How to discriminate between computer-aided and computer-hindered decisions: a case study in mammography

Spectrum of Cognitive Biases in Diagnostic Radiology

Cognitive biases are systematic thought processes involving the use of a filter of personal experiences and preferences arising from the tendency of the human brain to simplify information processing, especially when taking in vast amounts of data such as from imaging studies. These biases encompass a wide spectrum of thought processes and frequently overlap in their concepts, with multiple biases usually in operation when interpretive and perceptual errors occur in radiology. The authors review the gamut of cognitive biases that occur in radiology. These biases are organized according to their expected stage of occurrence while the radiologist reads and interprets an imaging study. In addition, the authors propose several additional cognitive biases that have not yet, to their knowledge, been defined in the radiologic literature but are applicable to diagnostic radiology. Case examples are used to illustrate potential biases and their impact, with emergency radiology serving as the clinical paradigm, given the associated high imaging volumes, wide diversity of imaging examinations, and rapid pace, which can further increase a radiologist's reliance on biases and heuristics. Potential strategies to recognize and overcome one's personal biases at each stage of image interpretation are also discussed. Awareness of such biases and their unintended effects on imaging interpretations and patient outcomes may help make radiologists cognizant of their own biases that can result in diagnostic errors. Identification of cognitive bias in departmental and systematic quality improvement practices may represent another tool to prevent diagnostic errors in radiology. ©RSNA, 2024 See the invited commentary by Larson in this issue.

Diagnostic decisions of specialist optometrists exposed to ambiguous deep-learning outputs

Artificial intelligence (AI) has great potential in ophthalmology. We investigated how ambiguous outputs from an AI diagnostic support system (AI-DSS) affected diagnostic responses from optometrists when assessing cases of suspected retinal disease. Thirty optometrists (15 more experienced, 15 less) assessed 30 clinical cases. For ten, participants saw an optical coherence tomography (OCT) scan, basic clinical information and retinal photography ('no AI'). For another ten, they were also given AI-generated OCT-based probabilistic diagnoses ('AI diagnosis'); and for ten, both AI-diagnosis and AI-generated OCT segmentations ('AI diagnosis + segmentation') were provided. Cases were matched across the three types of presentation and were selected to include 40% ambiguous and 20% incorrect AI outputs. Optometrist diagnostic agreement with the predefined reference standard was lowest for 'AI diagnosis + segmentation' (204/300, 68%) compared to 'AI diagnosis' (224/300, 75% p = 0.010), and 'no Al' (242/300, 81%, p =  < 0.001). Agreement with AI diagnosis consistent with the reference standard decreased (174/210 vs 199/210, p = 0.003), but participants trusted the AI more (p = 0.029) with segmentations. Practitioner experience did not affect diagnostic responses (p = 0.24). More experienced participants were more confident (p = 0.012) and trusted the AI less (p = 0.038). Our findings also highlight issues around reference standard definition.

Radiomics and artificial intelligence for risk stratification of pulmonary nodules: Ready for primetime?

Pulmonary nodules are ubiquitously found on computed tomography (CT) imaging either incidentally or via lung cancer screening and require careful diagnostic evaluation and management to both diagnose malignancy when present and avoid unnecessary biopsy of benign lesions. To engage in this complex decision-making, clinicians must first risk stratify pulmonary nodules to determine what the best course of action should be. Recent developments in imaging technology, computer processing power, and artificial intelligence algorithms have yielded radiomics-based computer-aided diagnosis tools that use CT imaging data including features invisible to the naked human eye to predict pulmonary nodule malignancy risk and are designed to be used as a supplement to routine clinical risk assessment. These tools vary widely in their algorithm construction, internal and external validation populations, intended-use populations, and commercial availability. While several clinical validation studies have been published, robust clinical utility and clinical effectiveness data are not yet currently available. However, there is reason for optimism as ongoing and future studies aim to target this knowledge gap, in the hopes of improving the diagnostic process for patients with pulmonary nodules.

Technical/Algorithm, Stakeholder, and Society (TASS) barriers to the application of artificial intelligence in medicine: A systematic review

INTRODUCTION

The use of artificial intelligence (AI), particularly machine learning and predictive analytics, has shown great promise in health care. Despite its strong potential, there has been limited use in health care settings. In this systematic review, we aim to determine the main barriers to successful implementation of AI in healthcare and discuss potential ways to overcome these challenges.

METHODS

We conducted a literature search in PubMed (1/1/2001-1/1/2023). The search was restricted to publications in the English language, and human study subjects. We excluded articles that did not discuss AI, machine learning, predictive analytics, and barriers to the use of these techniques in health care. Using grounded theory methodology, we abstracted concepts to identify major barriers to AI use in medicine.

RESULTS

We identified a total of 2,382 articles. After reviewing the 306 included papers, we developed 19 major themes, which we categorized into three levels: the Technical/Algorithm, Stakeholder, and Social levels (TASS). These themes included: Lack of Explainability, Need for Validation Protocols, Need for Standards for Interoperability, Need for Reporting Guidelines, Need for Standardization of Performance Metrics, Lack of Plan for Updating Algorithm, Job Loss, Skills Loss, Workflow Challenges, Loss of Patient Autonomy and Consent, Disturbing the Patient-Clinician Relationship, Lack of Trust in AI, Logistical Challenges, Lack of strategic plan, Lack of Cost-effectiveness Analysis and Proof of Efficacy, Privacy, Liability, Bias and Social Justice, and Education.

CONCLUSION

We identified 19 major barriers to the use of AI in healthcare and categorized them into three levels: the Technical/Algorithm, Stakeholder, and Social levels (TASS). Future studies should expand on barriers in pediatric care and focus on developing clearly defined protocols to overcome these barriers.

Artificial intelligence in medicine: has the time come to hang up the stethoscope?

The question of whether the time has come to hang up the stethoscope is bound up in the promises of artificial intelligence (AI), promises that have so far proven difficult to deliver, perhaps because of the mismatch between the technical capability of AI and its use in real-world clinical settings. This perspective argues that it is time to move away from discussing the generalised promise of disembodied AI and focus on specifics. We need to focus on how the computational method underlying AI, i.e. machine learning (ML), is embedded into tools, how those tools contribute to clinical tasks and decisions and to what extent they can be relied on. Accordingly, we pose four questions that must be asked to make the discussion real and to understand how ML tools contribute to health care: (1) What does the ML algorithm do? (2) How is output of the ML algorithm used in clinical tools? (3) What does the ML tool contribute to clinical tasks or decisions? (4) Can clinicians act or rely on the ML tool? Two exemplar ML tools are examined to show how these questions can be used to better understand the role of ML in supporting clinical tasks and decisions. Ultimately, ML is just a fancy method of automation. We show that it is useful in automating specific and narrowly defined clinical tasks but likely incapable of automating the full gamut of decisions and tasks performed by clinicians.

Analyzing Barriers and Enablers for the Acceptance of Artificial Intelligence Innovations into Radiology Practice: A Scoping Review

OBJECTIVES

This scoping review was conducted to determine the barriers and enablers associated with the acceptance of artificial intelligence/machine learning (AI/ML)-enabled innovations into radiology practice from a physician's perspective.

METHODS

A systematic search was performed using Ovid Medline and Embase. Keywords were used to generate refined queries with the inclusion of computer-aided diagnosis, artificial intelligence, and barriers and enablers. Three reviewers assessed the articles, with a fourth reviewer used for disagreements. The risk of bias was mitigated by including both quantitative and qualitative studies.

RESULTS

An electronic search from January 2000 to 2023 identified 513 studies. Twelve articles were found to fulfill the inclusion criteria: qualitative studies (n = 4), survey studies (n = 7), and randomized controlled trials (RCT) (n = 1). Among the most common barriers to AI implementation into radiology practice were radiologists' lack of acceptance and trust in AI innovations; a lack of awareness, knowledge, and familiarity with the technology; and perceived threat to the professional autonomy of radiologists. The most important identified AI implementation enablers were high expectations of AI's potential added value; the potential to decrease errors in diagnosis; the potential to increase efficiency when reaching a diagnosis; and the potential to improve the quality of patient care.

CONCLUSIONS

This scoping review found that few studies have been designed specifically to identify barriers and enablers to the acceptance of AI in radiology practice. The majority of studies have assessed the perception of AI replacing radiologists, rather than other barriers or enablers in the adoption of AI. To comprehensively evaluate the potential advantages and disadvantages of integrating AI innovations into radiology practice, gathering more robust research evidence on stakeholder perspectives and attitudes is essential.

Effect of Human-AI Interaction on Detection of Malignant Lung Nodules on Chest Radiographs

Background The factors affecting radiologists' diagnostic determinations in artificial intelligence (AI)-assisted image reading remain underexplored. Purpose To assess how AI diagnostic performance and reader characteristics influence detection of malignant lung nodules during AI-assisted reading of chest radiographs. Materials and Methods This retrospective study consisted of two reading sessions from April 2021 to June 2021. Based on the first session without AI assistance, 30 readers were assigned into two groups with equivalent areas under the free-response receiver operating characteristic curve (AUFROCs). In the second session, each group reinterpreted radiographs assisted by either a high or low accuracy AI model (blinded to the fact that two different AI models were used). Reader performance for detecting lung cancer and reader susceptibility (changing the original reading following the AI suggestion) were compared. A generalized linear mixed model was used to identify the factors influencing AI-assisted detection performance, including readers' attitudes and experiences of AI and Grit score. Results Of the 120 chest radiographs assessed, 60 were obtained in patients with lung cancer (mean age, 67 years ± 12 [SD]; 32 male; 63 cancers) and 60 in controls (mean age, 67 years ± 12; 36 male). Readers included 20 thoracic radiologists (5-18 years of experience) and 10 radiology residents (2-3 years of experience). Use of the high accuracy AI model improved readers' detection performance to a greater extent than use of the low accuracy AI model (area under the receiver operating characteristic curve, 0.77 to 0.82 vs 0.75 to 0.75; AUFROC, 0.71 to 0.79 vs 0.7 to 0.72). Readers who used the high accuracy AI showed a higher susceptibility (67%, 224 of 334 cases) to changing their diagnosis based on the AI suggestions than those using the low accuracy AI (59%, 229 of 386 cases). Accurate readings at the first session, correct AI suggestions, high accuracy Al, and diagnostic difficulty were associated with accurate AI-assisted readings, but readers' characteristics were not. Conclusion An AI model with high diagnostic accuracy led to improved performance of radiologists in detecting lung cancer on chest radiographs and increased radiologists' susceptibility to AI suggestions. © RSNA, 2023 Supplemental material is available for this article.

Artificial Intelligence in Ophthalmology - Status Quo and Future Perspectives

Artificial intelligence (AI) is an emerging technology in healthcare and holds the potential to disrupt many arms in medical care. In particular, disciplines using medical imaging modalities, including e.g. radiology but ophthalmology as well, are already confronted with a wide variety of AI implications. In ophthalmologic research, AI has demonstrated promising results limited to specific diseases and imaging tools, respectively. Yet, implementation of AI in clinical routine is not widely spread due to availability, heterogeneity in imaging techniques and AI methods. In order to describe the status quo, this narrational review provides a brief introduction to AI ("what the ophthalmologist needs to know"), followed by an overview of different AI-based applications in ophthalmology and a discussion on future challenges.Abbreviations: Age-related macular degeneration, AMD; Artificial intelligence, AI; Anterior segment OCT, AS-OCT; Coronary artery calcium score, CACS; Convolutional neural network, CNN; Deep convolutional neural network, DCNN; Diabetic retinopathy, DR; Machine learning, ML; Optical coherence tomography, OCT; Retinopathy of prematurity, ROP; Support vector machine, SVM; Thyroid-associated ophthalmopathy, TAO.

Artificial Intelligence in Pediatric Nephrology-A Call for Action

Artificial intelligence is playing an increasingly important role in many fields of clinical care to assist health care providers in patient management. In adult-focused nephrology, artificial intelligence is beginning to be used to improve clinical care, hemodialysis prescriptions, and follow-up of transplant recipients. This article provides an overview of medical artificial intelligence applications relevant to pediatric nephrology. We describe the core concepts of artificial intelligence and machine learning and cover the basics of neural networks and deep learning. We also discuss some examples for clinical applications of artificial intelligence in pediatric nephrology, including neonatal kidney function, early recognition of acute kidney injury, renally cleared drug dosing, intrapatient variability, urinary tract infection workup in infancy, and longitudinal disease progression. Furthermore, we consider the future of artificial intelligence in clinical pediatric nephrology and its potential impact on medical practice and address the ethical issues artificial intelligence raises in terms of clinical decision-making, health care provider-patient relationship, patient privacy, and data collection. This article also represents a call for action involving those of us striving to provide optimal services for children, adolescents, and young adults with chronic conditions.

Expectations for Artificial Intelligence (AI) in Psychiatry

PURPOSE OF REVIEW

Artificial intelligence (AI) is often presented as a transformative technology for clinical medicine even though the current technology maturity of AI is low. The purpose of this narrative review is to describe the complex reasons for the low technology maturity and set realistic expectations for the safe, routine use of AI in clinical medicine.

RECENT FINDINGS

For AI to be productive in clinical medicine, many diverse factors that contribute to the low maturity level need to be addressed. These include technical problems such as data quality, dataset shift, black-box opacity, validation and regulatory challenges, and human factors such as a lack of education in AI, workflow changes, automation bias, and deskilling. There will also be new and unanticipated safety risks with the introduction of AI. The solutions to these issues are complex and will take time to discover, develop, validate, and implement. However, addressing the many problems in a methodical manner will expedite the safe and beneficial use of AI to augment medical decision making in psychiatry.

Considerations for artificial intelligence clinical impact in oncologic imaging: an AI4HI position paper

To achieve clinical impact in daily oncological practice, emerging AI-based cancer imaging research needs to have clearly defined medical focus, AI methods, and outcomes to be estimated. AI-supported cancer imaging should predict major relevant clinical endpoints, aiming to extract associations and draw inferences in a fair, robust, and trustworthy way. AI-assisted solutions as medical devices, developed using multicenter heterogeneous datasets, should be targeted to have an impact on the clinical care pathway. When designing an AI-based research study in oncologic imaging, ensuring clinical impact in AI solutions requires careful consideration of key aspects, including target population selection, sample size definition, standards, and common data elements utilization, balanced dataset splitting, appropriate validation methodology, adequate ground truth, and careful selection of clinical endpoints. Endpoints may be pathology hallmarks, disease behavior, treatment response, or patient prognosis. Ensuring ethical, safety, and privacy considerations are also mandatory before clinical validation is performed. The Artificial Intelligence for Health Imaging (AI4HI) Clinical Working Group has discussed and present in this paper some indicative Machine Learning (ML) enabled decision-support solutions currently under research in the AI4HI projects, as well as the main considerations and requirements that AI solutions should have from a clinical perspective, which can be adopted into clinical practice. If effectively designed, implemented, and validated, cancer imaging AI-supported tools will have the potential to revolutionize the field of precision medicine in oncology.

Differential diagnosis checklists reduce diagnostic error differentially: A randomised experiment

INTRODUCTION

Wrong and missed diagnoses contribute substantially to medical error. Can a prompt to generate alternative diagnoses (prompt) or a differential diagnosis checklist (DDXC) increase diagnostic accuracy? How do these interventions affect the diagnostic process and self-monitoring?

METHODS

Advanced medical students (N = 90) were randomly assigned to one of four conditions to complete six computer-based patient cases: group 1 (prompt) was instructed to write down all diagnoses they considered while acquiring diagnostic test results and to finally rank them. Groups 2 and 3 received the same instruction plus a list of 17 differential diagnoses for the chief complaint of the patient. For half of the cases, the DDXC contained the correct diagnosis (DDXC+), and for the other half, it did not (DDXC-; counterbalanced). Group 4 (control) was only instructed to indicate their final diagnosis. Mixed-effects models were used to analyse results.

RESULTS

Students using a DDXC that contained the correct diagnosis had better diagnostic accuracy, mean (standard deviation), 0.75 (0.44), compared to controls without a checklist, 0.49 (0.50), P < 0.001, but those using a DDXC that did not contain the correct diagnosis did slightly worse, 0.43 (0.50), P = 0.602. The number and relevance of diagnostic tests acquired were not affected by condition, nor was self-monitoring. However, participants spent more time on a case in the DDXC-, 4:20 min (2:36), P ≤ 0.001, and DDXC+ condition, 3:52 min (2:09), than in the control condition, 2:59 min (1:44), P ≤ 0.001.

DISCUSSION

Being provided a list of possible diagnoses improves diagnostic accuracy compared with a prompt to create a differential diagnosis list, if the provided list contains the correct diagnosis. However, being provided a diagnosis list without the correct diagnosis did not improve and might have slightly reduced diagnostic accuracy. Interventions neither affected information gathering nor self-monitoring.

Ethics of Artificial Intelligence in Medicine and Ophthalmology

BACKGROUND

This review explores the bioethical implementation of artificial intelligence (AI) in medicine and in ophthalmology. AI, which was first introduced in the 1950s, is defined as "the machine simulation of human mental reasoning, decision making, and behavior". The increased power of computing, expansion of storage capacity, and compilation of medical big data helped the AI implementation surge in medical practice and research. Ophthalmology is a leading medical specialty in applying AI in screening, diagnosis, and treatment. The first Food and Drug Administration approved autonomous diagnostic system served to diagnose and classify diabetic retinopathy. Other ophthalmic conditions such as age-related macular degeneration, glaucoma, retinopathy of prematurity, and congenital cataract, among others, implemented AI too.

PURPOSE

To review the contemporary literature of the bioethical issues of AI in medicine and ophthalmology, classify ethical issues in medical AI, and suggest possible standardizations of ethical frameworks for AI implementation.

METHODS

Keywords were searched on Google Scholar and PubMed between October 2019 and April 2020. The results were reviewed, cross-referenced, and summarized. A total of 284 references including articles, books, book chapters, and regulatory reports and statements were reviewed, and those that were relevant were cited in the paper.

RESULTS

Most sources that studied the use of AI in medicine explored the ethical aspects. Bioethical challenges of AI implementation in medicine were categorized into 6 main categories. These include machine training ethics, machine accuracy ethics, patient-related ethics, physician-related ethics, shared ethics, and roles of regulators.

CONCLUSIONS

There are multiple stakeholders in the ethical issues surrounding AI in medicine and ophthalmology. Attention to the various aspects of ethics related to AI is important especially with the expanding use of AI. Solutions of ethical problems are envisioned to be multifactorial.

Do as AI say: susceptibility in deployment of clinical decision-aids

Artificial intelligence (AI) models for decision support have been developed for clinical settings such as radiology, but little work evaluates the potential impact of such systems. In this study, physicians received chest X-rays and diagnostic advice, some of which was inaccurate, and were asked to evaluate advice quality and make diagnoses. All advice was generated by human experts, but some was labeled as coming from an AI system. As a group, radiologists rated advice as lower quality when it appeared to come from an AI system; physicians with less task-expertise did not. Diagnostic accuracy was significantly worse when participants received inaccurate advice, regardless of the purported source. This work raises important considerations for how advice, AI and non-AI, should be deployed in clinical environments.

Not all biases are bad: equitable and inequitable biases in machine learning and radiology

The application of machine learning (ML) technologies in medicine generally but also in radiology more specifically is hoped to improve clinical processes and the provision of healthcare. A central motivation in this regard is to advance patient treatment by reducing human error and increasing the accuracy of prognosis, diagnosis and therapy decisions. There is, however, also increasing awareness about bias in ML technologies and its potentially harmful consequences. Biases refer to systematic distortions of datasets, algorithms, or human decision making. These systematic distortions are understood to have negative effects on the quality of an outcome in terms of accuracy, fairness, or transparency. But biases are not only a technical problem that requires a technical solution. Because they often also have a social dimension, the 'distorted' outcomes they yield often have implications for equity. This paper assesses different types of biases that can emerge within applications of ML in radiology, and discusses in what cases such biases are problematic. Drawing upon theories of equity in healthcare, we argue that while some biases are harmful and should be acted upon, others might be unproblematic and even desirable-exactly because they can contribute to overcome inequities.

Creating a Learning Televillage and Automated Digital Child Health Ecosystem

This article explores the impact of digital technologies, including telehealth, teleconsultations, wireless devices, and chatbots, in pediatrics. Automated digital health with the Internet of things will allow better collection of real-world data for generation of real-world evidence to improve child health. Artificial intelligence with predictive analytics in turn will drive evidence-based decision-support systems and deliver personalized care to children. This technology creates building blocks for a learning child health and health care ecosystem.

Automated prediction of mastitis infection patterns in dairy herds using machine learning

Mastitis in dairy cattle is extremely costly both in economic and welfare terms and is one of the most significant drivers of antimicrobial usage in dairy cattle. A critical step in the prevention of mastitis is the diagnosis of the predominant route of transmission of pathogens into either contagious (CONT) or environmental (ENV), with environmental being further subdivided as transmission during either the nonlactating “dry” period (EDP) or lactating period (EL). Using data from 1000 farms, random forest algorithms were able to replicate the complex herd level diagnoses made by specialist veterinary clinicians with a high degree of accuracy. An accuracy of 98%, positive predictive value (PPV) of 86% and negative predictive value (NPV) of 99% was achieved for the diagnosis of CONT vs ENV (with CONT as a “positive” diagnosis), and an accuracy of 78%, PPV of 76% and NPV of 81% for the diagnosis of EDP vs EL (with EDP as a “positive” diagnosis). An accurate, automated mastitis diagnosis tool has great potential to aid non-specialist veterinary clinicians to make a rapid herd level diagnosis and promptly implement appropriate control measures for an extremely damaging disease in terms of animal health, productivity, welfare and antimicrobial use.

Reduced Verification of Medication Alerts Increases Prescribing Errors

OBJECTIVE

Clinicians using clinical decision support (CDS) to prescribe medications have an obligation to ensure that prescriptions are safe. One option is to verify the safety of prescriptions if there is uncertainty, for example, by using drug references. Supervisory control experiments in aviation and process control have associated errors, with reduced verification arising from overreliance on decision support. However, it is unknown whether this relationship extends to clinical decision-making. Therefore, we examine whether there is a relationship between verification behaviors and prescribing errors, with and without CDS medication alerts, and whether task complexity mediates this.

METHODS

A total of 120 students in the final 2 years of a medical degree prescribed medicines for patient scenarios using a simulated electronic prescribing system. CDS (correct, incorrect, and no CDS) and task complexity (low and high) were varied. Outcomes were omission (missed prescribing errors) and commission errors (accepted false-positive alerts). Verification measures were access of drug references and view time percentage of task time.

RESULTS

Failure to access references for medicines with prescribing errors increased omission errors with no CDS (high-complexity: χ ²(1) = 12.716; p < 0.001) and incorrect CDS (Fisher's exact; low-complexity: p = 0.002; high-complexity: p = 0.001). Failure to access references for false-positive alerts increased commission errors (low-complexity: χ ²(1) = 16.673, p < 0.001; high-complexity: χ ²(1) = 18.690, p < 0.001). Fewer participants accessed relevant references with incorrect CDS compared with no CDS (McNemar; low-complexity: p < 0.001; high-complexity: p < 0.001). Lower view time percentages increased omission (F(3, 361.914) = 4.498; p = 0.035) and commission errors (F(1, 346.223) = 2.712; p = 0.045). View time percentages were lower in CDS-assisted conditions compared with unassisted conditions (F(2, 335.743) = 10.443; p < 0.001).

DISCUSSION

The presence of CDS reduced verification of prescription safety. When CDS was incorrect, reduced verification was associated with increased prescribing errors.

CONCLUSION

CDS can be incorrect, and verification provides one mechanism to detect errors. System designers need to facilitate verification without increasing workload or eliminating the benefits of correct CDS.

The Effect of Cognitive Load and Task Complexity on Automation Bias in Electronic Prescribing

OBJECTIVE

Determine the relationship between cognitive load (CL) and automation bias (AB).

BACKGROUND

Clinical decision support (CDS) for electronic prescribing can improve safety but introduces the risk of AB, where reliance on CDS replaces vigilance in information seeking and processing. We hypothesized high CL generated by high task complexity would increase AB errors.

METHOD

One hundred twenty medical students prescribed medicines for clinical scenarios using a simulated e-prescribing system in a randomized controlled experiment. Quality of CDS (correct, incorrect, and no CDS) and task complexity (low and high) were varied. CL, omission errors (failure to detect prescribing errors), and commission errors (acceptance of false positive alerts) were measured.

RESULTS

Increasing complexity from low to high significantly increased CL, F(1, 118) = 71.6, p < .001. CDS reduced CL in high-complexity conditions compared to no CDS, F(2, 117) = 4.72, p = .015. Participants who made omission errors in incorrect and no CDS conditions exhibited lower CL compared to those who did not, F(1, 636.49) = 3.79, p = .023.

CONCLUSION

Results challenge the notion that AB is triggered by increasing task complexity and associated increases in CL. Omission errors were associated with lower CL, suggesting errors may stem from an insufficient allocation of cognitive resources.

APPLICATION

This is the first research to examine the relationship between CL and AB. Findings suggest designers and users of CDS systems need to be aware of the risks of AB. Interventions that increase user vigilance and engagement may be beneficial and deserve further investigation.

Unintended consequences of machine learning in medicine?

Machine learning (ML) has the potential to significantly aid medical practice. However, a recent article highlighted some negative consequences that may arise from using ML decision support in medicine. We argue here that whilst the concerns raised by the authors may be appropriate, they are not specific to ML, and thus the article may lead to an adverse perception about this technique in particular. Whilst ML is not without its limitations like any methodology, a balanced view is needed in order to not hamper its use in potentially enabling better patient care.

Use of patient decision aids increased younger women's reluctance to begin screening mammography: a systematic review and meta-analysis

BACKGROUND

As breast cancer screening guidelines have changed recently, additional investigation is needed to understand changes in women's behavior after using breast cancer screening patient decision aids (BCS-PtDAs) and the potential effect on mammography utilization. This systematic review and meta-analysis sought to evaluate the effect of BCS-PtDAs on changes in women's intentions to undergo screening mammography and whether women deciding to begin or discontinue screening mammography displayed similar changes in screening intentions after using a BCS-PtDA.

METHODS

We searched Medline, Scopus, PsycINFO, CENTRAL, Health and Psychosocial Instruments, Health Technology Assessment Database, PsycARTICLES, and cited references in eligible papers for randomized controlled trials (RCTs) and observational studies, published through August 24, 2016. The proportions of women who did and not intend to undergo screening and who were uncertain about undergoing screening mammography were pooled, using risk ratios (RR) and random effects. According to the protocol, RCTs or observational studies and any language were considered eligible for systematic review if they included data about women for which shared decision making is recommended.

RESULTS

We ultimately included six studies with screening intention data for 2040 women. Compared to usual care, the use of BCS-PtDAs in three RCTs resulted in significantly more women deciding not to undergo screening mammography (RR 1.48 [95% CI 1.04-2.13]; P = 0.03), particularly for younger (38-50 years) women (1.77 [1.34-2.34]; P < 0.001). The use of BCS-PtDAs had a non-significant effect on the intentions of older women (69-89 years) to discontinue screening.

CONCLUSIONS

The use of BCS-PtDAs increased younger women's reluctance to undergo screening for breast cancer. The implementation of such BCS-PtDAs in clinical practice would be expected to result in a 77% increase in the number of younger women (aged 38-50) who do not intend to be screened, and as a consequence, may reduce utilization of screening mammography.

REGISTRATION

The protocol of this review is registered in the PROSPERO database, #CRD42016036695.

Automation bias in electronic prescribing

Background

Clinical decision support (CDS) in e-prescribing can improve safety by alerting potential errors, but introduces new sources of risk. Automation bias (AB) occurs when users over-rely on CDS, reducing vigilance in information seeking and processing. Evidence of AB has been found in other clinical tasks, but has not yet been tested with e-prescribing. This study tests for the presence of AB in e-prescribing and the impact of task complexity and interruptions on AB.

Methods

One hundred and twenty students in the final two years of a medical degree prescribed medicines for nine clinical scenarios using a simulated e-prescribing system. Quality of CDS (correct, incorrect and no CDS) and task complexity (low, low + interruption and high) were varied between conditions. Omission errors (failure to detect prescribing errors) and commission errors (acceptance of false positive alerts) were measured.

Results

Compared to scenarios with no CDS, correct CDS reduced omission errors by 38.3% (p < .0001, n = 120), 46.6% (p < .0001, n = 70), and 39.2% (p < .0001, n = 120) for low, low + interrupt and high complexity scenarios respectively. Incorrect CDS increased omission errors by 33.3% (p < .0001, n = 120), 24.5% (p < .009, n = 82), and 26.7% (p < .0001, n = 120). Participants made commission errors, 65.8% (p < .0001, n = 120), 53.5% (p < .0001, n = 82), and 51.7% (p < .0001, n = 120). Task complexity and interruptions had no impact on AB.

Conclusions

This study found evidence of AB omission and commission errors in e-prescribing. Verification of CDS alerts is key to avoiding AB errors. However, interventions focused on this have had limited success to date. Clinicians should remain vigilant to the risks of CDS failures and verify CDS.

Electronic supplementary material

The online version of this article (doi:10.1186/s12911-017-0425-5) contains supplementary material, which is available to authorized users.

Automation bias and verification complexity: a systematic review

INTRODUCTION

While potentially reducing decision errors, decision support systems can introduce new types of errors. Automation bias (AB) happens when users become overreliant on decision support, which reduces vigilance in information seeking and processing. Most research originates from the human factors literature, where the prevailing view is that AB occurs only in multitasking environments.

OBJECTIVES

This review seeks to compare the human factors and health care literature, focusing on the apparent association of AB with multitasking and task complexity.

DATA SOURCES

EMBASE, Medline, Compendex, Inspec, IEEE Xplore, Scopus, Web of Science, PsycINFO, and Business Source Premiere from 1983 to 2015.

STUDY SELECTION

Evaluation studies where task execution was assisted by automation and resulted in errors were included. Participants needed to be able to verify automation correctness and perform the task manually.

METHODS

Tasks were identified and grouped. Task and automation type and presence of multitasking were noted. Each task was rated for its verification complexity.

RESULTS

Of 890 papers identified, 40 met the inclusion criteria; 6 were in health care. Contrary to the prevailing human factors view, AB was found in single tasks, typically involving diagnosis rather than monitoring, and with high verification complexity.

LIMITATIONS

The literature is fragmented, with large discrepancies in how AB is reported. Few studies reported the statistical significance of AB compared to a control condition.

CONCLUSION

AB appears to be associated with the degree of cognitive load experienced in decision tasks, and appears to not be uniquely associated with multitasking. Strategies to minimize AB might focus on cognitive load reduction.

Improving the radiologist-CAD interaction: designing for appropriate trust

Computer-aided diagnosis (CAD) has great potential to improve radiologists' diagnostic performance. However, the reported performance of the radiologist-CAD team is lower than what might be expected based on the performance of the radiologist and the CAD system in isolation. This indicates that the interaction between radiologists and the CAD system is not optimal. An important factor in the interaction between humans and automated aids (such as CAD) is trust. Suboptimal performance of the human-automation team is often caused by an inappropriate level of trust in the automation. In this review, we examine the role of trust in the radiologist-CAD interaction and suggest ways to improve the output of the CAD system so that it allows radiologists to calibrate their trust in the CAD system more effectively. Observer studies of the CAD systems show that radiologists often have an inappropriate level of trust in the CAD system. They sometimes under-trust CAD, thereby reducing its potential benefits, and sometimes over-trust it, leading to diagnostic errors they would not have made without CAD. Based on the literature on trust in human-automation interaction and the results of CAD observer studies, we have identified four ways to improve the output of CAD so that it allows radiologists to form a more appropriate level of trust in CAD. Designing CAD systems for appropriate trust is important and can improve the performance of the radiologist-CAD team. Future CAD research and development should acknowledge the importance of the radiologist-CAD interaction, and specifically the role of trust therein, in order to create the perfect artificial partner for the radiologist. This review focuses on the role of trust in the radiologist-CAD interaction. The aim of the review is to encourage CAD developers to design for appropriate trust and thereby improve the performance of the radiologist-CAD team.

Short-term outcomes of screening mammography using computer-aided detection: a population-based study of medicare enrollees

BACKGROUND

Computer-aided detection (CAD) has rapidly diffused into screening mammography practice despite limited and conflicting data on its clinical effect.

OBJECTIVE

To determine associations between CAD use during screening mammography and the incidence of ductal carcinoma in situ (DCIS) and invasive breast cancer, invasive cancer stage, and diagnostic testing.

DESIGN

Retrospective cohort study.

SETTING

Medicare program.

PARTICIPANTS

Women aged 67 to 89 years having screening mammography between 2001 and 2006 in U.S. SEER (Surveillance, Epidemiology and End Results) regions (409 459 mammograms from 163 099 women).

MEASUREMENTS

Incident DCIS and invasive breast cancer within 1 year after mammography, invasive cancer stage, and diagnostic testing within 90 days after screening among women without breast cancer.

RESULTS

From 2001 to 2006, CAD prevalence increased from 3.6% to 60.5%. Use of CAD was associated with greater DCIS incidence (adjusted odds ratio [OR], 1.17 [95% CI, 1.11 to 1.23]) but no difference in invasive breast cancer incidence (adjusted OR, 1.00 [CI, 0.97 to 1.03]). Among women with invasive cancer, CAD was associated with greater likelihood of stage I to II versus III to IV cancer (adjusted OR, 1.27 [CI, 1.14 to 1.41]). In women without breast cancer, CAD was associated with increased odds of diagnostic mammography (adjusted OR, 1.28 [CI, 1.27 to 1.29]), breast ultrasonography (adjusted OR, 1.07 [CI, 1.06 to 1.09]), and breast biopsy (adjusted OR, 1.10 [CI, 1.08 to 1.12]).

LIMITATION

Short follow-up for cancer stage, potential unmeasured confounding, and uncertain generalizability to younger women.

CONCLUSION

Use of CAD during screening mammography among Medicare enrollees is associated with increased DCIS incidence, the diagnosis of invasive breast cancer at earlier stages, and increased diagnostic testing among women without breast cancer.

PRIMARY FUNDING SOURCE

Center for Healthcare Policy and Research, University of California, Davis.