Factors associated with the intention to engage in care planning among persons with mild cognitive impairment and dementia.

This study examined factors associated with the intention to engage in advance care planning among persons with cognitive impairment. This cross-sectional study recruited 116 persons with cognitive impairment by convenience sampling from two teaching hospitals in Northern Taiwan from November 1, 2018, to December 31, 2020. Fewer than 50% of the participants intended to engage in advance care planning, and less than 10% signed the living will for hospice and palliative care. Multivariate linear regression determined factors influencing advance care planning intention included education level, a proxy signed do-not-resuscitate document, belief that family members would provide a signed do-not-resuscitate at their end-of-life, and necessity of explaining future care in advance. It is recommended to popularize advance care planning education and ensure the rights of persons with cognitive impairment to enable them to fully participate in their own care plans through family-centered advance care planning.

The effect of a family-centered advance care planning intervention for persons with cognitive impairment and their family caregivers on end-of-life care discussions and decisions.

Advanced care planning (ACP) includes advance directives (AD), which can specify provisions for palliative care and types of life-sustaining treatments for an individual requiring end-of-life (EoL) care. ACP for persons in the early stages of cognitive decline can decrease anxiety and conflict for family members needing to make decisions about EoL-care, which is especially critical for family caregivers (FCGs) if they play a role as a surrogate regarding healthcare decisions. However, ACP for persons with cognitive impairment (PWCIs) is often overlooked. This study explored the effects of a family-centered ACP intervention on decisions about EoL-care, life-sustaining treatment decisions, and discussions of related topics among PWCIs and FCGs. The study was conducted in outpatient clinics of regional teaching hospitals in northern Taiwan. Participants were dyads consisting of persons diagnosed with mild cognitive impairment or mild dementia and their FCGs. The family-centered ACP intervention was provided by an ACP-trained senior registered nurse. A one-group, pretest-posttest design was used to evaluate the effect of the intervention on 44 dyads. Four structured questionnaires collected data regarding familiarity with ACP, intention to engage in ACP, participation in personal discussions between the dyads about ACP, and consistency between PWCIs and FCGs for decisions about life-sustaining treatments at EoL. Paired t, Kappa, and McNemar tests were used to compare differences between pre-intervention data (pretest) and post-intervention data (posttest). There were significant increases in familiarity with ACP, components of ACP, and the number of topics PWCIs and FCGs personally discussed surrounding EoL-care decisions. There was no change for either group in wanting to have a formal ACP consultation and only modest increases in consistency between PWCIs and FCGs for life-sustaining treatment decisions after completion of the family-centered ACP intervention. Clinicians caring for PWCIs should incorporate family-centered ACP interventions and support ongoing discussions about life-sustaining medical treatments to ensure their preferences regarding EoL-care are respected. The accessibility and availability of consultations about ACP should also be provided.

Deduction learning for precise noninvasive measurements of blood glucose with a dozen rounds of data for model training.

Personalized modeling has long been anticipated to approach precise noninvasive blood glucose measurements, but challenged by limited data for training personal model and its unavoidable outlier predictions. To overcome these long-standing problems, we largely enhanced the training efficiency with the limited personal data by an innovative Deduction Learning (DL), instead of the conventional Induction Learning (IL). The domain theory of our deductive method, DL, made use of accumulated comparison of paired inputs leading to corrections to preceded measured blood glucose to construct our deep neural network architecture. DL method involves the use of paired adjacent rounds of finger pulsation Photoplethysmography signal recordings as the input to a convolutional-neural-network (CNN) based deep learning model. Our study reveals that CNN filters of DL model generated extra and non-uniform feature patterns than that of IL models, which suggests DL is superior to IL in terms of learning efficiency under limited training data. Among 30 diabetic patients as our recruited volunteers, DL model achieved 80% of test prediction in zone A of Clarke Error Grid (CEG) for model training with 12 rounds of data, which was 20% improvement over IL method. Furthermore, we developed an automatic screening algorithm to delete low confidence outlier predictions. With only a dozen rounds of training data, DL with automatic screening achieved a correlation coefficient ([Formula: see text]) of 0.81, an accuracy score ([Formula: see text]) of 93.5, a root mean squared error of 13.93 mg/dl, a mean absolute error of 12.07 mg/dl, and 100% predictions in zone A of CEG. The nonparametric Wilcoxon paired test on [Formula: see text] for DL versus IL revealed near significant difference with p-value 0.06. These significant improvements indicate that a very simple and precise noninvasive measurement of blood glucose concentration is achievable.

90% Accuracy for Photoplethysmography-Based Non-Invasive Blood Glucose Prediction by Deep Learning with Cohort Arrangement and Quarterly Measured HbA1c.

Previously published photoplethysmography-(PPG) based non-invasive blood glucose (NIBG) measurements have not yet been validated over 500 subjects. As illustrated in this work, we increased the number subjects recruited to 2538 and found that the prediction accuracy (the ratio in zone A of Clarke's error grid) reduced to undesirable 60.6%. We suspect the low prediction accuracy induced by larger sample size might arise from the physiological diversity of subjects, and one possibility is that the diversity might originate from medication. Therefore, we split the subjects into two cohorts for deep learning: with and without medication (1682 and 856 recruited subjects, respectively). In comparison, the cohort training for subjects without any medication had approximately 30% higher prediction accuracy over the cohort training for those with medication. Furthermore, by adding quarterly (every 3 months) measured glycohemoglobin (HbA1c), we were able to significantly boost the prediction accuracy by approximately 10%. For subjects without medication, the best performing model with quarterly measured HbA1c achieved 94.3% prediction accuracy, RMSE of 12.4 mg/dL, MAE of 8.9 mg/dL, and MAPE of 0.08, which demonstrates a very promising solution for NIBG prediction via deep learning. Regarding subjects with medication, a personalized model could be a viable means of further investigation.

[The Impact of Family-Centered Advance Care Planning for Persons With Dementia and Family Caregivers on Decision-Making Conflicts in End-of-Life Care].

BACKGROUND: Participating in advance care planning (ACP) discussions during the early stages of dementia is crucial to ensuring the quality of end-of-life (EoL) care. Inadequate discussions regarding ACP and EoL care between persons with dementia and family caregivers often lead to decisional conflicts when persons with dementia are in the later stages of their disease. PURPOSE: To explore the impact of a family-centered ACP information intervention on the EoL care decision-making conflicts between persons with dementia and their family caregivers. METHODS: A one-group, pretest-posttest, pre-experimental design was applied. Data were collected at outpatient clinics in regional teaching hospitals in northern Taiwan. Participants included 43 dyads of persons diagnosed with mild cognitive impairment or mild dementia and their family caregivers. The intervention was implemented by an ACP-trained senior registered nurse and was guided using ACP manuals and family-centered strategies. The decisional conflict scale was the main measure used. Paired t tests were used to compare differences between pre-intervention data and 4-weeks' post-intervention data. RESULTS: The ACP information intervention significantly reduced the decisional conflict score for end-of-life decision making in the participants with mild dementia (p < .001). In addition, significant declines were observed in all aspects of decision-making conflicts, including value clarification, uncertainty, and effective decision-making. The mean total conflict score of the family caregivers was also significantly reduced (p < .001), but no significant difference was found in the aspect of support. CONCLUSIONS: Family-centered care strategies provide knowledge about end-of-life care for persons with dementia. These strategies also facilitate regular and continuous communication between family caregivers, persons with dementia, and medical professionals, reducing decisional conflicts in EoL care.

Advance care planning information intervention for persons with mild dementia and their family caregivers: Impact on end-of-life care decision conflicts.

Persons with dementia are at high risk for loss of decision-making ability due to increased cognitive decline as the disease progresses. Participation in advance care planning (ACP) discussions in the early stages of dementia is crucial for end-of-life (EoL) decision-making to ensure quality of EoL care. A lack of discussions about ACP and EoL care between persons with dementia and family caregivers (FCGs), can lead to decisional conflicts when persons with dementia are in the later stages of the disease. This study explored the effects of a family-centered ACP information intervention among persons with dementia and FCGs. The study was conducted in outpatient clinics in Taiwan. Participants were dyads (n = 40) consisting of persons diagnosed with mild cognitive impairment or mild dementia and their FCGs. A one-group, pretest-posttest, pre-experimental design was employed. The intervention was provided by an ACP-trained senior registered nurse and was guided by ACP manuals and family-centered strategies. Outcome data were collected with four structured questionnaires regarding knowledge of end-stage dementia treatment, knowledge of ACP, attitude towards ACP, and EoL decisional conflict about acceptance or refusal of cardiopulmonary resuscitation, ventilators, and tracheostomy. Paired t tests compared differences between pre-intervention data and 4-weeks' post-intervention data. The intervention resulted in significant improvements among persons with dementia and FCGs for knowledge of end-stage dementia treatment (p = .008 and p < .001, respectively), knowledge of ACP (both p < .001), and significant reductions in decisional conflicts (both p < .001). Scores for positive and negative attitude toward ACP did not change for persons with dementia; however, there was a reduction in negative attitude for FCGs (p = .001). Clinical care for persons with dementia should incorporate ACP interventions that provide knowledge about EoL dementia care using family-centered care strategies that facilitate regular and continuous communication between FCGs, persons with dementia, and medical personnel to reduce decisional conflicts for EoL care.