Materiały źródłowe

• #1 The prognosis of mild cognitive impairment: A systematic review and meta-analysis – PubMed

  https://pubmed.ncbi.nlm.nih.gov/40078377/

  Knowledge gaps remain about the prognosis of mild cognitive impairment (MCI). Conversion rates to dementia vary widely, and reversion to normal cognition has gained attention. This review updates evidence on MCI conversion risk and probability of stability and reversion. From 89 studies (mean follow-up: 5.2 years), conversion risk was 41.5% (38.3%-44.7%) in clinical and 27.0% (22.0%-32.0%) in population-based studies, with Alzheimer’s dementia as the most common outcome. Stability rates were 49.3% (clinical) and 49.8% (population). Reversion was 8.7% (clinical) and 28.2% (population). Our findings highlight higher conversion in clinical settings and 30% reversion in population studies, calling for sustainable care pathway development. […] Prognosis for mild cognitive impairment (MCI) varies by setting; dementia risk is higher and the probability of reversion is lower in clinical-based studies. In both clinical and population settings, cognitive stability is 50%. A reorganization of health services could ensure sustainable care for individuals with MCI. Significant heterogeneity in MCI studies impacts data interpretation; follow-up length is crucial. Long-term prognosis studies on MCI in low- and middle-income countries are urgently needed.

• #2 Screening and predicting progression from high-risk mild cognitive impairment to Alzheimer’s disease | Scientific Reports

  https://www.nature.com/articles/s41598-021-96914-3

  Individuals with mild cognitive impairment (MCI) are clinically heterogeneous, with different risks of progression to Alzheimers disease. […] Therefore, identifying patients with MCI who are at risk of progression to AD and improving the prognosis of MCI is of vital importance in the personalised clinical management of AD. […] The optimal model included a change rate of clinical assessments and three neuroimaging measurements and was significantly associated with a net reclassification improvement (NRI) of 0.246 (95% CI 0.021, 0.848) and integrated discrimination improvement (IDI) of 0.090 (95% CI0.062, 0.170). […] Considering the limited medical and financial resources, our findings recommend follow-up MRI examination 1 year after identification for high-risk individuals, while regular clinical assessments for low-risk individuals.

• #3 Prognosis prediction model for conversion from mild cognitive impairment to Alzheimer’s disease created by integrative analysis of multi-omics data | Alzheimer’s Research & Therapy | Full Text

  https://alzres.biomedcentral.com/articles/10.1186/s13195-020-00716-0

  Mild cognitive impairment (MCI) is a precursor to Alzheimers disease (AD), but not all MCI patients develop AD. Biomarkers for early detection of individuals at high risk for MCI-to-AD conversion are urgently required. […] The final prediction model, composed of 24 miR-eQTLs and three clinical factors (age, sex, and APOE4 alleles), successfully classified MCI patients into low and high risk of MCI-to-AD conversion (log-rank test P=3.44104 and achieved a concordance index of 0.702 on an independent test set. […] Our proposed model was demonstrated to be effective in MCI-to-AD conversion prediction. […] Accurate prediction of MCI-to-AD conversion would enable earlier intervention for MCI patients at high risk, potentially reducing conversion to AD. […] The annual conversion rate from MCI to AD has been reported as 10 to 15%. After 6 years of follow-up, approximately 80% of MCI patients will have converted to AD (MCI converters [MCI-C])

• #4 Selecting the most important self-assessed features for predicting conversion to mild cognitive impairment with random forest and permutation-based methods | Scientific Reports

  https://www.nature.com/articles/s41598-020-77296-4

  Mild cognitive impairment (MCI) is an intermediary stage between the expected decline of normal aging and the pathological decline associated with dementia. The prevalence of MCI may vary depending on the studies with estimates from ∼3 to ∼42% prevalence, existing however an agreement that age is the most important risk factor. Compared to cognitively normal individuals, MCI patients have a higher risk of progressing to dementia. The annual conversion rate from MCI to AD is approximately ∼517%, much higher than for the general population whose rate is about ∼12%. […] Since the diagnosis of MCI has a marked prognostic value, its early detection has become a priority target in aging research for the last few years. […] The strongest result in this study is that the most important self-assessed variable for future conversion to MCI is the subjective cognitive decline (SCD) which is selected as the most important across all the feature selection techniques -filter method, embedded method, and permutation-based methods. This result is not unexpected if we acknowledge that self-report of subtle cognitive decline can appear at the end of the preclinical stage of AD even in the absence of significant objective impairment detectable in standardized neuropsychological assessment.

• #5 Predicting progression of mild cognitive impairment to dementia using neuropsychological data: a supervised learning approach using time windows | BMC Medical Informatics and Decision Making | Full Text

  https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-017-0497-2

  Clinical studies with MCI patients have reported higher risk rates of conversion to dementia (in particularly to AD) than community studies, suggesting these patients as a group of singular interest to follow-up studies and interventions. […] In a recent systematic review, MCI diagnosis was associated with an annual conversion rate up to 20%, however with substantial variation in risk estimates. […] Despite the efforts, to date, no single biomarker to predict conversion from MCI to dementia with high accuracy was yet found. […] The proposed Time Windows approach reduces the heterogeneity in MCI population caused by the slow cognitive decline characteristic in dementia. […] As a result, we foresee more accurate prognostic models, as classifiers learn from a set of patients with similar disease progression patterns.

• #6 Identification of Outcome-Oriented Progression Subtypes from Mild Cognitive Impairment to Alzheimer’s Disease Using Electronic Health Records | medRxiv

  https://www.medrxiv.org/content/10.1101/2023.07.27.23293270.full

  Alzheimers disease (AD) is a complex heterogeneous neurodegenerative disease that requires an in-depth understanding of its progression pathways and contributing factors to develop effective risk stratification and prevention strategies. […] Mild cognitive impairment (MCI) is a translational intermediate state between normal cognitive function and dementia. […] The management of AD has identified MCI as a crucial target for both prognosis and therapy. […] However, not all MCI patients will convert to AD, and approximately 10% to 20% of individuals with MCI will advance to AD within one year, while the remaining individuals who do not progress to AD may either experience other types of dementia or maintain stability. […] Therefore, understanding the progression of those individuals progressing from MCI to AD and identifying early diagnostic markers are of increasing clinical importance, which is essential to develop effective therapies and improve the quality of patients life.

• #7 Mild Cognitive Impairment Progression and Alzheimer’s Disease Risk: A Comprehensive Analysis of 3553 Cases over 203 Months

  https://www.mdpi.com/2077-0383/13/2/518

  Mild cognitive impairment (MCI), also known as „preclinical dementia”, describes a condition marked by cognitive decline exceeding what is expected for one’s age and education level but not meeting the criteria for dementia. […] This study revealed an overall progression rate of 92.8% from MCI to the clinical stage of dementia during the follow-up period, with an annual rate of 15.7%. […] Notably, all prodromal cases of Lewy body dementia/Parkinson’s disease (LBD/PDD) and frontotemporal dementia (FTD) advanced to clinical stages, whereas 7% of vascular dementia (VaD) cases and 8.4% of AD cases remained in the prodromal stage throughout follow-up. […] Furthermore, we observed a faster progression rate in MCI-AD cases compared to non-AD sufferers (53.9% vs. 35.5%, Entropy: 0.850). […] It is important to note that not all individuals with MCI will progress to dementia, and there is no definitive way to predict which individuals will.

• #8 Study protocol for a prediction model for mild cognitive impairment in older adults with diabetes mellitus and construction of a nurse-led screening system: a prospective observational study | BMJ Open

  https://bmjopen.bmj.com/content/14/2/e075466

  Mild cognitive impairment (MCI) refers to a mild decline in memory and other thought processes but not functional decline. A recent study estimated that the overall prevalence of MCI in China is 15.5%. MCI is a transitional stage between normal cognitive function and dementia. Approximately 10%15% of older adults with MCI would develop dementia. Meanwhile, 10%40% of MCI cases can revert to normal cognition for more than 45 years. Hence, people with MCI are the key population for secondary prevention of dementia. […] Diabetes mellitus (DM) is an important risk factor for dementia. DM may increase the risk of progression from MCI to dementia, in addition to increasing the risk of progression from intact cognition to dementia. Researchers have also found that diabetes and pre-diabetes inhibit MCI reversion. Current theories indicate that hyperglycaemia, cerebral microvascular injury, insulin resistance, altered insulin signalling, neuroinflammation and build-up of cerebral amyloid and tau proteins may contribute to the pathophysiology underlying cognitive decline and DM.

• #9 Mild Cognitive Impairment (MCI): Symptoms & Treatment

  https://my.clevelandclinic.org/health/diseases/17990-mild-cognitive-impairment

  Some people with MCI eventually develop dementia, but others don’t. […] Studies show that about 15% of people with MCI older than age 65 years developed dementia within two years of the initial MCI diagnosis. […] The rate of decline in someone with mild cognitive impairment often depends on the underlying cause. […] Researchers continue to study the mental and medical changes that occur in people with MCI. They hope to one day be able to better predict who might be at an increased risk of developing and the speed at which they develop specific types of dementia.

• #10 Selecting the most important self-assessed features for predicting conversion to mild cognitive impairment with random forest and permutation-based methods | Scientific Reports

  https://www.nature.com/articles/s41598-020-77296-4

  Subjective cognitive decline may span for over one decade before it eventuates in MCI and AD. Furthermore, there is evidence about the relationship between SCD and AD biomarkers such as brain amyloid deposition, cerebral hypometabolism, altered brain connectivity, and atrophy. […] Our results show other recurrent risk factors that increase the likelihood of developing MCI and AD. Specifically, two are worth noting: APOE genotyping and cognitive reserve related variables. […] The feature selection problem of choosing the self-assessed features that contribute most to the target feature (conversion from normal cognition to MCI) was investigated using three different techniques. […] Random Forest showed a high predictive performance with an accuracy of 0.851 which may be considered relatively high bearing in mind that we only focused on self-reported features. […] Our results underlie then the utility of ensemble methods such as random forest and permutation-based methods as a triage risk screening tool, for example, to identify early on individuals that will likely require medical care at a later stage.

• #11 Prognosis prediction model for conversion from mild cognitive impairment to Alzheimer’s disease created by integrative analysis of multi-omics data | Alzheimer’s Research & Therapy | Full Text

  https://alzres.biomedcentral.com/articles/10.1186/s13195-020-00716-0

  Therefore, biomarkers for early detection of MCI-C and prognosis prediction models are both desperately required. […] Our final prediction model produced similar C-indices (0.718 and 0.702) in the discovery and validation cohorts and successfully classified MCI patients into two groups, low and high, in terms of risk of MCI-to-AD conversion (log-rank test P=3.63107 and 3.44104). […] These results demonstrate that miR-eQTLs could be efficient biomarkers for the early detection of individuals at high risk of MCI-to-AD conversion, although replication studies using a larger number of samples are necessary. […] Our findings represent SNP-miRNA pairs with eQTL effects. […] We have proposed an MCI-to-AD conversion prediction model based on a Cox proportional hazard method using SNP-miRNA pairs with eQTL effects. Our proposed model may enable early detection of patients at high risk of MCI-to-AD conversion. […] Important hub genes associated with AD pathogenesis were also identified in a network-based meta-analysis of miR-eQTL target genes.

• #12 Mild Cognitive Impairment Progression and Alzheimer’s Disease Risk: A Comprehensive Analysis of 3553 Cases over 203 Months

  https://www.mdpi.com/2077-0383/13/2/518

  However, the current understanding does not provide a consensus on which cases are more likely to advance to clinical phases during the preclinical stages, leaving clinicians without specific prognostic information to share with patients. […] Our study found that MCI-AD progresses faster than non-AD MCI (53.9% vs. 35.5%, Entropy = 0.850), and comorbid conditions, like epilepsy, impact progression, independent of gender or established biomarkers. […] The findings suggest that epilepsy and hypertension may play a role in the prognosis of Non-AD MCI patients, while epilepsy may predict rapid progression in MCI-AD patients.

• #13 Selecting the most important self-assessed features for predicting conversion to mild cognitive impairment with random forest and permutation-based methods | Scientific Reports

  https://www.nature.com/articles/s41598-020-77296-4

  Subjective cognitive decline may span for over one decade before it eventuates in MCI and AD. Furthermore, there is evidence about the relationship between SCD and AD biomarkers such as brain amyloid deposition, cerebral hypometabolism, altered brain connectivity, and atrophy. […] Our results show other recurrent risk factors that increase the likelihood of developing MCI and AD. Specifically, two are worth noting: APOE genotyping and cognitive reserve related variables. […] The feature selection problem of choosing the self-assessed features that contribute most to the target feature (conversion from normal cognition to MCI) was investigated using three different techniques. […] Random Forest showed a high predictive performance with an accuracy of 0.851 which may be considered relatively high bearing in mind that we only focused on self-reported features. […] Our results underlie then the utility of ensemble methods such as random forest and permutation-based methods as a triage risk screening tool, for example, to identify early on individuals that will likely require medical care at a later stage.

• #14 Predicting the Progression of Mild Cognitive Impairment Using Machine Learning: A Systematic, Quantitative and Critical Review | medRxiv

  https://www.medrxiv.org/content/10.1101/2020.09.01.20185959v1.full-text

  We performed a systematic review of studies focusing on the automatic prediction of the progression of mild cognitive impairment to Alzheimers 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 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.

• #15 Predicting the Progression of Mild Cognitive Impairment Using Machine Learning: A Systematic, Quantitative and Critical Review | medRxiv

  https://www.medrxiv.org/content/10.1101/2020.09.01.20185959v1.full-text

  We also highlight that shortterm 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. […] We showed that studies using cognitive variables or FDG PET reported significantly better results than studies that did not, and that including other feature types does not significantly improve performance compared to using cognition or FDG PET alone. These modalities should be further explored, cognition because it can be easily collected in clinical routine, and FDG PET for the interest it might represent for the imaging community and for increasing our understanding of the disease. […] In light of this review, we believe that one should give higher priority to other modalities. More specific cognitive tests could be created, and the impact of using digitized tests, that can be frequently used at home by the patients themselves, should be studied.

• #16 Screening and predicting progression from high-risk mild cognitive impairment to Alzheimer’s disease | Scientific Reports

  https://www.nature.com/articles/s41598-021-96914-3

  The results indicate that ADAS-13 is more sensitive in classifying patients with MCI and filtering out high-risk individuals. […] The A2+ ΔMRI model had the best predictive performance for progression to AD among high-risk patients with MCI. […] In conclusion, the study indicated that follow-up MRI examination is recommended 1 year after identification for high-risk patients, and regular clinical cognitive assessments for low-risk MCI patients, especially considering limited medical and financial resources.

• #17 Predicting progression of mild cognitive impairment to dementia using neuropsychological data: a supervised learning approach using time windows | BMC Medical Informatics and Decision Making | Full Text

  https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-017-0497-2

  Predicting progression from a stage of Mild Cognitive Impairment to dementia is a major pursuit in current research. […] This hampers the prognostic task. […] Nevertheless, when learning prognostic models, most studies use the entire cohort of MCI patients regardless of their disease stages. […] The proposed Time Windows approach outperformed the First Last approach. […] Prognostic models using time windows have higher performance when predicting progression from MCI to dementia, when compared to the prognostic approach commonly used in the literature. […] Furthermore, the proposed Time Windows approach is more relevant from a clinical point of view, predicting conversion within a temporal interval rather than sometime in the future and allowing clinicians to timely adjust treatments and clinical appointments.

• #18 Predicting progression of mild cognitive impairment to dementia using neuropsychological data: a supervised learning approach using time windows | BMC Medical Informatics and Decision Making | Full Text

  https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-017-0497-2

  The Time Windows approach is more relevant from a clinical point of view, as it provides a temporal interval of conversion thus allowing clinicians to timely adjust treatments and clinical appointments. […] Our prognostic model, using neuropsychological data, was able to predict conversion to dementia as early as 5 years before the event.

• #19 Predicting the Conversion from Mild Cognitive Impairment to Alzheimer’s Disease Using an Explainable AI Approach

  https://www.mdpi.com/2078-2489/15/5/249

  Hybrid approaches, which incorporate longitudinal and heterogeneous data along with supervised and unsupervised methods, have proven to be more effective under certain circumstances and generalize better, achieving results with up to 85% accuracy, particularly in distinguishing between MCI progressive from non-progressive cases. […] The importance of this prediction is high, as it can inform the healthcare professional of a potential worsening in the patient’s condition and can lead to earlier pharmacologic or non-pharmacologic intervention to delay the transition. […] Consequently, the development of a predictive model for MCI progression holds immense promise, offering significant advantages in both research and practical applications.

• #20 Alzheimer’s: Will doctors soon be able to predict cognitive decline?

  https://www.medicalnewstoday.com/articles/researchers-figure-out-how-they-could-predict-individual-stages-of-alzheimers

  The researchers constructed models predicting MMSE, which they then used to estimate time to reach an MMSE of 20 (mild dementia) for those with MCI, and 15 (moderate dementia) for those with mild dementia, using different baseline CSF amyloid and MMSE measurements. […] The predictions can also be used by a clinician to discuss with a patient the potential effect of a treatment. […] This research lays the foundation for the types of prognostic tools that can not only give us a sense of what might be expected along the road ahead, but also, how we might alter that course by addressing a variety of modifiable risk factors to change the disease trajectory and improve our chances of maintaining higher levels of cognitive health and function over a longer horizon.

• #21 Identification of Outcome-Oriented Progression Subtypes from Mild Cognitive Impairment to Alzheimer’s Disease Using Electronic Health Records | medRxiv

  https://www.medrxiv.org/content/10.1101/2023.07.27.23293270.full

  The objective of this paper is to develop a computational approach that can identify outcome-oriented progression pathways from MCI to AD using large collections of EHRs. […] By leveraging EHR data and machine learning, our approach can facilitate earlier diagnosis and intervention for AD, ultimately improving the quality of life for patients and their families. […] The results showed that a higher proportion of patients from Site B transitioned to AD but in average has a longer conversion time than Site A patients. […] Our analysis of both data sources revealed that there are two main distinct progression pathways that can be identified. […] These findings suggest that the progression of the disease may vary depending on the initial state that patients convert to. […] By better understanding the distinct subtypes of patients and their disease progression patterns, we may be able to develop more personalized and effective treatments for individuals with MCI, slowing down or preventing from their progression to AD.

• #22 Study protocol for a prediction model for mild cognitive impairment in older adults with diabetes mellitus and construction of a nurse-led screening system: a prospective observational study | BMJ Open

  https://bmjopen.bmj.com/content/14/2/e075466

  This prospective observational study will construct a nurse-led MCI screening system for older adults with DM who are likely to have MCI simultaneously. A prediction model will be developed and validated to assist nurses in the prompt and accurate detection of MCI by evaluating the contributions of the significant predictors available in primary care. […] This study will develop a nurse-led screening system for the timely detection of MCI in community-dwelling older adults with DM. Potential predictors will be identified through a comprehensive evaluation of demographic variables, lifestyle factors, history of diseases, physical examinations, laboratory tests and neuropsychological tests. This may assist nurses or health workers in modifying diabetes regimens or providing support for patient care in terms of cognitive impairment. The application of the model with the best performance in this study may help improve the efficiency of MCI detection in primary care and offer opportunities for early interventions for dementia prevention.

• #23 Alzheimer’s: Will doctors soon be able to predict cognitive decline?

  https://www.medicalnewstoday.com/articles/researchers-figure-out-how-they-could-predict-individual-stages-of-alzheimers

  Following a diagnosis, it is difficult to predict how the disease will progress in each person. […] Now, a research team in Amsterdam has designed a model that can predict cognitive decline in people with mild cognitive impairment or mild dementia due to Alzheimers disease. […] In some people, MCI can develop into dementia, such as Alzheimers disease, but it is hard to predict whether a person with MCI will go on to develop dementia. […] I think in the future it can. When patients get a diagnosis, their next question is: what can I expect? Or what is my prognosis? This model provides a first attempt to an answer. It provides a prognosis for cognitive decline on an individual basis, she told us. […] This is encouraging research as it suggests that researchers can produce a model which is able to predict how the symptoms experienced by people with mild cognitive impairment or early Alzheimers disease might change. Predicting how these symptoms may change cognition over time is vitally important for those living with dementia and their carers to prepare for the future, ultimately leading to better care.

Zobacz więcej