Unveiling the sound of the cognitive status: Machine Learning-based speech analysis in the Alzheimer's disease spectrum.

BACKGROUND: Advancement in screening tools accessible to the general population for the early detection of Alzheimer's disease (AD) and prediction of its progression is essential for achieving timely therapeutic interventions and conducting decentralized clinical trials. This study delves into the application of Machine Learning (ML) techniques by leveraging paralinguistic features extracted directly from a brief spontaneous speech (SS) protocol. We aimed to explore the capability of ML techniques to discriminate between different degrees of cognitive impairment based on SS. Furthermore, for the first time, this study investigates the relationship between paralinguistic features from SS and cognitive function within the AD spectrum. METHODS: Physical-acoustic features were extracted from voice recordings of patients evaluated in a memory unit who underwent a SS protocol. We implemented several ML models evaluated via cross-validation to identify individuals without cognitive impairment (subjective cognitive decline, SCD), with mild cognitive impairment (MCI), and with dementia due to AD (ADD). In addition, we established models capable of predicting cognitive domain performance based on a comprehensive neuropsychological battery from Fundació Ace (NBACE) using SS-derived information. RESULTS: The results of this study showed that, based on a paralinguistic analysis of sound, it is possible to identify individuals with ADD (F1 = 0.92) and MCI (F1 = 0.84). Furthermore, our models, based on physical acoustic information, exhibited correlations greater than 0.5 for predicting the cognitive domains of attention, memory, executive functions, language, and visuospatial ability. CONCLUSIONS: In this study, we show the potential of a brief and cost-effective SS protocol in distinguishing between different degrees of cognitive impairment and forecasting performance in cognitive domains commonly affected within the AD spectrum. Our results demonstrate a high correspondence with protocols traditionally used to assess cognitive function. Overall, it opens up novel prospects for developing screening tools and remote disease monitoring.

Influence of smoking on patient-reported outcome measures (PROMs) in patients undergoing surgery for adult spinal deformity: a propensity score-matched analysis.

PURPOSE: The purpose of this study was to determine the isolated influence of smoking in patient-reported outcome measures (PROMs) for adult spinal deformity (ASD) surgery excluding known tobacco-related complications. METHODS: Retrospective analysis of a prospective multicenter ASD database. Patients operated on ASD with 2 year post-operative follow-up were included. Former smokers (non-active smokers) and patients developing mechanical or infectious complications were excluded. Changes of PROMs over time were analyzed using mixed models for repeated measures (MMRM). Propensity score matching (PSM) (1:1 ratio, caliper 0.10) was performed without replacement using optimum algorithm, tolerance ≤ 0.001, and estimated with 95% confidence interval (CI). PROMS in both groups were compared by paired t test or Wilcoxon signed-rank test. RESULTS: 692 out of 1246 surgical patients met our inclusion criteria. 153 smokers were matched with 153 non-smokers according to age, BMI, number of fused levels, and global tilt. After PSM both groups were homogeneous regarding baseline parameters, surgical data, and complications (mechanical complications and infection excluded). Smokers had worse baseline results for SRS-total, SRS-pain COMI-back, and ODI; smokers also showed worse 2-year outcomes for SRS-total, SRS-function, SRS-pain, SRS-self-image, and ODI. However, no differences between the two groups were found in the improvement from baseline to 2-year follow-up or in the timing of this improvement (MMRM). The proportion of patients reaching the minimal clinically important difference (MCID) after surgery was similar in the two groups, but the proportion of patients reaching patient acceptable symptom state (PASS) was significantly lower in smokers for SRS-Subtotal, SRS-function, and SRS-image. CONCLUSION: Even in the absence of smoking-related complications, smokers had worse PROMs at baseline and 2 years after surgery with less patients achieving PASS, but similar degrees on improvement compared to non-smokers. The proportion achieving MCID was also similar between the two cohorts.

A 5-year follow-up of the effect of corrective surgery in young adults with idiopathic scoliosis.

PURPOSE: The purpose of this study was to determine mid-long-term outcomes (5 years) following surgery for young adult idiopathic scoliosis (YAdIS). METHODS: This is a retrospective review of a prospective, multicenter adult deformity database including patients operated on idiopathic scoliosis by a single posterior approach, age at surgery between 19 and 29 (considered young adults), and 5-year follow-up. Demographic, radiographic and PROMS were analyzed preoperatively, at 2 years and at final follow-up. RESULTS: Forty-two patients were included. Mean preoperative major curve angle was 59.65 ± 18.94. Main coronal curve initial correction was 56.38%, with 6% loss at 5 years. From baseline to 5 years after surgery, there was improvement in all PROMs (P < 0.004)-especially self-image-, except NRS-leg pain. This improvement was present at 6 months for all PROMs except for functional outcomes (SRS-Function and ODI) in which the improvement took place between 6 months and 2 years. In the 2- to 5-year follow-up period, no significant changes were seen in any PROMs. The percentage of patients reaching MCID from baseline at 5 years was: 75% for SRS-image, 45% for SRS-pain, 47.5% for SRS-function, 51.3% for SRS-mental, 42.5% for SRS-total and 15.4% for ODI. Patients reaching PASS at 5 years were: 88.1% for SRS-image, 81% for SRS-pain, 92.9% for SRS-function, 57.1% for SRS-mental, 88.1% for SRS-total, 92.7% for ODI and 69% for NRS pain. 11 minor and 4 major complications were identified. CONCLUSION: YAdIS surgery resulted in an early and significant improvement in PROMs, especially for self-image, significantly reaching MCID and PASS thresholds. These results were maintained during long-term (5-year) follow-up.