Impact of a clinical decision support tool on prediction of progression in early-stage dementia: a prospective validation study

Use of a digital tool to support the diagnostic process in memory clinics-a usability study

BACKGROUND

Both memory clinic professionals and patients see value in digital tools, yet these hardly find their way to clinical practice. We explored the usability of a digital tool to support the diagnostic work-up in daily memory clinic practice. We evaluated four modules that integrate multi-modal patient data (1.cognitive test; cCOG, and 2. MRI quantification; cMRI) into useful diagnostic information for clinicians (3. cDSI) and understandable and personalized information for patients (4. patient report).

METHODS

We conducted a mixed-methods study in five Dutch memory clinics. Fourteen clinicians (11 geriatric specialists/residents, two neurologists, one nurse practitioner) were invited to integrate the tool into routine care with 43 new memory clinic patients. We evaluated usability and user experiences through quantitative data from questionnaires (patients, care partners, clinicians), enriched with thematically analyzed qualitative data from interviews (clinicians).

RESULTS

We observed wide variation in tool use among clinicians. Our core findings were that clinicians: 1) were mainly positive about the patient report, since it contributes to patient-centered and personalized communication. This was endorsed by patients and care partners, who indicated that the patient report was useful and understandable and helped them to better understand their diagnosis, 2) considered the tool acceptable in addition to their own clinical competence, 3) indicated that the usefulness of the tool depended on the patient population and purpose of the diagnostic process, 4) addressed facilitators (ease of use, practice makes perfect) and barriers (high workload, lack of experience, data unavailability).

CONCLUSION

This multicenter usability study revealed a willingness to adopt a digital tool to support the diagnostic process in memory clinics. Clinicians, patients, and care partners appreciated the personalized diagnostic report. More attention to education and training of clinicians is needed to utilize the full functionality of the tool and foster implementation in actual daily practice. These findings provide an important step towards a lasting adoption of digital tools in memory clinic practice.

Removing outliers from the normative database improves regional atrophy detection in single-subject voxel-based morphometry

PURPOSE

Single-subject voxel-based morphometry (VBM) compares an individual T1-weighted MRI to a sample of normal MRI in a normative database (NDB) to detect regional atrophy. Outliers in the NDB might result in reduced sensitivity of VBM. The primary aim of the current study was to propose a method for outlier removal ("NDB cleaning") and to test its impact on the performance of VBM for detection of Alzheimer's disease (AD) and frontotemporal lobar degeneration (FTLD).

METHODS

T1-weighted MRI of 81 patients with biomarker-confirmed AD (n = 51) or FTLD (n = 30) and 37 healthy subjects with simultaneous FDG-PET/MRI were included as test dataset. Two different NDBs were used: a scanner-specific NDB (37 healthy controls from the test dataset) and a non-scanner-specific NDB comprising 164 normal T1-weighted MRI from 164 different MRI scanners. Three different quality metrics based on leave-one-out testing of the scans in the NDB were implemented. A scan was removed if it was an outlier with respect to one or more quality metrics. VBM maps generated with and without NDB cleaning were assessed visually for the presence of AD or FTLD.

RESULTS

Specificity of visual interpretation of the VBM maps for detection of AD or FTLD was 100% in all settings. Sensitivity was increased by NDB cleaning with both NDBs. The effect was statistically significant for the multiple-scanner NDB (from 0.47 [95%-CI 0.36-0.58] to 0.61 [0.49-0.71]).

CONCLUSION

NDB cleaning has the potential to improve the sensitivity of VBM for the detection of AD or FTLD without increasing the risk of false positive findings.

Artificial Intelligence for Dementia Research Methods Optimization

INTRODUCTION

Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater.

METHODS

We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research.

RESULTS

We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future.

DISCUSSION

ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.

Impact of normative brain volume reports on the diagnosis of neurodegenerative dementia disorders in neuroradiology: A real-world, clinical practice study

Background: Normative brain volume reports (NBVR) are becoming more available in the work-up of patients with suspected dementia disorders, potentially leveraging the value of structural MRI in clinical settings. The present study aims to investigate the impact of NBVRs on the diagnosis of neurodegenerative dementia disorders in real-world clinical practice.

Methods: We retrospectively analyzed data of 112 memory clinic patients, who were consecutively referred for MRI and 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) during a 12-month period. Structural MRI was assessed by two residents with 2 and 3 years of neuroimaging experience. Statements and diagnostic confidence regarding the presence of a neurodegenerative disorder in general (first level) and Alzheimer’s disease (AD) pattern in particular (second level) were recorded without and with NBVR information. FDG-PET served as the reference standard.

Results: Overall, despite a trend towards increased accuracy, the impact of NBVRs on diagnostic accuracy was low and non-significant. We found a significant drop of sensitivity (0.75–0.58; p < 0.001) and increase of specificity (0.62–0.85; p < 0.001) for rater 1 at identifying patients with neurodegenerative dementia disorders. Diagnostic confidence increased for rater 2 (p < 0.001).

Conclusions: Overall, NBVRs had a limited impact on diagnostic accuracy in real-world clinical practice. Potentially, NBVR might increase diagnostic specificity and confidence of neuroradiology residents. To this end, a well-defined framework for integration of NBVR in the diagnostic process and improved algorithms of NBVR generation are essential.

Expert validation of prediction models for a clinical decision-support system in audiology

For supporting clinical decision-making in audiology, Common Audiological Functional Parameters (CAFPAs) were suggested as an interpretable intermediate representation of audiological information taken from various diagnostic sources within a clinical decision-support system (CDSS). Ten different CAFPAs were proposed to represent specific functional aspects of the human auditory system, namely hearing threshold, supra-threshold deficits, binaural hearing, neural processing, cognitive abilities, and a socio-economic component. CAFPAs were established as a viable basis for deriving audiological findings and treatment recommendations, and it has been demonstrated that model-predicted CAFPAs, with machine learning models trained on expert-labeled patient cases, are sufficiently accurate to be included in a CDSS, but it requires further validation by experts. The present study aimed to validate model-predicted CAFPAs based on previously unlabeled cases from the same data set. Here, we ask to which extent domain experts agree with the model-predicted CAFPAs and whether potential disagreement can be understood in terms of patient characteristics. To these aims, an expert survey was designed and applied to two highly-experienced audiology specialists. They were asked to evaluate model-predicted CAFPAs and estimate audiological findings of the given audiological information about the patients that they were presented with simultaneously. The results revealed strong relative agreement between the two experts and importantly between experts and the prediction for all CAFPAs, except for the neural processing and binaural hearing-related ones. It turned out, however, that experts tend to score CAFPAs in a larger value range, but, on average, across patients with smaller scores as compared with the machine learning models. For the hearing threshold-associated CAFPA in frequencies smaller than 0.75 kHz and the cognitive CAFPA, not only the relative agreement but also the absolute agreement between machine and experts was very high. For those CAFPAs with an average difference between the model- and expert-estimated values, patient characteristics were predictive of the disagreement. The findings are discussed in terms of how they can help toward further improvement of model-predicted CAFPAs to be incorporated in a CDSS for audiology.

Use of a smartphone app to inform healthcare workers of hospital policy during a pandemic such as COVID-19: A mixed methods observational study

Objective

To evaluate the use of a COVID-19 app containing relevant information for healthcare workers (HCWs) in hospitals and to determine user experience.

Methods

A smartphone app (Firstline) was adapted to exclusively contain local COVID-19 policy documents and treatment protocols. This COVID-19 app was offered to all HCWs of a 900-bed tertiary care hospital. App use was evaluated with user analytics and user experience in an online questionnaire.

Results

A total number of 1168 HCWs subscribed to the COVID-19 app which was used 3903 times with an average of 1 minute and 20 seconds per session during a three-month period. The number of active users peaked in April 2020 with 1017 users. Users included medical specialists (22.3%), residents (16.5%), nurses (22.2%), management (6.2%) and other (26.5%). Information for HCWs such as when to test for SARS-CoV-2 (1214), latest updates (1181), the COVID-19 telephone list (418) and the SARS-CoV-2 / COVID-19 guideline (280) were the most frequently accessed advice. Seventy-one users with a mean age of 46.1 years from 19 different departments completed the questionnaire. Respondents considered the COVID-19 app clear (54/59; 92%), easy-to-use (46/55; 84%), fast (46/52; 88%), useful (52/56; 93%), and had faith in the information (58/70; 83%). The COVID-19 app was used to quickly look up something (43/68; 63%), when no computer was available (15/68; 22%), look up / dial COVID-related phone numbers (15/68; 22%) or when walking from A to B (11/68; 16%). Few respondents felt app use cost time (5/68; 7%).

Conclusions

Our COVID-19 app proved to be a relatively simple yet innovative tool that was used by HCWs from all disciplines involved in taking care of COVID-19 patients. The up-to-date app was used for different topics and had high user satisfaction amongst questionnaire respondents. An app with local hospital policy could be an invaluable tool during a pandemic.

Clinician Preimplementation Perspectives of a Decision-Support Tool for the Prediction of Cardiac Arrhythmia Based on Machine Learning: Near-Live Feasibility and Qualitative Study

Background

Artificial intelligence (AI), such as machine learning (ML), shows great promise for improving clinical decision-making in cardiac diseases by outperforming statistical-based models. However, few AI-based tools have been implemented in cardiology clinics because of the sociotechnical challenges during transitioning from algorithm development to real-world implementation.

Objective

This study explored how an ML-based tool for predicting ventricular tachycardia and ventricular fibrillation (VT/VF) could support clinical decision-making in the remote monitoring of patients with an implantable cardioverter defibrillator (ICD).

Methods

Seven experienced electrophysiologists participated in a near-live feasibility and qualitative study, which included walkthroughs of 5 blinded retrospective patient cases, use of the prediction tool, and questionnaires and interview questions. All sessions were video recorded, and sessions evaluating the prediction tool were transcribed verbatim. Data were analyzed through an inductive qualitative approach based on grounded theory.

Results

The prediction tool was found to have potential for supporting decision-making in ICD remote monitoring by providing reassurance, increasing confidence, acting as a second opinion, reducing information search time, and enabling delegation of decisions to nurses and technicians. However, the prediction tool did not lead to changes in clinical action and was found less useful in cases where the quality of data was poor or when VT/VF predictions were found to be irrelevant for evaluating the patient.

Conclusions

When transitioning from AI development to testing its feasibility for clinical implementation, we need to consider the following: expectations must be aligned with the intended use of AI; trust in the prediction tool is likely to emerge from real-world use; and AI accuracy is relational and dependent on available information and local workflows. Addressing the sociotechnical gap between the development and implementation of clinical decision-support tools based on ML in cardiac care is essential for succeeding with adoption. It is suggested to include clinical end-users, clinical contexts, and workflows throughout the overall iterative approach to design, development, and implementation.

Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer's disease

Background

Although convolutional neural networks (CNNs) achieve high diagnostic accuracy for detecting Alzheimer’s disease (AD) dementia based on magnetic resonance imaging (MRI) scans, they are not yet applied in clinical routine. One important reason for this is a lack of model comprehensibility. Recently developed visualization methods for deriving CNN relevance maps may help to fill this gap as they allow the visualization of key input image features that drive the decision of the model. We investigated whether models with higher accuracy also rely more on discriminative brain regions predefined by prior knowledge.

Methods

We trained a CNN for the detection of AD in N = 663 T1-weighted MRI scans of patients with dementia and amnestic mild cognitive impairment (MCI) and verified the accuracy of the models via cross-validation and in three independent samples including in total N = 1655 cases. We evaluated the association of relevance scores and hippocampus volume to validate the clinical utility of this approach. To improve model comprehensibility, we implemented an interactive visualization of 3D CNN relevance maps, thereby allowing intuitive model inspection.

Results

Across the three independent datasets, group separation showed high accuracy for AD dementia versus controls (AUC ≥ 0.91) and moderate accuracy for amnestic MCI versus controls (AUC ≈ 0.74). Relevance maps indicated that hippocampal atrophy was considered the most informative factor for AD detection, with additional contributions from atrophy in other cortical and subcortical regions. Relevance scores within the hippocampus were highly correlated with hippocampal volumes (Pearson’s r ≈ −0.86, p < 0.001).

Conclusion

The relevance maps highlighted atrophy in regions that we had hypothesized a priori. This strengthens the comprehensibility of the CNN models, which were trained in a purely data-driven manner based on the scans and diagnosis labels. The high hippocampus relevance scores as well as the high performance achieved in independent samples support the validity of the CNN models in the detection of AD-related MRI abnormalities. The presented data-driven and hypothesis-free CNN modeling approach might provide a useful tool to automatically derive discriminative features for complex diagnostic tasks where clear clinical criteria are still missing, for instance for the differential diagnosis between various types of dementia.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13195-021-00924-2.

Technical and clinical validation of commercial automated volumetric MRI tools for dementia diagnosis-a systematic review

Developments in neuroradiological MRI analysis offer promise in enhancing objectivity and consistency in dementia diagnosis through the use of quantitative volumetric reporting tools (QReports). Translation into clinical settings should follow a structured framework of development, including technical and clinical validation steps. However, published technical and clinical validation of the available commercial/proprietary tools is not always easy to find and pathways for successful integration into the clinical workflow are varied. The quantitative neuroradiology initiative (QNI) framework highlights six necessary steps for the development, validation and integration of quantitative tools in the clinic. In this paper, we reviewed the published evidence regarding regulatory-approved QReports for use in the memory clinic and to what extent this evidence fulfils the steps of the QNI framework. We summarize unbiased technical details of available products in order to increase the transparency of evidence and present the range of reporting tools on the market. Our intention is to assist neuroradiologists in making informed decisions regarding the adoption of these methods in the clinic. For the 17 products identified, 11 companies have published some form of technical validation on their methods, but only 4 have published clinical validation of their QReports in a dementia population. Upon systematically reviewing the published evidence for regulatory-approved QReports in dementia, we concluded that there is a significant evidence gap in the literature regarding clinical validation, workflow integration and in-use evaluation of these tools in dementia MRI diagnosis.

Ethical Implications of Alzheimer's Disease Prediction in Asymptomatic Individuals through Artificial Intelligence

Biomarker-based predictive tests for subjectively asymptomatic Alzheimer’s disease (AD) are utilized in research today. Novel applications of artificial intelligence (AI) promise to predict the onset of AD several years in advance without determining biomarker thresholds. Until now, little attention has been paid to the new ethical challenges that AI brings to the early diagnosis in asymptomatic individuals, beyond contributing to research purposes, when we still lack adequate treatment. The aim of this paper is to explore the ethical arguments put forward for AI aided AD prediction in subjectively asymptomatic individuals and their ethical implications. The ethical assessment is based on a systematic literature search. Thematic analysis was conducted inductively of 18 included publications. The ethical framework includes the principles of autonomy, beneficence, non-maleficence, and justice. Reasons for offering predictive tests to asymptomatic individuals are the right to know, a positive balance of the risk-benefit assessment, and the opportunity for future planning. Reasons against are the lack of disease modifying treatment, the accuracy and explicability of AI aided prediction, the right not to know, and threats to social rights. We conclude that there are serious ethical concerns in offering early diagnosis to asymptomatic individuals and the issues raised by the application of AI add to the already known issues. Nevertheless, pre-symptomatic testing should only be offered on request to avoid inflicted harm. We recommend developing training for physicians in communicating AI aided prediction.

Use of a Decision Support Tool on Prognosis of Work Ability in Work Disability Assessments: An Experimental Study Among Insurance Physicians

Purpose Assessment of prognosis of work disability is a challenging task for occupational health professionals. An evidence-based decision support tool, based on a prediction model, could aid professionals in the decision-making process. This study aimed to evaluate the efficacy of such a tool on Dutch insurance physicians' (IPs) prognosis of work ability and their prognostic confidence, and assess IPs' attitudes towards use of the tool. Methods We conducted an experimental study including six case vignettes among 29 IPs. For each vignette, IPs first specified their own prognosis of future work ability and prognostic confidence. Next, IPs were informed about the outcome of the prediction model and asked whether this changed their initial prognosis and prognostic confidence. Finally, respondents reported their attitude towards use of the tool in real practice. Results The concordance between IPs' prognosis and the outcome of the prediction model was low: IPs' prognosis was more positive in 72 (41%) and more negative in 20 (11%) cases. Using the decision support tool, IPs changed their prognosis in only 13% of the cases. IPs prognostic confidence decreased when prognosis was discordant, and remained unchanged when it was concordant. Concerning attitudes towards use, the wish to know more about the tool was considered as the main barrier. Conclusion The efficacy of the tool on IPs' prognosis of work ability and their prognostic confidence was low. Although the perceived barriers were overall limited, only a minority of the IPs indicated that they would be willing to use the tool in practice.

Shaping a data-driven era in dementia care pathway through computational neurology approaches

BACKGROUND

Dementia is caused by a variety of neurodegenerative diseases and is associated with a decline in memory and other cognitive abilities, while inflicting an enormous socioeconomic burden. The complexity of dementia and its associated comorbidities presents immense challenges for dementia research and care, particularly in clinical decision-making.

MAIN BODY

Despite the lack of disease-modifying therapies, there is an increasing and urgent need to make timely and accurate clinical decisions in dementia diagnosis and prognosis to allow appropriate care and treatment. However, the dementia care pathway is currently suboptimal. We propose that through computational approaches, understanding of dementia aetiology could be improved, and dementia assessments could be more standardised, objective and efficient. In particular, we suggest that these will involve appropriate data infrastructure, the use of data-driven computational neurology approaches and the development of practical clinical decision support systems. We also discuss the technical, structural, economic, political and policy-making challenges that accompany such implementations.

CONCLUSION

The data-driven era for dementia research has arrived with the potential to transform the healthcare system, creating a more efficient, transparent and personalised service for dementia.

Blood TDP-43 Combined with Demographics Information Predicts Dementia Occurrence in Community Non-Dementia Elderly

BACKGROUND

TAR DNA-binding protein-43 (TDP-43) and neurofilament light chain (NfL) are promising fluid biomarkers of disease progression for various dementia.

OBJECTIVE

We would explore whether blood levels of NfL and TDP-43 could predict the long-term progression to dementia, and the relationship of TDP-43 levels between cerebrospinal fluid (CSF) and blood.

METHODS

A total of 86 non-dementia elderly received 7-year follow-up, and were divided into 49 stable normal control (NC)/mild cognitive impairment (MCI) subjects, 19 subjects progressing from NC to MCI, and 18 subjects progressing from NC/MCI to dementia. Blood TDP-43 and NfL levels, and cognitive functions were measured in all subjects. Furthermore, another cohort of 23 dementia patients, including 13 AD and 10 non-AD patients received blood and CSF measurements of TDP-43.

RESULTS

In cohort 1, compared to stable NC/MCI group, there were higher levels of blood TDP-43 at baseline in subjects progressing from NC/MCI to dementia. The combination of baseline blood TDP-43 levels with demographics including age, education, and diabetes had the detection for dementia occurrence. Baseline blood levels of NfL are negatively associated with cognitive function at 7-year follow-up. In cohort 2, we found there were no relationship between CSF and blood levels of TDP-43. Moreover, the levels of TDP-43 in CSF was positively associated with the age of patients, especially in AD group.

CONCLUSION

Single blood TDP-43 could not estimate dementia occurrence; however, TDP-43 combined with demographics has the predictive effect for dementia occurrence and NfL level is associated with a decrease of cognitive function.

Predicting the progression of mild cognitive impairment using machine learning: A systematic, quantitative and critical review

We performed a systematic review of studies focusing on the automatic prediction of the progression of mild cognitive impairment to Alzheimer's disease (AD) dementia, and a quantitative analysis of the methodological choices impacting performance. This review included 172 articles, from which 234 experiments were extracted. For each of them, we reported the used data set, the feature types, the algorithm type, performance and potential methodological issues. The impact of these characteristics on the performance was evaluated using a multivariate mixed effect linear regressions. We found that using cognitive, fluorodeoxyglucose-positron emission tomography or potentially electroencephalography and magnetoencephalography variables significantly improved predictive performance compared to not including them, whereas including other modalities, in particular T1 magnetic resonance imaging, did not show a significant effect. The good performance of cognitive assessments questions the wide use of imaging for predicting the progression to AD and advocates for exploring further fine domain-specific cognitive assessments. We also identified several methodological issues, including the absence of a test set, or its use for feature selection or parameter tuning in nearly a fourth of the papers. Other issues, found in 15% of the studies, cast doubts on the relevance of the method to clinical practice. We also highlight that short-term predictions are likely not to be better than predicting that subjects stay stable over time. These issues highlight the importance of adhering to good practices for the use of machine learning as a decision support system for the clinical practice.

Cognitively supernormal older adults maintain a unique structural connectome that is resistant to Alzheimer's pathology

Studying older adults with excellent cognitive capacities (Supernormals) provides a unique opportunity for identifying factors related to cognitive success - a critical topic across lifespan. There is a limited understanding of Supernormals' neural substrates, especially whether any of them attends shaping and supporting superior cognitive function or confer resistance to age-related neurodegeneration such as Alzheimer's disease (AD). Here, applying a state-of-the-art diffusion imaging processing pipeline and finite mixture modelling, we longitudinally examine the structural connectome of Supernormals. We find a unique structural connectome, containing the connections between frontal, cingulate, parietal, temporal, and subcortical regions in the same hemisphere that remains stable over time in Supernormals, relatively to typical agers. The connectome significantly classifies positive vs. negative AD pathology at 72% accuracy in a new sample mixing Supernormals, typical agers, and AD risk [amnestic mild cognitive impairment (aMCI)] subjects. Among this connectome, the mean diffusivity of the connection between right isthmus cingulate cortex and right precuneus most robustly contributes to predicting AD pathology across samples. The mean diffusivity of this connection links negatively to global cognition in those Supernormals with positive AD pathology. But this relationship does not exist in typical agers or aMCI. Our data suggest the presence of a structural connectome supporting cognitive success. Cingulate to precuneus white matter integrity may be useful as a structural marker for monitoring neurodegeneration and may provide critical information for understanding how some older adults maintain or excel cognitively in light of significant AD pathology.

cCOG: A web-based cognitive test tool for detecting neurodegenerative disorders

INTRODUCTION

Web-based cognitive tests have potential for standardized screening in neurodegenerative disorders. We examined accuracy and consistency of cCOG, a computerized cognitive tool, in detecting mild cognitive impairment (MCI) and dementia.

METHODS

Clinical data of 306 cognitively normal, 120 mild cognitive impairment (MCI), and 69 dementia subjects from three European cohorts were analyzed. Global cognitive score was defined from standard neuropsychological tests and compared to the corresponding estimated score from the cCOG tool containing seven subtasks. The consistency of cCOG was assessed comparing measurements administered in clinical settings and in the home environment.

RESULTS

cCOG produced accuracies (receiver operating characteristic-area under the curve [ROC-AUC]) between 0.71 and 0.84 in detecting MCI and 0.86 and 0.94 in detecting dementia when administered at the clinic and at home. The accuracy was comparable to the results of standard neuropsychological tests (AUC 0.69-0.77 MCI/0.91-0.92 dementia).

DISCUSSION

cCOG provides a promising tool for detecting MCI and dementia with potential for a cost-effective approach including home-based cognitive assessments.

Evaluating 2-[18F]FDG-PET in differential diagnosis of dementia using a data-driven decision model

•

Addition of 2-[¹⁸F]FDG-PET to common diagnostic tests improved the accuracy for DLB and FTD.

•

Two new 2-[¹⁸F]FDG-PET biomarkers demonstrated specific disease patterns for DLB and FTD.

•

Different combinations of diagnostic tests were valuable for each subtype of dementia.

2-[¹⁸F]fluoro-2-deoxy-d-glucose positron emission tomography (2-[¹⁸F]FDG-PET) has an emerging supportive role in dementia diagnostic as distinctive metabolic patterns are specific for Alzheimer's disease (AD), dementia with Lewy bodies (DLB) and frontotemporal dementia (FTD). Previous studies have demonstrated that a data-driven decision model based on the disease state index (DSI) classifier supports clinicians in the differential diagnosis of dementia by using different combinations of diagnostic tests and biomarkers. Until now, this model has not included 2-[¹⁸F]FDG-PET data.

The objective of the study was to evaluate 2-[¹⁸F]FDG-PET biomarkers combined with commonly used diagnostic tests in the differential diagnosis of dementia using the DSI classifier.

We included data from 259 subjects diagnosed with AD, DLB, FTD, vascular dementia (VaD), and subjective cognitive decline from two independent study cohorts. We also evaluated three 2-[¹⁸F]FDG-PET biomarkers (anterior vs. posterior index (API-PET), occipital vs. temporal index, and cingulate island sign) to improve the classification accuracy for both FTD and DLB.

We found that the addition of 2-[¹⁸F]FDG-PET biomarkers to cognitive tests, CSF and MRI biomarkers considerably improved the classification accuracy for all pairwise comparisons of DLB (balanced accuracies: DLB vs. AD from 64% to 77%; DLB vs. FTD from 71% to 92%; and DLB vs. VaD from 71% to 84%). The two 2-[¹⁸F]FDG-PET biomarkers, API-PET and occipital vs. temporal index, improved the accuracy for FTD and DLB, especially as compared to AD. Moreover, different combinations of diagnostic tests were valuable to differentiate specific subtypes of dementia.

In conclusion, this study demonstrated that the addition of 2-[¹⁸F]FDG-PET to commonly used diagnostic tests provided complementary information that may help clinicians in diagnosing patients, particularly for differentiating between patients with FTD, DLB, and AD.

Normative brain volume reports may improve differential diagnosis of dementing neurodegenerative diseases in clinical practice

OBJECTIVES

Normative brain volume reports (NBVRs) are becoming more and more available for the workup of dementia patients in clinical routine. However, it is yet unknown how this information can be used in the radiological decision-making process. The present study investigates the diagnostic value of NBVRs for detection and differential diagnosis of distinct regional brain atrophy in several dementing neurodegenerative disorders.

METHODS

NBVRs were obtained for 81 consecutive patients with distinct dementing neurodegenerative diseases and 13 healthy controls (HC). Forty Alzheimer's disease (AD; 18 with dementia, 22 with mild cognitive impairment (MCI), 11 posterior cortical atrophy (PCA)), 20 frontotemporal dementia (FTD), and ten semantic dementia (SD) cases were analyzed, and reports were tested qualitatively for the representation of atrophy patterns. Gold standard diagnoses were based on the patients' clinical course, FDG-PET imaging, and/or cerebrospinal fluid (CSF) biomarkers following established diagnostic criteria. Diagnostic accuracy of pattern representations was calculated.

RESULTS

NBVRs improved the correct identification of patients vs. healthy controls based on structural MRI for rater 1 (p < 0.001) whereas the amount of correct classifications was rather unchanged for rater 2. Correct differential diagnosis of dementing neurodegenerative disorders was significantly improved for both rater 1 (p = 0.001) and rater 2 (p = 0.022). Furthermore, interrater reliability was improved from moderate to excellent for both detection and differential diagnosis of neurodegenerative diseases (κ = 0.556/0.894 and κ = 0.403/0.850, respectively).

CONCLUSION

NBVRs deliver valuable and observer-independent information, which can improve differential diagnosis of neurodegenerative diseases.

KEY POINTS

• Normative brain volume reports increase detection of neurodegenerative atrophy patterns compared to visual reading alone. • Differential diagnosis of regionally distinct atrophy patterns is improved. • Agreement between radiologists is significantly improved from moderate to excellent when using normative brain volume reports.

Accuracy and Effects of Clinical Decision Support Systems Integrated With BMJ Best Practice-Aided Diagnosis: Interrupted Time Series Study

BACKGROUND

Clinical decision support systems (CDSS) are an integral component of health information technologies and can assist disease interpretation, diagnosis, treatment, and prognosis. However, the utility of CDSS in the clinic remains controversial.

OBJECTIVE

The aim is to assess the effects of CDSS integrated with British Medical Journal (BMJ) Best Practice-aided diagnosis in real-world research.

METHODS

This was a retrospective, longitudinal observational study using routinely collected clinical diagnosis data from electronic medical records. A total of 34,113 hospitalized patient records were successively selected from December 2016 to February 2019 in six clinical departments. The diagnostic accuracy of the CDSS was verified before its implementation. A self-controlled comparison was then applied to detect the effects of CDSS implementation. Multivariable logistic regression and single-group interrupted time series analysis were used to explore the effects of CDSS. The sensitivity analysis was conducted using the subgroup data from January 2018 to February 2019.

RESULTS

The total accuracy rates of the recommended diagnosis from CDSS were 75.46% in the first-rank diagnosis, 83.94% in the top-2 diagnosis, and 87.53% in the top-3 diagnosis in the data before CDSS implementation. Higher consistency was observed between admission and discharge diagnoses, shorter confirmed diagnosis times, and shorter hospitalization days after the CDSS implementation (all P<.001). Multivariable logistic regression analysis showed that the consistency rates after CDSS implementation (OR 1.078, 95% CI 1.015-1.144) and the proportion of hospitalization time 7 days or less (OR 1.688, 95% CI 1.592-1.789) both increased. The interrupted time series analysis showed that the consistency rates significantly increased by 6.722% (95% CI 2.433%-11.012%, P=.002) after CDSS implementation. The proportion of hospitalization time 7 days or less significantly increased by 7.837% (95% CI 1.798%-13.876%, P=.01). Similar results were obtained in the subgroup analysis.

CONCLUSIONS

The CDSS integrated with BMJ Best Practice improved the accuracy of clinicians' diagnoses. Shorter confirmed diagnosis times and hospitalization days were also found to be associated with CDSS implementation in retrospective real-world studies. These findings highlight the utility of artificial intelligence-based CDSS to improve diagnosis efficiency, but these results require confirmation in future randomized controlled trials.