PRESERVE: Randomized Trial of Intensive Versus Standard Blood Pressure Control in Small Vessel Disease.

[Figure: see text].

Fully automated cognitive screening tool based on assessment of speech and language.

INTRODUCTION: Recent years have seen an almost sevenfold rise in referrals to specialist memory clinics. This has been associated with an increased proportion of patients referred with functional cognitive disorder (FCD), that is, non-progressive cognitive complaints. These patients are likely to benefit from a range of interventions (eg, psychotherapy) distinct from the requirements of patients with neurodegenerative cognitive disorders. We have developed a fully automated system, 'CognoSpeak', which enables risk stratification at the primary-secondary care interface and ongoing monitoring of patients with memory concerns. METHODS: We recruited 15 participants to each of four groups: Alzheimer's disease (AD), mild cognitive impairment (MCI), FCD and healthy controls. Participants responded to 12 questions posed by a computer-presented talking head. Automatic analysis of the audio and speech data involved speaker segmentation, automatic speech recognition and machine learning classification. RESULTS: CognoSpeak could distinguish between participants in the AD or MCI groups and those in the FCD or healthy control groups with a sensitivity of 86.7%. Patients with MCI were identified with a sensitivity of 80%. DISCUSSION: Our fully automated system achieved levels of accuracy comparable to currently available, manually administered assessments. Greater accuracy should be achievable through further system training with a greater number of users, the inclusion of verbal fluency tasks and repeat assessments. The current data supports CognoSpeak's promise as a screening and monitoring tool for patients with MCI. Pending confirmation of these findings, it may allow clinicians to offer patients at low risk of dementia earlier reassurance and relieve pressures on specialist memory services.

An Interactional Profile to Assist the Differential Diagnosis of Neurodegenerative and Functional Memory Disorders.

OBJECTIVE: Specialist services for dementia are seeing an increasing number of patients. We investigated whether interactional and linguistic features in the communication behavior of patients with memory problems could help distinguish between those with problems secondary to neurological disorders (ND) and those with functional memory disorder (FMD). METHODS: In part 1 of this study, a diagnostic scoring aid (DSA) was developed encouraging linguists to provide quantitative ratings for 14 interactional features. An optimal cut-off differentiating ND and FMD was established by applying the DSA to 30 initial patient-doctor memory clinic encounters. In part 2, the DSA was tested prospectively in 10 additional cases analyzed independently by 2 conversation analysts blinded to medical information. RESULTS: In part 1, the median score of the DSA was +5 in ND and -5 in FMD (P<0.001). The optimal numeric DSA cut-off (+1) identified patients with ND with a sensitivity of 86.7% and a specificity of 100%. In part 2, DSA scores of rater 1 correctly predicted 10/10 and those of rater 2 predicted 9/10 diagnoses. CONCLUSIONS: This study indicates that interactional and linguistic features can help distinguish between patients developing dementia and those with FMD and could aid the stratification of patients with memory problems.

Distinctive neuropsychological profiles differentiate patients with functional memory disorder from patients with amnestic-mild cognitive impairment.

OBJECTIVES: Patients with functional memory disorder (FMD) report significant memory failures in everyday life. Differentiating these patients from those with memory difficulties due to early stage neurodegenerative conditions is clinically challenging. The current study explored whether distinctive neuropsychological profiles could be established, suitable to differentiate patients with FMD from healthy individuals and those experiencing amnestic mild cognitive impairment (a-MCI). METHODS: Patients with a clinical diagnosis of FMD were compared with patients with a-MCI, and healthy matched controls on several tests assessing different cognitive functions. Patients with clinically established mood disorders were excluded. Patients with FMD and a-MCI were broadly comparable on the level of their subjective memory complaints as assessed by clinical interview. RESULTS: The neuropsychological profile of the FMD patients, although they expressed subjective memory and attention concerns during their clinical interview was distinct from patients with a-MCI on tests of memory [semantic fluency, age of acquisition (AoA) analysis of semantic fluency, verbal and non-verbal memory]. FMD patients did not differ significantly from healthy controls, but their scores on the letter fluency and digit cancellation tasks were not significantly different from those of the a-MCI patients indicating a possible sub-threshold deficit on these tasks. CONCLUSION: Whilst subjective complaints are common within the FMD population, no objective impairment could be detected, even on a sensitive battery of tasks designed to detect subtle deficits caused by an early neurodegenerative brain disease. This study indicates that FMD patients can be successfully differentiated from patients with neurodegenerative memory decline by characterising their neuropsychological profile.

Using DTI to assess white matter microstructure in cerebral small vessel disease (SVD) in multicentre studies.

Diffusion tensor imaging (DTI) metrics such as fractional anisotropy (FA) and mean diffusivity (MD) have been proposed as clinical trial markers of cerebral small vessel disease (SVD) due to their associations with outcomes such as cognition. However, studies investigating this have been predominantly single-centre. As clinical trials are likely to be multisite, further studies are required to determine whether associations with cognition of similar strengths can be detected in a multicentre setting. One hundred and nine patients (mean age =68 years) with symptomatic lacunar infarction and confluent white matter hyperintensities (WMH) on MRI was recruited across six sites as part of the PRESERVE DTI substudy. After handling missing data, 3T-MRI scanning was available from five sites on five scanner models (Siemens and Philips), alongside neuropsychological and quality of life (QoL) assessments. FA median and MD peak height were extracted from DTI histogram analysis. Multiple linear regressions were performed, including normalized brain volume, WMH lesion load, and n° lacunes as covariates, to investigate the association of FA and MD with cognition and QoL. DTI metrics from all white matter were significantly associated with global cognition (standardized ß =0.268), mental flexibility (ß =0.306), verbal fluency (ß =0.376), and Montreal Cognitive Assessment (MoCA) (ß =0.273). The magnitudes of these associations were comparable with those previously reported from single-centre studies found in a systematic literature review. In this multicentre study, we confirmed associations between DTI parameters and cognition, which were similar in strength to those found in previous single-centre studies. The present study supports the use of DTI metrics as biomarkers of disease progression in multicentre studies.

Conversational assessment in memory clinic encounters: interactional profiling for differentiating dementia from functional memory disorders.

OBJECTIVES: In the UK dementia is under-diagnosed, there is limited access to specialist memory clinics, and many of the patients referred to such clinics are ultimately found to have functional (non-progressive) memory disorders (FMD), rather than a neurodegenerative disorder. Government initiatives on 'timely diagnosis' aim to improve the rate and quality of diagnosis for those with dementia. This study seeks to improve the screening and diagnostic process by analysing communication between clinicians and patients during initial specialist clinic visits. Establishing differential conversational profiles could help the timely differential diagnosis of memory complaints. METHOD: This study is based on video- and audio recordings of 25 initial consultations between neurologists and patients referred to a UK memory clinic. Conversation analysis was used to explore recurrent communicative practices associated with each diagnostic group. RESULTS: Two discrete conversational profiles began to emerge, to help differentiate between patients with dementia and functional memory complaints, based on (1) whether the patient is able to answer questions about personal information; (2) whether they can display working memory in interaction; (3) whether they are able to respond to compound questions; (4) the time taken to respond to questions; and (5) the level of detail they offer when providing an account of their memory failure experiences. CONCLUSION: The distinctive conversational profiles observed in patients with functional memory complaints on the one hand and neurodegenerative memory conditions on the other suggest that conversational profiling can support the differential diagnosis of functional and neurodegenerative memory disorders.

Medical management with or without interventional therapy for unruptured brain arteriovenous malformations (ARUBA): a multicentre, non-blinded, randomised trial.

BACKGROUND: The clinical benefit of preventive eradication of unruptured brain arteriovenous malformations remains uncertain. A Randomised trial of Unruptured Brain Arteriovenous malformations (ARUBA) aims to compare the risk of death and symptomatic stroke in patients with an unruptured brain arteriovenous malformation who are allocated to either medical management alone or medical management with interventional therapy. METHODS: Adult patients (≥18 years) with an unruptured brain arteriovenous malformation were enrolled into this trial at 39 clinical sites in nine countries. Patients were randomised (by web-based system, in a 1:1 ratio, with random permuted block design [block size 2, 4, or 6], stratified by clinical site) to medical management with interventional therapy (ie, neurosurgery, embolisation, or stereotactic radiotherapy, alone or in combination) or medical management alone (ie, pharmacological therapy for neurological symptoms as needed). Patients, clinicians, and investigators are aware of treatment assignment. The primary outcome is time to the composite endpoint of death or symptomatic stroke; the primary analysis is by intention to treat. This trial is registered with ClinicalTrials.gov, number NCT00389181. FINDINGS: Randomisation was started on April 4, 2007, and was stopped on April 15, 2013, when a data and safety monitoring board appointed by the National Institute of Neurological Disorders and Stroke of the National Institutes of Health recommended halting randomisation because of superiority of the medical management group (log-rank Z statistic of 4·10, exceeding the prespecified stopping boundary value of 2·87). At this point, outcome data were available for 223 patients (mean follow-up 33·3 months [SD 19·7]), 114 assigned to interventional therapy and 109 to medical management. The primary endpoint had been reached by 11 (10·1%) patients in the medical management group compared with 35 (30·7%) in the interventional therapy group. The risk of death or stroke was significantly lower in the medical management group than in the interventional therapy group (hazard ratio 0·27, 95% CI 0·14-0·54). No harms were identified, other than a higher number of strokes (45 vs 12, p<0·0001) and neurological deficits unrelated to stroke (14 vs 1, p=0·0008) in patients allocated to interventional therapy compared with medical management. INTERPRETATION: The ARUBA trial showed that medical management alone is superior to medical management with interventional therapy for the prevention of death or stroke in patients with unruptured brain arteriovenous malformations followed up for 33 months. The trial is continuing its observational phase to establish whether the disparities will persist over an additional 5 years of follow-up. FUNDING: National Institutes of Health, National Institute of Neurological Disorders and Stroke.

Memory difficulties are not always a sign of incipient dementia: a review of the possible causes of loss of memory efficiency.

INTRODUCTION OR BACKGROUND: Memory problems are a very common reason for presenting to primary care. There is a need for better treatments for dementia. Increased government and media interest may result in greater number seeking help for memory problems, which may not reduce the dementia gap but rather increase numbers seen who do not have dementia. This review highlights the issues around the diagnostic criteria and terminology used for people with memory complaints. SOURCES OF DATA: A comprehensive literature search using PubMed using keywords for articles on subjective memory decline (SMD)/impairment/complaints, subjective cognitive decline (SCD), mild cognitive impairment (MCI) and functional memory disorder (FMD). AREAS OF AGREEMENT: There is a need for early accurate detection of dementia syndromes so that trials of new treatments can begin earlier on the disease process. AREAS OF CONTROVERSY: Diagnostic criteria and terminology used for disorders of memory including SCD, MCI and FMD. GROWING POINTS: This article reviews SCD and whether this can be used to predict Alzheimer's disease. The review also discusses the terminology used for non-progressive memory problems and the long-term outcomes for this patient group. AREAS TIMELY FOR DEVELOPING RESEARCH: The accurate distinction of premorbid dementia syndromes from benign non-progressive memory problems. Studies of treatment options for people with benign non-progressive memory problems and longer-term follow-up to determine which patients develop chronic problems.

Addressing barriers and identifying facilitators to support informed consent and recruitment in the Cavernous malformations A Randomised Effectiveness (CARE) pilot phase trial: insights from the integrated QuinteT recruitment intervention (QRI).

Background: It was anticipated that recruitment to the Cavernous malformations: A Randomised Effectiveness (CARE) pilot randomised trial would be challenging. The trial compared medical management and surgery (neurosurgical resection or stereotactic radiosurgery) with medical management alone, for people with symptomatic cerebral cavernous malformation (ISRCTN41647111). Previous trials comparing surgical and medical management for intracranial vascular malformations failed to recruit to target. A QuinteT Recruitment Intervention was integrated during trial accrual, September 2021-April 2023 inclusive, to improve informed consent and recruitment. Methods: The QuinteT Recruitment Intervention combined iterative collection and analysis of quantitative data (28 trial site screening logs recording numbers/proportions screened, eligible, approached and randomised) and qualitative data (79 audio-recorded recruitment discussions, 19 interviews with healthcare professionals, 11 interviews with patients, 2 investigator workshops, and observations of study meetings, all subject to thematic, content or conversation analysis). We triangulated quantitative and qualitative data to identify barriers and facilitators to recruitment and how and why these arose. Working with the chief investigators and trial management group, we addressed barriers and facilitators with corresponding actions to improve informed consent and recruitment. Findings: Barriers identified included how usual care practices made equipoise challenging, multi-disciplinary teams sometimes overrode recruiter equipoise and logistical issues rendered symptomatic cavernoma diagnosis and assessment for stereotactic radiosurgery challenging. Facilitators identified included the preparedness of some neurosurgeons' to offer surgery to people otherwise offered medical management alone, multi-disciplinary team equipoise, and effective information provision presenting participation as a solution to equipoise regarding management. Actions, before and during recruitment, to improve inclusivity of site screening, approach and effectiveness of information provision resulted in 72 participants recruited following a 5-month extension, exceeding the target of 60 participants. Interpretation: QuinteT Recruitment Intervention insights revealed barriers and facilitators, enabling identification of remedial actions. Recruitment to a definitive trial would benefit from further training/support to encourage clinicians to be comfortable approaching patients to whom medical management is usually offered, and broadening the pool of neurosurgeons and multi-disciplinary team members prepared to offer surgery, particularly stereotactic radiosurgery. Funding: National Institute for Health and Care Research.

Cognitive screening in the acute stroke setting.

BACKGROUND: current literature suggests that two-thirds of patients will have cognitive impairment at 3 months post-stroke. Post-stroke cognitive impairment is associated with impaired function and increased mortality. UK guidelines recommend all patients with stroke have a cognitive assessment within 6 weeks. There is no 'gold standard' cognitive screening tool. The Montreal cognitive assessment (MoCA) is more sensitive than the Mini-Mental State Examination (MMSE) in mild cognitive impairment and for cognitive impairment in the non-acute post-stroke setting and in a Chinese-speaking acute stroke setting. METHODS: a convenience sample of 50 patients, admitted with stroke or transient ischaemic attack (TIA), were screened within 14 days, using the MoCA and the MMSE. RESULTS: the mean MoCA was 21.80 versus a mean MMSE of 26.98; 70% were impaired on the MoCA (cut-off <26) versus 26% on MMSE (cut-off <27). The MoCA could be completed in <10 min in 90% of cases. CONCLUSION: the MoCA is easy and quick to use in the acute stroke setting. Further work is required to determine whether a low score on the MoCA in the acute stroke setting will predict the cognitive and functional status and to explore what the best cut-off should be in an acute post-stroke setting.

Thrombolysis Outcomes in Acute Ischaemic Stroke Patients with Pre-Existing Cognitive Impairment.

BACKGROUND: Thrombolysis treatment for ischaemic stroke in patients with pre-existing disabilities, including cognitive impairment, remains controversial. Previous studies have suggested functional outcomes post-thrombolysis are worse in patients with cognitive impairment. This study aimed to compare and explore factors contributing to thrombolysis outcomes, including haemorrhagic complications, in cognitively and non-cognitively impaired patients with ischaemic stroke. MATERIALS AND METHODS: A retrospective analysis of 428 ischaemic stroke patients who were thrombolysed between January 2016 and February 2021 was performed. Cognitive impairment was defined as a diagnosis of dementia, mild cognitive impairment, or clinical evidence of the condition. The outcome measures included morbidity (using NIHSS and mRS), haemorrhagic complications, and mortality, and were analysed using multivariable logistic regression models. RESULTS: The analysis of the cohort revealed that 62 patients were cognitively impaired. When compared to those without cognitive impairment, this group showed worse functional status at discharge (mRS 4 vs. 3, p < 0.001) and a higher probability of dying within 90 days (OR 3.34, 95% CI 1.85-6.01, p < 0.001). A higher risk of a fatal ICH post-thrombolysis was observed in the cognitively impaired patients, and, after controlling for covariates, cognitive impairment remained a significant predictor of a fatal haemorrhage (OR 4.79, 95% CI 1.24-18.45, p = 0.023). CONCLUSIONS: Cognitively impaired ischaemic stroke patients experience increased morbidity, mortality, and haemorrhagic complications following thrombolytic therapy. However cognitive status is not independently predictive of most outcome measures. Further work is required to elucidate contributing factors to the poor outcomes observed in these patients and help guide thrombolysis decision-making in clinical practice.

Feasibility of comparing medical management and surgery (with neurosurgery or stereotactic radiosurgery) with medical management alone in people with symptomatic brain cavernoma - protocol for the Cavernomas: A Randomised Effectiveness (CARE) pilot trial.

INTRODUCTION: The top research priority for cavernoma, identified by a James Lind Alliance Priority setting partnership was 'Does treatment (with neurosurgery or stereotactic radiosurgery) or no treatment improve outcome for people diagnosed with a cavernoma?' This pilot randomised controlled trial (RCT) aims to determine the feasibility of answering this question in a main phase RCT. METHODS AND ANALYSIS: We will perform a pilot phase, parallel group, pragmatic RCT involving approximately 60 children or adults with mental capacity, resident in the UK or Ireland, with an unresected symptomatic brain cavernoma. Participants will be randomised by web-based randomisation 1:1 to treatment with medical management and with surgery (neurosurgery or stereotactic radiosurgery) versus medical management alone, stratified by prerandomisation preference for type of surgery. In addition to 13 feasibility outcomes, the primary clinical outcome is symptomatic intracranial haemorrhage or new persistent/progressive focal neurological deficit measured at 6 monthly intervals. An integrated QuinteT Recruitment Intervention (QRI) evaluates screening logs, audio recordings of recruitment discussions, and interviews with recruiters and patients/parents/carers to identify and address barriers to participation. A Patient Advisory Group has codesigned the study and will oversee its progress. ETHICS AND DISSEMINATION: This study was approved by the Yorkshire and The Humber-Leeds East Research Ethics Committee (21/YH/0046). We will submit manuscripts to peer-reviewed journals, describing the findings of the QRI and the Cavernomas: A Randomised Evaluation (CARE) pilot trial. We will present at national specialty meetings. We will disseminate a plain English summary of the findings of the CARE pilot trial to participants and public audiences with input from, and acknowledgement of, the Patient Advisory Group. TRIAL REGISTRATION NUMBER: ISRCTN41647111.

Stretch syncope: reflex vasodepressor faints easily mistaken for epilepsy.

The pathophysiology of stretch syncope is demonstrated through the clinical, electrophysiological, and hemodynamic findings in three patients. Fifty-seven attacks were captured by video/EEG monitoring. Simultaneous EEG, transcranial (middle cerebral artery) doppler, and continuous arterial pressure measurements were obtained for at least one typical attack of each patient. They all experienced a compulsion to precipitate their attacks. Episodes started with a stereotyped phase of stretching associated with neck torsion and breath holding, followed by a variable degree of loss of consciousness and asymmetric, recurrent facial and upper limb jerks in the more prolonged episodes. Significant sinus tachycardia coincided with the phase of stretching and was followed within 9-16 seconds by rhythmic generalized slow wave abnormalities on the EEG in attacks with impairment of consciousness. Transcranial doppler studies showed a dramatic drop in cerebral perfusion in the middle cerebral arteries during the episodes. The combination of the stereotyped semiology of the attacks, the pseudofocal myoclonic jerking, and the rhythmic generalized slow wave EEG abnormalities with the tachycardia make differential diagnosis from epilepsy challenging.

Medical management with interventional therapy versus medical management alone for unruptured brain arteriovenous malformations (ARUBA): final follow-up of a multicentre, non-blinded, randomised controlled trial.

BACKGROUND: In A Randomized trial of Unruptured Brain Arteriovenous malformations (ARUBA), randomisation was halted at a mean follow-up of 33·3 months after a prespecified interim analysis showed that medical management alone was superior to the combination of medical management and interventional therapy in preventing symptomatic stroke or death. We aimed to study whether these differences persisted through 5-years' follow-up. METHODS: ARUBA was a non-blinded, randomised trial done at 39 clinical centres in nine countries. Adults (age ≥18 years) diagnosed with an unruptured brain arteriovenous malformation, who had never undergone interventional therapy, and were considered by participating clinical centres to be suitable for intervention to eradicate the lesion, were eligible for inclusion. Patients were randomly assigned (1:1) by a web-based data collection system, stratified by clinical centre in a random permuted block design with block sizes of two, four, and six, to medical management alone or with interventional therapy (neurosurgery, embolisation, or stereotactic radiotherapy, alone or in any combination, sequence, or number). Although patients and investigators at a given centre were not masked to treatment assignment, investigators at other centres and those in the clinical coordinating centre were not informed of assignment or outcomes at any of the centres. The primary outcome was time to death or symptomatic stroke confirmed by imaging, assessed by a neurologist at each centre not involved in the management of participants' care, and monitored by an independent committee using an adaptive approach with interim analyses. Enrolment began on April 4, 2007, and was halted on April 15, 2013, after which follow-up continued until July 15, 2015. All analyses were by intention to treat. This trial is registered with ClinicalTrials.gov, NCT00389181. FINDINGS: Of 1740 patients screened, 226 were randomly assigned to medical management alone (n=110) or medical management plus interventional therapy (n=116). During a mean follow-up of 50·4 months (SD 22·9), the incidence of death or symptomatic stroke was lower with medical management alone (15 of 110, 3·39 per 100 patient-years) than with medical management with interventional therapy (41 of 116, 12·32 per 100 patient-years; hazard ratio 0·31, 95% CI 0·17 to 0·56). Two patients in the medical management group and four in the interventional therapy group (two attributed to intervention) died during follow-up. Adverse events were observed less often in patients allocated to medical management compared with interventional therapy (283 vs 369; 58·97 vs 78·73 per 100 patient-years; risk difference -19·76, 95% CI -30·33 to -9·19). INTERPRETATION: After extended follow-up, ARUBA showed that medical management alone remained superior to interventional therapy for the prevention of death or symptomatic stroke in patients with an unruptured brain arteriovenous malformation. The data concerning the disparity in outcomes should affect standard specialist practice and the information presented to patients. The even longer-term risks and differences between the two therapeutic approaches remains uncertain. FUNDING: National Institute of Neurological Disorders and Stroke for the randomisation phase and Vital Projects Fund for the follow-up phase.

Cerebral microbleeds and intracranial haemorrhage risk in patients anticoagulated for atrial fibrillation after acute ischaemic stroke or transient ischaemic attack (CROMIS-2): a multicentre observational cohort study.

BACKGROUND: Cerebral microbleeds are a potential neuroimaging biomarker of cerebral small vessel diseases that are prone to intracranial bleeding. We aimed to determine whether presence of cerebral microbleeds can identify patients at high risk of symptomatic intracranial haemorrhage when anticoagulated for atrial fibrillation after recent ischaemic stroke or transient ischaemic attack. METHODS: Our observational, multicentre, prospective inception cohort study recruited adults aged 18 years or older from 79 hospitals in the UK and one in the Netherlands with atrial fibrillation and recent acute ischaemic stroke or transient ischaemic attack, treated with a vitamin K antagonist or direct oral anticoagulant, and followed up for 24 months using general practitioner and patient postal questionnaires, telephone interviews, hospital visits, and National Health Service digital data on hospital admissions or death. We excluded patients if they could not undergo MRI, had a definite contraindication to anticoagulation, or had previously received therapeutic anticoagulation. The primary outcome was symptomatic intracranial haemorrhage occurring at any time before the final follow-up at 24 months. The log-rank test was used to compare rates of intracranial haemorrhage between those with and without cerebral microbleeds. We developed two prediction models using Cox regression: first, including all predictors associated with intracranial haemorrhage at the 20% level in univariable analysis; and second, including cerebral microbleed presence and HAS-BLED score. We then compared these with the HAS-BLED score alone. This study is registered with ClinicalTrials.gov, number NCT02513316. FINDINGS: Between Aug 4, 2011, and July 31, 2015, we recruited 1490 participants of whom follow-up data were available for 1447 (97%), over a mean period of 850 days (SD 373; 3366 patient-years). The symptomatic intracranial haemorrhage rate in patients with cerebral microbleeds was 9·8 per 1000 patient-years (95% CI 4·0-20·3) compared with 2·6 per 1000 patient-years (95% CI 1·1-5·4) in those without cerebral microbleeds (adjusted hazard ratio 3·67, 95% CI 1·27-10·60). Compared with the HAS-BLED score alone (C-index 0·41, 95% CI 0·29-0·53), models including cerebral microbleeds and HAS-BLED (0·66, 0·53-0·80) and cerebral microbleeds, diabetes, anticoagulant type, and HAS-BLED (0·74, 0·60-0·88) predicted symptomatic intracranial haemorrhage significantly better (difference in C-index 0·25, 95% CI 0·07-0·43, p=0·0065; and 0·33, 0·14-0·51, p=0·00059, respectively). INTERPRETATION: In patients with atrial fibrillation anticoagulated after recent ischaemic stroke or transient ischaemic attack, cerebral microbleed presence is independently associated with symptomatic intracranial haemorrhage risk and could be used to inform anticoagulation decisions. Large-scale collaborative observational cohort analyses are needed to refine and validate intracranial haemorrhage risk scores incorporating cerebral microbleeds to identify patients at risk of net harm from oral anticoagulation. FUNDING: The Stroke Association and the British Heart Foundation.

Toward the Automation of Diagnostic Conversation Analysis in Patients with Memory Complaints.

BACKGROUND: The early diagnosis of dementia is of great clinical and social importance. A recent study using the qualitative methodology of conversation analysis (CA) demonstrated that language and communication problems are evident during interactions between patients and neurologists, and that interactional observations can be used to differentiate between cognitive difficulties due to neurodegenerative disorders (ND) or functional memory disorders (FMD). OBJECTIVE: This study explores whether the differential diagnostic analysis of doctor-patient interactions in a memory clinic can be automated. METHODS: Verbatim transcripts of conversations between neurologists and patients initially presenting with memory problems to a specialist clinic were produced manually (15 with FMD, and 15 with ND). A range of automatically detectable features focusing on acoustic, lexical, semantic, and visual information contained in the transcripts were defined aiming to replicate the diagnostic qualitative observations. The features were used to train a set of five machine learning classifiers to distinguish between ND and FMD. RESULTS: The mean rate of correct classification between ND and FMD was 93% ranging from 97% by the Perceptron classifier to 90% by the Random Forest classifier.Using only the ten best features, the mean correct classification score increased to 95%. CONCLUSION: This pilot study provides proof-of-principle that a machine learning approach to analyzing transcripts of interactions between neurologists and patients describing memory problems can distinguish people with neurodegenerative dementia from people with FMD.