Does integrating nonurgent, clinically significant radiology alerts within the electronic health record impact closed-loop communication and follow-up?

Artificial intelligence in cardiac computed tomography

Artificial Intelligence (AI) is a broad discipline of computer science and engineering. Modern application of AI encompasses intelligent models and algorithms for automated data analysis and processing, data generation, and prediction with applications in visual perception, speech understanding, and language translation. AI in healthcare uses machine learning (ML) and other predictive analytical techniques to help sort through vast amounts of data and generate outputs that aid in diagnosis, clinical decision support, workflow automation, and prognostication. Coronary computed tomography angiography (CCTA) is an ideal union for these applications due to vast amounts of data generation and analysis during cardiac segmentation, coronary calcium scoring, plaque quantification, adipose tissue quantification, peri-operative planning, fractional flow reserve quantification, and cardiac event prediction. In the past 5 years, there has been an exponential increase in the number of studies exploring the use of AI for cardiac computed tomography (CT) image acquisition, de-noising, analysis, and prognosis. Beyond image processing, AI has also been applied to improve the imaging workflow in areas such as patient scheduling, urgent result notification, report generation, and report communication. In this review, we discuss algorithms applicable to AI and radiomic analysis; we then present a summary of current and emerging clinical applications of AI in cardiac CT. We conclude with AI's advantages and limitations in this new field.

Revenue and Cost Analysis of a System Utilizing Natural Language Processing and a Nurse Coordinator for Radiology Follow-up Recommendations

Radiology reports often contain recommendations for follow-up imaging, Provider adherence to these radiology recommendations can be incomplete, which may result in patient harm, lost revenue, or litigation. This study sought to perform a revenue assessment of a hybrid natural language processing (NLP) and human follow-up system. Reports generated from January 2020 to April 2021 that were indexed as overdue from follow-up recommendations by mPower Follow-Up Recommendation Algorithm (Nuance Communications Inc., Burlington, MA), were assessed for follow up and revenue. Follow-up exams completed because of the hybrid system were tabulated and given revenue amounts based on Medicare national reimbursement rates. These rates were then summated. A total of n =3011 patients were flagged via the mPower algorithm as having not received a timely follow-up indicated for procedure. Of these, n = 427 required the quality nurse to contact their healthcare provider to place orders. The follow-up imaging of these patients accounted for $62,937.66 of revenue. This revenue was calculated as higher than personnel cost (based on national average quality and safety nurse salary and time allotted on follow-ups). Our results indicate that a hybrid human-artificial intelligence follow-up system can be profitable, while potentially adding to patient safety. Our revenue figure likely significantly underestimates the true revenue obtained at our institution. This was due to the use of Medicare national reimbursement rates to calculate revenue, for the purposes of generalizability.

The Use of Artificial Intelligence (AI) in the Radiology Field: What Is the State of Doctor-Patient Communication in Cancer Diagnosis?

BACKGROUND

In the past decade, interest in applying Artificial Intelligence (AI) in radiology to improve diagnostic procedures increased. AI has potential benefits spanning all steps of the imaging chain, from the prescription of diagnostic tests to the communication of test reports. The use of AI in the field of radiology also poses challenges in doctor-patient communication at the time of the diagnosis. This systematic review focuses on the patient role and the interpersonal skills between patients and physicians when AI is implemented in cancer diagnosis communication.

METHODS

A systematic search was conducted on PubMed, Embase, Medline, Scopus, and PsycNet from 1990 to 2021. The search terms were: ("artificial intelligence" or "intelligence machine") and "communication" "radiology" and "oncology diagnosis". The PRISMA guidelines were followed.

RESULTS

517 records were identified, and 5 papers met the inclusion criteria and were analyzed. Most of the articles emphasized the success of the technological support of AI in radiology at the expense of patient trust in AI and patient-centered communication in cancer disease. Practical implications and future guidelines were discussed according to the results.

CONCLUSIONS

AI has proven to be beneficial in helping clinicians with diagnosis. Future research may improve patients' trust through adequate information about the advantageous use of AI and an increase in medical compliance with adequate training on doctor-patient diagnosis communication.

Urgent and unexpected findings in oncology and hematology patients: A practical approach to imaging

Urgent and unexpected findings are very common in oncology and haematology patients. This article reviews the most important points included in the European Society of Radiology's guidelines and proposes a practical approach to reporting and communicating these findings more efficiently. This approach is explained with illustrative examples. Radiologists can provide added value in the management of these findings by helping referring clinicians reach the best decisions. To this end, it is essential to know the imaging manifestations of the most common findings that must be reported urgently, such as the specific toxicity of different treatments, the complications of tumours and catheters, infections, and thrombosis. Moreover, it is crucial to consider the individual patient's treatment, risk factors, clinical situation, and immune status.

Novel Quality Measure Set: Closing the Completion Loop on Radiology Follow-up Recommendations for Noncritical Actionable Incidental Findings

BACKGROUND

Care gaps occur when radiology follow-up recommendations are poorly communicated or not completed, resulting in missed or delayed diagnosis potentially leading to worse patient outcomes. This ACR-led initiative assembled a technical expert panel (TEP) to advise development of quality measures intended to improve communication and drive increased completion rates for radiology follow-up recommendations.

MATERIALS AND METHODS

A multistakeholder TEP was assembled to advise the development of quality measures. The project scope, limited to noncritical actionable incidental findings (AIFs), encourages practices to develop and implement systems ensuring appropriate communication and follow-up to completion.

RESULTS

A suite of nine measures were developed: four outcome measures include closing the loop on completion of radiology follow-up recommendations for nonemergent AIFs (with pulmonary nodule and abdominal aortic aneurysm use cases) and overall cancer diagnoses. Five process measures address communication and tracking of AIFs: inclusion of available evidence or guidelines informing the recommendation, communication of AIFs to the practice managing ongoing care, identifying when AIFs have been communicated to the patient, and employing tracking and reminder systems for AIFs.

CONCLUSION

This ACR-led initiative developed a measure set intended to improve patient outcomes by ensuring that AIFs are appropriately communicated and followed up. The intent of these measures is to focus improvement on specific areas in which gaps in communication and AIF follow-up may occur, prompting systems to devote resources that will identify and implement solutions to improve patient care.

A Mixed-Methods Systematic Review of the Effectiveness and Experiences of Quality Improvement Interventions in Radiology

OBJECTIVE

This study aimed to compile and synthesize evidence regarding the effectiveness of quality improvement interventions in radiology and the experiences and perspectives of staff and patients.

METHODS

Databases searched for both published and unpublished studies were as follows: EMBASE, MEDLINE, CINAHL, Joanna Briggs Institute, Cochrane Central Register of Controlled Trials, PsycINFO, Scopus, Web of Science, Mednar, Trove, Google Gray, OCLC WorldCat, and Dissertations and Theses. This review included both qualitative and quantitative studies of patients undergoing radiological examinations and/or medical imaging health care professionals; a broad range of quality improvement interventions including introduction of health information technology, effects of training and education, improved reporting, safety programs, and medical devices; the experiences and perspectives of staff and patients; context of radiological setting; a broad range of outcomes including patient safety; and a result-based convergent synthesis design.

RESULTS

Eighteen studies were selected from 4846 identified by a systematic literature search. Five groups of interventions were identified: health information technology (n = 6), training and education (n = 6), immediate and critical reporting (n = 3), safety programs (n = 2), and the introduction of mobile radiography (n = 1), with demonstrated improvements in outcomes, such as improved operational and workflow efficiency, report turnaround time, and teamwork and communication.

CONCLUSIONS

The findings were constrained by the limited range of interventions and outcome measures. Further research should be conducted with study designs that might produce findings that are more generalizable, examine the other dimensions of quality, and address the issues of cost and risk versus benefit.

Workflow Applications of Artificial Intelligence in Radiology and an Overview of Available Tools

In the past decade, there has been tremendous interest in applying artificial intelligence (AI) to improve the field of radiology. Currently, numerous AI applications are in development, with potential benefits spanning all steps of the imaging chain from test ordering to report communication. AI has been proposed as a means to optimize patient scheduling, improve worklist management, enhance image acquisition, and help radiologists interpret diagnostic studies. Although the potential for AI in radiology appears almost endless, the field is still in the early stages, with many uses still theoretical, in development, or limited to single institutions. Moreover, although the current use of AI in radiology has emphasized its clinical applications, some of which are in the distant future, it is increasingly clear that AI algorithms could also be used in the more immediate future for a variety of noninterpretive and quality improvement uses. Such uses include the integration of AI into electronic health record systems to reduce unwarranted variation in radiologists' follow-up recommendations and to improve other dimensions of radiology report quality. In the end, the potential of AI in radiology must be balanced with acknowledgment of its current limitations regarding generalizability and data privacy.

Urgent and unexpected findings in oncology and hematology patients: a practical approach to imaging

Urgent and unexpected findings are very common in oncology and hematology patients. This article reviews the most important points included in the European Society of Radiology's guidelines and proposes a practical approach to reporting and communicating these findings more efficiently. This approach is explained with illustrative examples. Radiologists can provide added value in the management of these findings by helping referring clinicians reach the best decisions. To this end, it is essential to know the imaging manifestations of the most common findings that must be reported urgently, such as the specific toxicity of different treatments, the complications of tumors and catheters, infections, and thrombosis. Moreover, it is crucial to consider the individual patient's treatment, risk factors, clinical situation, and immune status.

Use of Electronic Health Record Access and Audit Logs to Identify Physician Actions Following Noninterruptive Alert Opening: Descriptive Study

Background

Electronic health record (EHR) access and audit logs record behaviors of providers as they navigate the EHR. These data can be used to better understand provider responses to EHR–based clinical decision support (CDS), shedding light on whether and why CDS is effective.

Objective

This study aimed to determine the feasibility of using EHR access and audit logs to track primary care physicians’ (PCPs’) opening of and response to noninterruptive alerts delivered to EHR InBaskets.

Methods

We conducted a descriptive study to assess the use of EHR log data to track provider behavior. We analyzed data recorded following opening of 799 noninterruptive alerts sent to 75 PCPs’ InBaskets through a prior randomized controlled trial. Three types of alerts highlighted new medication concerns for older patients’ posthospital discharge: information only (n=593), medication recommendations (n=37), and test recommendations (n=169). We sought log data to identify the person opening the alert and the timing and type of PCPs’ follow-up EHR actions (immediate vs by the end of the following day). We performed multivariate analyses examining associations between alert type, patient characteristics, provider characteristics, and contextual factors and likelihood of immediate or subsequent PCP action (general, medication-specific, or laboratory-specific actions). We describe challenges and strategies for log data use.

Results

We successfully identified the required data in EHR access and audit logs. More than three-quarters of alerts (78.5%, 627/799) were opened by the PCP to whom they were directed, allowing us to assess immediate PCP action; of these, 208 alerts were followed by immediate action. Expanding on our analyses to include alerts opened by staff or covering physicians, we found that an additional 330 of the 799 alerts demonstrated PCP action by the end of the following day. The remaining 261 alerts showed no PCP action. Compared to information-only alerts, the odds ratio (OR) of immediate action was 4.03 (95% CI 1.67-9.72) for medication-recommendation and 2.14 (95% CI 1.38-3.32) for test-recommendation alerts. Compared to information-only alerts, ORs of medication-specific action by end of the following day were significantly greater for medication recommendations (5.59; 95% CI 2.42-12.94) and test recommendations (1.71; 95% CI 1.09-2.68). We found a similar pattern for OR of laboratory-specific action. We encountered 2 main challenges: (1) Capturing a historical snapshot of EHR status (number of InBasket messages at time of alert delivery) required incorporation of data generated many months prior with longitudinal follow-up. (2) Accurately interpreting data elements required iterative work by a physician/data manager team taking action within the EHR and then examining audit logs to identify corresponding documentation.

Conclusions

EHR log data could inform future efforts and provide valuable information during development and refinement of CDS interventions. To address challenges, use of these data should be planned before implementing an EHR–based study.

Semiautomated System for Nonurgent, Clinically Significant Pathology Results

BACKGROUND

Failure of timely test result follow-up has consequences including delayed diagnosis and treatment, added costs, and potential patient harm. Closed-loop communication is key to ensure clinically significant test results (CSTRs) are acknowledged and acted upon appropriately. A previous implementation of the Alert Notification of Critical Results (ANCR) system to facilitate closed-loop communication of imaging CSTRs yielded improved communication of critical radiology results and enhanced adherence to institutional CSTR policies.

OBJECTIVE

This article extends the ANCR application to pathology and evaluates its impact on closed-loop communication of new malignancies, a common and important type of pathology CSTR.

MATERIALS AND METHODS

This Institutional Review Board-approved study was performed at a 150-bed community, academically affiliated hospital. ANCR was adapted for pathology CSTRs. Natural language processing was used on 30,774 pathology reports 13 months pre- and 13 months postintervention, identifying 5,595 reports with malignancies. Electronic health records were reviewed for documented acknowledgment for a random sample of reports. Percent of reports with documented acknowledgment within 15 days assessed institutional policy adherence. Time to acknowledgment was compared pre- versus postintervention and postintervention with and without ANCR alerts. Pathologists were surveyed regarding ANCR use and satisfaction.

RESULTS

Acknowledgment within 15 days was documented for 98 of 107 (91.6%) pre- and 89 of 103 (86.4%) postintervention reports (p = 0.2294). Median time to acknowledgment was 7 days (interquartile range [IQR], 3, 11) preintervention and 6 days (IQR, 2, 10) postintervention (p = 0.5083). Postintervention, median time to acknowledgment was 2 days (IQR, 1, 6) for reports with ANCR alerts versus 6 days (IQR, 2.75, 9) for reports without alerts (p = 0.0351). ANCR alerts were sent on 15 of 103 (15%) postintervention reports. All pathologists reported that the ANCR system positively impacted their workflow; 75% (three-fourths) felt that the ANCR system improved efficiency of communicating CSTRs.

CONCLUSION

ANCR expansion to facilitate closed-loop communication of pathology CSTRs was favorably perceived and associated with significant improved time to documented acknowledgment for new malignancies. The rate of adherence to institutional policy did not improve.

Missed Lung Cancer

The chest radiograph is one of the most commonly used imaging studies and is the modality of choice for initial evaluation of many common clinical scenarios. Over the last two decades, chest computed tomography has been increasingly used for a wide variety of indications, including respiratory illnesses, trauma, oncologic staging, and more recently lung cancer screening. Diagnostic radiologists should be familiar with the common causes of missed lung cancers on imaging studies in order to avoid detection and interpretation errors. Failure to detect these lesions can potentially have serious implications for both patients as well as the interpreting radiologist.

Assigning responsibility to close the loop on radiology test results

Failure to follow-up on test results represents a serious breakdown point in the diagnostic process which can lead to missed or delayed diagnoses and patient harm. Amidst discussions to ensure fail-safe test result follow-up, an important, yet under-discussed question emerges: how do we determine who is ultimately responsible for initiating follow-up action on the tests that are ordered? This seemingly simple question belies its true complexity. Although many of these complexities are also applicable to other diagnostic specialities, the field of medical imaging provides an ideal context to discuss the challenges of attributing responsibility of test result follow-up. In this review, we summarize several key concepts and challenges in the context of critical results, wet reads, and incidental findings to stimulate further discussion on responsibility issues in radiology. These discussions could help establish reliable closed-loop communication to ensure that every test result is sent, received, acknowledged and acted upon without failure.

Expanding the Scope of an Automated Radiology Recommendation-Tracking Engine: Initial Experiences and Lessons Learned

An automated radiology recommendation-tracking engine for incidental focal masses in the liver, pancreas, kidneys, and adrenal glands was launched within our institution in July 2013. For 2 years, the majority of CT, MR, and US examination reports generated within our health system were mined by the engine. However, the need to expand the system beyond the initial four organs was soon identified. In July 2015, the second phase of the system was implemented and expanded to include additional anatomic structures in the abdomen and pelvis, as well as to provide non-radiology and non-imaging options for follow-up. The most frequent organs with incidental findings, outside of the original four, included the ovaries and the endometrium, which also correlated to the most frequently ordered imaging follow-up study of pelvic ultrasound and non-imaging follow-up study of endometrial biopsies, respectively. The second phase expansion has demonstrated new venues for augmenting and improving radiologist roles in optimal communication and management of incidental findings.