RESUMEN

This paper considers the problems of modeling and predicting a long-term and "blurry" relapse that occurs after a medical act, such as a surgery. We do not consider a short-term complication related to the act itself, but a long-term relapse that clinicians cannot explain easily, since it depends on unknown sets or sequences of past events that occurred before the act. The relapse is observed only indirectly, in a "blurry" fashion, through longitudinal prescriptions of drugs over a long period of time after the medical act. We introduce a new model, called ZiMM (Zero-inflated Mixture of Multinomial distributions) in order to capture long-term and blurry relapses. On top of it, we build an end-to-end deep-learning architecture called ZiMM Encoder-Decoder (ZiMM ED) that can learn from the complex, irregular, highly heterogeneous and sparse patterns of health events that are observed through a claims-only database. ZiMM ED is applied on a "non-clinical" claims database, that contains only timestamped reimbursement codes for drug purchases, medical procedures and hospital diagnoses, the only available clinical feature being the age of the patient. This setting is more challenging than a setting where bedside clinical signals are available. Our motivation for using such a non-clinical claims database is its exhaustivity population-wise, compared to clinical electronic health records coming from a single or a small set of hospitals. Indeed, we consider a dataset containing the claims of almost all French citizens who had surgery for prostatic problems, with a history between 1.5 and 5 years. We consider a long-term (18 months) relapse (urination problems still occur despite surgery), which is blurry since it is observed only through the reimbursement of a specific set of drugs for urination problems. Our experiments show that ZiMM ED improves several baselines, including non-deep learning and deep-learning approaches, and that it allows working on such a dataset with minimal preprocessing work.

Asunto(s)

RESUMEN

BACKGROUND: The 16-item Vitamin D Status Predictor (VDSP) questionnaire helps to identify, without resorting to a blood test, older adults with low vitamin D concentrations. Our objective was to determine whether a self-administered VDSP was concordant with the VDSP administered by a physician, and to examine the concordance of every single item of the VDSP. METHODS: A total of 349 older in- and outpatients (mean, 83.2±7.2years; 59% female) were consecutively recruited in the geriatric ward of the University Hospital of Angers, France. All participants completed a self-administered VDSP questionnaire (self-VDSP) in paper format composed of 17 items exploring age, gender, general condition, nutrition, vision, mood, cognition, gait and falls, and osteoporosis. All participants underwent subsequently a full clinical examination by a physician exploring the same areas (rater-VDSP). RESULTS: The agreement between the self-VDSP and the rater-VDSP was almost perfect for the probability of having low vitamin D concentrations, regardless of the definition used (i.e., ≤25, ≤50 or ≤75 nmol/L). The agreements between physicians' and patients' responses were significant for every single VDSP item. The agreement was fair to perfect for all items, except for cognitive disorders, undernutrition and polymorbidity (poor agreement). CONCLUSIONS: Older adults are able to evaluate their own probabilities of severe vitamin D deficiency, deficiency and insufficiency. A self-questionnaire may promote the use of the VDSP tool in this population, and help clinicians in decisions to supplement their patients in a reasoned way.

Asunto(s)

RESUMEN

The 16-item Vitamin D Status Predictor (VDSP) tool identifies healthy older community-dwellers at risk of hypovitaminosis D and may guide the use of blood tests in this population. The objective of the present hospital-based study was to test the efficacy of the VDSP to identify geriatric patients with hypovitaminosis D. The study included 199 nonsupplemented geriatric in- and outpatients consecutively admitted to Angers University Hospital, France (mean ± SD, 82.0 ± 7.8 years; 53.3% female). Serum 25-hydroxyvitaminD (25(OH)D) was measured at the time of the physician-administered VDSP. Hypovitaminosis D was defined as serum 25(OH)D concentration ≤ 75 nmol/L for vitamin D insufficiency, 25(OH)D ≤ 50 nmol/L for vitamin D deficiency, and 25(OH)D ≤ 25 nmol/L for severe vitamin D deficiency. We found that 184 participants (92.4%) had vitamin D insufficiency, 136 (68.3%) had vitamin D deficiency, and 67 (33.7%) had severe vitamin D deficiency. The VDSP identified severe vitamin D deficiency with an area under curve (AUC) = 0.83 and OR = 24.0. The VDSP was able to identify vitamin D deficiency and vitamin D insufficiency with less accuracy (AUC = 0.71 and AUC = 0.73, respectively). In conclusion, the 16-item VDSP is a short questionnaire that accurately identifies geriatric patients with severe vitamin D deficiency. This tool may guide the use of blood collection for determining geriatric patients' vitamin D status.

Asunto(s)

RESUMEN

BACKGROUND: Hepatic encephalopathy (HE) is a complex neuropsychiatric syndrome that occurs most often in a context of acute or chronic liver disease. Despite the seriousness of the pathology, only a few treatments have been developed for improving its management. Rifaximin-α is the first treatment that has been clinically developed for overt HE (OHE) episodes. Recent results of clinical studies demonstrated its significant improvement in the health-related quality of life. The objective of the current study was to estimate the long-term cost-effectiveness of rifaximin-α used in combination with lactulose compared with lactulose monotherapy in cirrhotic patients, who have experienced at least two prior OHE events. METHODS: A Markov model was used to estimate rifaximin-α cost-effectiveness, evaluating it from the perspective of all contributors as recommended by French health technology assessment guidelines. Costs were based on current French treatment practices. The transition between health states was based on the reanalysis of the rifaximin-α pivotal clinical trials RFHE3001 and RFHE3002. The main outcome of the model was cost per quality adjusted life year (QALY). RESULTS: The results indicate that rifaximin-α is a cost-effective treatment option with an incremental cost per QALY gained of €19,187 and €18,517 over two different time horizons (2 and 5 years). The robustness of the model was studied using probabilistic sensitivity analysis. CONCLUSION: For the societal willingness to pay threshold of €27,000 per QALY gained, rifaximin-α in combination with lactulose is a cost-effective and affordable treatment for patients who have experienced at least two prior overt HE episodes.

Asunto(s)

RESUMEN

OBJECTIVE: To compare performance criteria (i.e., sensitivity, specificity, positive predictive value, negative predictive value, area under receiver operating characteristic curve and accuracy) of linear and non-linear statistical models for fall risk in older community-dwellers. METHODS: Participants were recruited in two large population-based studies, "Prévention des Chutes, Réseau 4" (PCR4, n=1760, cross-sectional design, retrospective collection of falls) and "Prévention des Chutes Personnes Agées" (PCPA, n=1765, cohort design, prospective collection of falls). Six linear statistical models (i.e., logistic regression, discriminant analysis, Bayes network algorithm, decision tree, random forest, boosted trees), three non-linear statistical models corresponding to artificial neural networks (multilayer perceptron, genetic algorithm and neuroevolution of augmenting topologies [NEAT]) and the adaptive neuro fuzzy interference system (ANFIS) were used. Falls ≥1 characterizing fallers and falls ≥2 characterizing recurrent fallers were used as outcomes. Data of studies were analyzed separately and together. RESULTS: NEAT and ANFIS had better performance criteria compared to other models. The highest performance criteria were reported with NEAT when using PCR4 database and falls ≥1, and with both NEAT and ANFIS when pooling data together and using falls ≥2. However, sensitivity and specificity were unbalanced. Sensitivity was higher than specificity when identifying fallers, whereas the converse was found when predicting recurrent fallers. CONCLUSIONS: Our results showed that NEAT and ANFIS were non-linear statistical models with the best performance criteria for the prediction of falls but their sensitivity and specificity were unbalanced, underscoring that models should be used respectively for the screening of fallers and the diagnosis of recurrent fallers.

Asunto(s)

RESUMEN

OBJECTIVES: Hypovitaminosis D is highly prevalent among seniors. Although evidence is insufficient to recommend routine vitamin D screening in seniors, universal vitamin D supplementation is not desirable either. To rationalize vitamin D determination, our objective was to elaborate and test a clinical diagnostic tool for the identification of seniors with hypovitaminosis D without using a blood test. DESIGN: Derivation of a clinical diagnostic tool using artificial neural networks (multilayer perceptron; MLP) in randomized training subgroup of Prévention des Chutes, Réseau 4' cohort, and validation in randomized testing subgroup. SETTING: Health Examination Centers of health insurance, Lyon, France. PARTICIPANTS: A total of 1924 community-dwellers aged ≥ 65 years without vitamin D supplements, consecutively recruited between 2009 and 2012. MEASUREMENTS: Hypovitaminosis D defined as serum 25-hydroxyvitamin (25OHD) concentration ≤ 75 nmol/L, ≤ 50 nmol/L, or ≤ 25 nmol/L. A set of clinical variables (age, gender, living alone, individual deprivation, body mass index, undernutrition, polymorbidity, number of drugs used daily, psychoactive drugs, biphosphonates, strontium, calcium supplements, falls, fear of falling, vertebral fractures, Timed Up and Go, walking aids, lower-limb proprioception, handgrip strength, visual acuity, wearing glasses, cognitive disorders, sad mood) were recorded. Several MLPs, based on varying amounts of variables according to their relative importance, were tested consecutively. RESULTS: A total of 1729 participants (89.9%) had 25OHD ≤ 75 nmol/L, 1288 (66.9%) had 25OHD ≤ 50 nmol/L, and 525 (27.2%) had 25OHD ≤ 25 nmol/L. MLP using 16 clinical variables was able to diagnose hypovitaminosis D ≤ 75 nmol/L with accuracy = 96.3%, area under curve (AUC) = 0.938, and κ = 79.3 indicating almost perfect agreement. It was also able to diagnose hypovitaminosis D ≤ 50 nmol/L with accuracy = 81.5, AUC = 0.867, and κ = 57.8 (moderate agreement); and hypovitaminosis D ≤ 25 nmol/L with accuracy = 82.5, AUC = 0.385, and κ = 55.0 (moderate agreement). CONCLUSIONS: We elaborated an algorithm able to identify, from 16 clinical variables, seniors with hypovitaminosis D.

Asunto(s)

RESUMEN

BACKGROUND: Identification of the risk of recurrent falls is complex in older adults. The aim of this study was to examine the efficiency of 3 artificial neural networks (ANNs: multilayer perceptron [MLP], modified MLP, and neuroevolution of augmenting topologies [NEAT]) for the classification of recurrent fallers and nonrecurrent fallers using a set of clinical characteristics corresponding to risk factors of falls measured among community-dwelling older adults. METHODS: Based on a cross-sectional design, 3289 community-dwelling volunteers aged 65 and older were recruited. Age, gender, body mass index (BMI), number of drugs daily taken, use of psychoactive drugs, diphosphonate, calcium, vitamin D supplements and walking aid, fear of falling, distance vision score, Timed Up and Go (TUG) score, lower-limb proprioception, handgrip strength, depressive symptoms, cognitive disorders, and history of falls were recorded. Participants were separated into 2 groups based on the number of falls that occurred over the past year: 0 or 1 fall and 2 or more falls. In addition, total population was separated into training and testing subgroups for ANN analysis. RESULTS: Among 3289 participants, 18.9% (n = 622) were recurrent fallers. NEAT, using 15 clinical characteristics (ie, use of walking aid, fear of falling, use of calcium, depression, use of vitamin D supplements, female, cognitive disorders, BMI <21 kg/m(2), number of drugs daily taken >4, vision score <8, use of psychoactive drugs, lower-limb proprioception score ≤5, TUG score >9 seconds, handgrip strength score ≤29 (N), and age ≥75 years), showed the best efficiency for identification of recurrent fallers, sensitivity (80.42%), specificity (92.54%), positive predictive value (84.38), negative predictive value (90.34), accuracy (88.39), and Cohen κ (0.74), compared with MLP and modified MLP. CONCLUSIONS: NEAT, using a set of 15 clinical characteristics, was an efficient ANN for the identification of recurrent fallers in older community-dwellers.

Asunto(s)

RESUMEN

BACKGROUND: The aims of this study were 1) to confirm that combinations of brief geriatric assessment (BGA) items were significant risk factors for prolonged LHS among geriatric patients hospitalized in acute care medical units after their admission to the emergency department (ED); and 2) to determine whether these combinations of BGA items could be used as a prognostic tool of prolonged LHS. METHODS: Based on a prospective observational cohort design, 1254 inpatients (mean age ± standard deviation, 84.9±5.9 years; 59.3% female) recruited upon their admission to ED and discharged in acute care medical units of Angers University Hospital, France, were selected in this study. At baseline assessment, a BGA was performed and included the following 6 items: age ≥85years, male gender, polypharmacy (i.e., ≥5 drugs per day), use of home-help services, history of falls in previous 6 months and temporal disorientation (i.e., inability to give the month and/or year). The LHS in acute care medical units was prospectively calculated in number of days using the hospital registry. RESULTS: Area under receiver operating characteristic (ROC) curves of prolonged LHS of different combinations of BGA items ranged from 0.50 to 0.57. Cox regression models revealed that combinations defining a high risk of prolonged LHS, identified from ROC curves, were significant risk factors for prolonged LHS (hazard ratio >1.16 with P>0.010). Kaplan-Meier distributions of discharge showed that inpatients classified in high-risk group of prolonged LHS were discharged later than those in low-risk group (P<0.003). Prognostic value for prolonged LHS of all combinations was poor with sensitivity under 77%, a high variation of specificity (from 26.6 to 97.4) and a low likelihood ratio of positive test under 5.6. CONCLUSION: Combinations of 6-item BGA tool were significant risk factors for prolonged LHS but their prognostic value was poor in the studied sample of older inpatients.

Asunto(s)

RESUMEN

OBJECTIVE: To compare gait variability among older community-dwellers with and without fear of falling and history of falls, and 2) to examine the association between gait variability and fear of falling while taking into account the effect of potential confounders. METHODS: Based on a cross-sectional design, 1,023 French community-dwellers (mean age ± SD, 70.5 ± 5.0 years; 50.7% women) were included in this study. The primary endpoints were fear of falling, stride-to-stride variability of stride time and walking speed measured using GAITRite® system. Age, gender, history of falls, number of drugs daily taken per day, body mass index, lower-limb proprioception, visual acuity, use of psychoactive drugs and cognitive impairment were used as covariables in the statistical analysis. P-values less than 0.05 were considered as statistically significant. RESULTS: A total of 60.5% (n=619) participants were non-fallers without fear of falling, 19% (n=194) fallers without fear of falling, 9.9% (n=101) non-fallers with fear of falling, and 10.7% (n=109) fallers with fear of falling. Stride-to-stride variability of stride time was significantly higher in fallers with fear of falling compared to non-fallers without fear of falling. Full adjusted linear regression models showed that only lower walking speed value was associated to an increase in stride-to-stride variability of stride time and not fear of falling, falls or their combination. While using a walking speed ≥ 1.14 m/s (i.e., level of walking speed that did not influence stride-to-stride variability of stride time), age and combination of fear of falling with history of previous falls were significantly associated with an increased stride-to-stride variability of stride time. CONCLUSIONS: The findings show that the combination of fear of falling with falls increased stride-to-stride variability of stride time. However, the effect of this combination depended on the level of walking speed, increase in stride-to-stride variability of stride time at lower walking speed being related to a biomechanical effect overriding fear of falling-related effects.

Asunto(s)

RESUMEN

BACKGROUND: There is an increased interest of individuals in quantifying their own health and functional status. The aim of this study was to examine the concordance of answers to a self-administered questionnaire exploring health and functional status with information collected during a full clinical examination performed by a physician among cognitively healthy adults (CHI) and older patients with mild cognitive impairment (MCI) or mild-to-moderate Alzheimer disease (AD). METHODS: Based on cross-sectional design, a total of 60 older adults (20 CHI, 20 patients with MCI, and 20 patients with mild-to-moderate AD) were recruited in the memory clinic of Angers, France. All participants completed a self-administered questionnaire in paper format composed of 33 items exploring age, gender, nutrition, place of living, social resources, drugs daily taken, memory complaint, mood and general feeling, fatigue, activities of daily living, physical activity and history of falls. Participants then underwent a full clinical examination by a physician exploring the same domains. RESULTS: High concordance between the self-administered questionnaire and physician's clinical examination was showed. The few divergences were related to cognitive status, answers of AD and MCI patients to the self-administered questionnaire being less reliable than those of CHI. CONCLUSION: Older adults are able to evaluate their own health and functional status, regardless of their cognitive status. This result needs to be confirmed and opens new perspectives for the quantified self-trend and could be helpful in daily clinical practice of primary care.

Asunto(s)

Asunto(s)

Asunto(s)

Asunto(s)

Asunto(s)