Identifying dementia early in time, using real world data, is a public health challenge. As only two-thirds of people with dementia now ultimately receive a formal diagnosis in United Kingdom health ...systems and many receive it late in the disease process, there is ample room for improvement. The policy of the UK government and National Health Service (NHS) is to increase rates of timely dementia diagnosis. We used data from general practice (GP) patient records to create a machine-learning model to identify patients who have or who are developing dementia, but are currently undetected as having the condition by the GP.
We used electronic patient records from Clinical Practice Research Datalink (CPRD). Using a case-control design, we selected patients aged >65y with a diagnosis of dementia (cases) and matched them 1:1 by sex and age to patients with no evidence of dementia (controls). We developed a list of 70 clinical entities related to the onset of dementia and recorded in the 5 years before diagnosis. After creating binary features, we trialled machine learning classifiers to discriminate between cases and controls (logistic regression, naïve Bayes, support vector machines, random forest and neural networks). We examined the most important features contributing to discrimination.
The final analysis included data on 93,120 patients, with a median age of 82.6 years; 64.8% were female. The naïve Bayes model performed least well. The logistic regression, support vector machine, neural network and random forest performed very similarly with an AUROC of 0.74. The top features retained in the logistic regression model were disorientation and wandering, behaviour change, schizophrenia, self-neglect, and difficulty managing.
Our model could aid GPs or health service planners with the early detection of dementia. Future work could improve the model by exploring the longitudinal nature of patient data and modelling decline in function over time.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
To determine comparative fracture risk in HIV patients compared with uninfected controls.
A randomised cross-sectional study assessing bone mineral density (BMD), fracture history and risk factors in ...the 2 groups.
Hospital Outpatients.
222 HIV infected patients and an equal number of age-matched controls.
Fracture risk factors were assessed and biochemical, endocrine and bone markers measured. BMD was assessed at hip and spine. 10-year fracture probability (FRAX) and remaining lifetime fracture probability (RFLP) were calculated.
BMD, and history of fractures.
Reported fractures occurred more frequently in HIV than controls, (45 vs. 16; 20.3 vs. 7%; OR=3.27; p=0.0001), and unsurprisingly in this age range, non-fragility fractures in men substantially contributed to this increase. Osteoporosis was more prevalent in patients with HIV (17.6% vs. 3.6%, p<0.0001). BMD was most reduced, and predicted fracture rates most increased, at the spine. Low BMD was associated with antiretroviral therapy (ART), low body mass index and PTH. 10-year FRAX risk was <5% for all groups. RLFP was greater in patients with HIV (OR=1.22; p=0.003) and increased with ART (2.4 vs. 1.50; OR= 1.50; p=0.03).
The increased fracture rate in HIV patients in our relatively youthful population is partly driven by fractures, including non-fragility fractures, in men. Nonetheless, these findings may herald a rise in osteoporotic fractures in HIV patients. An appropriate screening and management response is required to assess these risks and identify associated lifestyle factors that are also associated with other conditions such as cardiovascular disease and diabetes.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Dr. Tsiakalos should be listed as the ninth author and affiliated with Third Department of Internal Medicine, Medical School, National and Kapodistrian University of Athens, Athens, Greece. (2013) ...Correction: A Cross-Sectional Randomised Study of Fracture Risk in People with HIV Infection in the Probono 1 Study.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Objective: There is evidence from neuroimaging studies of an association between insomnia and early dementia biomarkers, but observational studies have so far failed to show a clear association ...between insomnia and the later development of dementia. We investigated the association between dementia diagnosis and recording of insomnia symptoms 5-10 years earlier in primary care.
Method: A case-control study using data from the Clinical Practice Research Datalink. 15,209 cases with dementia (either Alzheimer's, vascular, mixed or non-specific subtypes) at least 65 years old at time of diagnosis, were matched with the same number of controls on year of birth and gender. We ascertained the presence of insomnia symptoms during a five-year period starting 10 years before the index date. Odds ratios for developing dementia were estimated using logistic regression after controlling for hypnotic exposure and physical and mental health comorbidities.
Results: The adjusted odds ratio for dementia in those with previous insomnia was 1.34 (95% CI = 1.20-1.50).
Conclusion: There is an association between dementia and previous insomnia. It may be possible to incorporate insomnia into predictive tools for dementia.
Celotno besedilo
Dostopno za:
BFBNIB, DOBA, IZUM, KILJ, NUK, OILJ, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK, VSZLJ
Aims
To assess follow-up of sodium levels for in-patients prescribed antidepressants in practice compare to the standard of 3 monthly sodium levels for all patients who are prescribed antidepressants ...and at risk of hyponatraemia
Method
A list of the 20 most recently discharged patients from Meridian Ward, an older-adult functional inpatient ward, was prepared by the team administrator on 6th May 2020.
We audited the entire duration of our patient's stay on Meridian Ward (we did not include periods of their admission when they were on other wards) using the electronic notes system, Carenotes.
We also checked the electronic biochemistry results system, ICE, for sodium results, and the discharge summary for mentions of fluid restriction, medications and handover to GP of sodium-checking. We also checked scanned drug charts to see if they were on antidepressants and other implicated drugs.
For people with episodes of hyponatraemia, in order to retrieve further info we looked at discharge summary and searched the activity notes for the following terms
“Hyponat”
“sodium”
“fluid restrict”
“Low na”
We regarded the following conditions as risk factors for hyponatraemia:
cardiac
malignancy
respiratory
hypothyroid
renal
hepatic
stroke
We regarded following medications as risk factors:
opioids
diuretics
carbamazepine
theophylline
antipsychotics
NSAIDs
PPIs
ACE-I
ARBs
amiodarone
domperidone
sulphonylureas
Result
14 of the 20 patients were taking antidepressants. Of those: 13 were eligible for regular sodium monitoring due to risk factors 11 of these had 3-monthly sodium levels during admission For only 2 of these did we make a plan for the GP to continue to monitor the sodium level in community 3 had an episode of hyponatraemia implicated antidepressants: sertraline plus mirtazapine mirtazapine (very serious episode which caused seizure) sertraline for 2 of them an appropriate plan was made 1 without a plan - a mild hyponatraemia with nothing documented in the notes
Conclusion
During their admission to Meridian Ward, 85% of patients taking antidepressants who had risk factors for hyponatraemia had three-monthly sodium levels in line with the trust guidance. However, only two patients (15%) had a plan for further sodium levels in the discharge summary sent to the GP. This highlights a need for improved awareness of risk factors for hyponatraemia and, in particular, improved communication with general practitioners who are going to take over prescribing of antidepressant medications.
Recommendations
3 monthly Na levels for all patients with risk factors
i.e. on any antidepressant prescribed PLUS any one of:
>80 years
History of low sodium
AKI during admission
Relevant comorbidities (see above)
>1 antidepressant
Other meds that can cause hyponatraemia
More frequent monitoring for all those with with multiple risk factors AND who are starting/increasing antidepressant:
baseline sodium plus repeat after 2 and 4 weeks
Communicate to GP the need for 3-monthly sodium monitoring for those with above risk factors
Re-audit in 6-12 months’ time
Dementia is one of the most feared illnesses that has a growing year-to-year negative global impact, having a health and social care cost higher than cancer, stroke and chronic heart disease, taken ...together. Without the availability of a cure, nor a standardised clinical test, the utilisation of machine learning methods to identify individuals that are at risk of developing dementia could bring a new step towards proactive intervention. This study's goal is to carry out a precursor analysis leading to building classification models with enhanced capabilities for differentiating diagnoses of CN (Cognitively Normal), MCI (Mild Cognitive Impairment) and Dementia. The predictive modelling approach we propose is based on the ReliefF method combined with statistical permutation tests for feature selection, and on model training, tuning, and testing based on algorithms such as Random Forests, Support Vector Machines, Gaussian Processes, Stochastic Gradient Boosting, and eXtreme Gradient Boosting. Stability of model performances were studied in computationally intensive Monte Carlo simulations. The results consistently show that our models accurately detect dementia, and also mild cognitive impairment patients by only using the inclusion of baseline measurements as predictors, thus illustrating the importance of baseline measurements. The best results issued from Monte Carlo were achieved by eXtreme Gradient Boosting optimised models, with an accuracy of 0.88 (SD 0.02), a sensitivity of 0.93 (SD 0.02) and a specificity of 0.94 (SD 0.01) for dementia, and a sensitivity of 0.86 (SD 0.02) and a specificity of 0.9 (SD 0.02) for mild cognitive impairment. These results support in particular future developments for a risk-based method that can identify an individual's risk of developing dementia.