joint osteoarthritis; presence or absence of lateral recess stenosis; types of disc bulge or herniation; and herniation location using both methods were recorded. Percentage disagreement among the radiologists for each variable was calculated and compared using the Wilcoxon signed rank test. RESULTS: There was a statistically significant decrease among the five radiologists in percentage disagreement for neural foraminal stenosis (46% versus 35%, P = .0146) and facet joint osteoarthritis (45% and 22%, P < .0001) for reports created by free dictation compared with those created using the CAR tool. There was no statistically significant difference in interreader variability for the assessment of central canal stenosis, lateral recess effacement, disc herniation, disc bulge, or herniation location. CONCLUSIONS: Implementation of a CAR tool for the interpretation of degenerative changes on lumbar spine MRI decreases interreader variability in the assessment of neural foraminal stenosis and facet joint osteoarthritis.