Automatic speech analysis to early detect functional cognitive decline in elderly population

This study aimed at evaluating whether people with a normal cognitive function can be discriminated from subjects with a mild impairment of cognitive function based on a set of acoustic features derived from spontaneous speech. Voice recordings from 90 Italian subjects (age >65 years; group 1: 47 subjects with MMSE>26; group 2: 43 subjects with 20≤ MMSE ≤26) were collected. Voice samples were processed using a MATLAB-based custom software to derive a broad set of known acoustic features. Linear mixed model analyses were performed to select the features able to significantly distinguish between groups. The selected features (% of unvoiced segments, duration of unvoiced segments, % of voice breaks, speech rate, and duration of syllables), alone or in addition to age and years of education, were used to build a learning-based classifier. The leave-one-out cross validation was used for testing and the classifier accuracy was computed. When the voice features were used alone, an overall classification accuracy of 0.73 was achieved. When age and years of education were additionally used, the overall accuracy increased up to 0.80. These performances were lower than the accuracy of 0.86 found in a recent study. However, in that study the classification was based on several tasks, including more cognitive demanding tasks. Our results are encouraging because acoustic features, derived for the first time only from an ecologic continuous speech task, were able to discriminate people with a normal cognitive function from people with a mild cognitive decline. This study poses the basis for the development of a mobile application performing automatic voice analysis on-the-fly during phone calls, which might potentially support the detection of early signs of functional cognitive decline.

Drug-Induced Hyponatremia: NSAIDs, a Neglected Cause that Should Be Considered

Hyponatremia is the most common electrolyte disorder. It may have serious consequences in asyntomatic patients with a mild disease. Therefore, an evaluation of unsual causes is of paramount importance. Polypharmacy is highly prevalent in older people and many drugs can cause hyponatremia as a collateral effect. In our retrospective analysis of geriatric medical records dated 2015 we found that 39 out of the 273 hospitalized patients had hyponatremia. Polipharmacy was highly prevalent, especially in hyponatremic patients. Non-steroidal anti-inflammatory drugs, which are seldom considered as a cause of hyponatremia were instead found to be associated to an increased risk of the disorder (adjustedOR 3.61, 95% CI 1 - 12.99, p = 0.05). In-hospital mortality was higher in patients with moderate or severe hyponatremia at hospital admission. Our study underlines the importance of considering rare but potentially reversible causes of hyponatremia, which can lead to serious consequences.

Behaviour disorder caused by Cushing's syndrome in an older person

An 81-year-old woman was hospitalised for behavioural disorders that had been progressively emerging over a period of few weeks. The symptoms appeared to worsen over time. A diagnosis of vascular dementia, complicated by psychosis, was initially hypothesised. The inefficacy of the antipsychotic/benzodiazepine medications used, along with the presence of hypertension, hypokalaemia and metabolic alkalosis (resistant to pharmacological attempts of correction), as well as the hirsutism and the development of several infections, led us to consider Cushing's syndrome. Endocrinological analysis suggested ectopic adrenocorticotropic hormone (ACTH) secretion. Although endogenous Cushing's syndrome is rare in older people, it should always be considered among the differential diagnosis of behavioural disorders.

Nutritional Status in Frail Cirrhotic Patients Undergoing Liver Transplantation

The liver is the largest and most important metabolic organ, playing a pivotal role in the integration of biochemical pathways of carbohydrates, fats, proteins, and vitamins (1). End-stage liver disease (ESLD) has an important negative effect on nutritional status (2) and malnutrition is a common problem in patients waiting for liver transplantation (LT). The mean weight loss during ESLD is about 9 Kg and this contributes to further morbidities and mortality (3).

Decreased adrenergic tone in acromegaly: evidence from direct recording of muscle sympathetic nerve activity

OBJECTIVE

Sympathovagal imbalance has been shown in acromegaly by indirect measurements of adrenergic tone. Data regarding direct measurement of sympathetic activity are lacking as yet. Aim of this study was to assess the adrenergic tone through direct recording of muscle sympathetic nerve activity (MSNA) in acromegalic patients.

DESIGN

Fifteen patients (age 26-66 years, eight women) with newly diagnosed active acromegaly without hyperprolactinaemia, pituitary hormone deficiencies, obstructive sleep apnoea and cardiac hypertrophy, and 15 healthy subjects matched for age, sex and body mass index were recruited. After evaluating anthropometric and echocardiographic parameters, anterior pituitary function, glucose and lipid metabolism, and measuring plasma leptin, direct recording of sympathetic outflow via the microneurographic technique was performed.

RESULTS

For similar anthropometric and metabolic parameters in patients and controls, HOMA index was significantly increased in the former (4·2 ± 2·39 vs 1·6 ± 0·19, P < 0·001). Surprisingly, this finding of insulin resistance was accompanied by a marked sympathetic inhibition (MSNA 18·3 ± 8·10 vs 37·3 ± 6·48 bursts/min, P < 0·0001, respectively in patients and controls). A reduction in plasma leptin (1·6 ± 1·04 vs 6·5 ± 2·01 μg/l, P < 0·0001) was also recorded in the patients. MSNA was positively correlated with leptin (P < 0·0001).

CONCLUSIONS

Newly diagnosed acromegalic patients without cardiac hypertrophy display a decreased sympathetic outflow in spite of insulin resistance. This finding might be related to hypoleptinaemia.