CNN-Based Identification of Parkinson's Disease from Continuous Speech in Noisy Environments.

Parkinson's disease is a progressive neurodegenerative disorder caused by dopaminergic neuron degeneration. Parkinsonian speech impairment is one of the earliest presentations of the disease and, along with tremor, is suitable for pre-diagnosis. It is defined by hypokinetic dysarthria and accounts for respiratory, phonatory, articulatory, and prosodic manifestations. The topic of this article targets artificial-intelligence-based identification of Parkinson's disease from continuous speech recorded in a noisy environment. The novelty of this work is twofold. First, the proposed assessment workflow performed speech analysis on samples of continuous speech. Second, we analyzed and quantified Wiener filter applicability for speech denoising in the context of Parkinsonian speech identification. We argue that the Parkinsonian features of loudness, intonation, phonation, prosody, and articulation are contained in the speech, speech energy, and Mel spectrograms. Thus, the proposed workflow follows a feature-based speech assessment to determine the feature variation ranges, followed by speech classification using convolutional neural networks. We report the best classification accuracies of 96% on speech energy, 93% on speech, and 92% on Mel spectrograms. We conclude that the Wiener filter improves both feature-based analysis and convolutional-neural-network-based classification performances.

Comparison of Artificial Intelligence-Based Applications for Mandible Segmentation: From Established Platforms to In-House-Developed Software.

Medical image segmentation, whether semi-automatically or manually, is labor-intensive, subjective, and needs specialized personnel. The fully automated segmentation process recently gained importance due to its better design and understanding of CNNs. Considering this, we decided to develop our in-house segmentation software and compare it to the systems of established companies, an inexperienced user, and an expert as ground truth. The companies included in the study have a cloud-based option that performs accurately in clinical routine (dice similarity coefficient of 0.912 to 0.949) with an average segmentation time ranging from 3'54″ to 85'54″. Our in-house model achieved an accuracy of 94.24% compared to the best-performing software and had the shortest mean segmentation time of 2'03″. During the study, developing in-house segmentation software gave us a glimpse into the strenuous work that companies face when offering clinically relevant solutions. All the problems encountered were discussed with the companies and solved, so both parties benefited from this experience. In doing so, we demonstrated that fully automated segmentation needs further research and collaboration between academics and the private sector to achieve full acceptance in clinical routines.

Point-of-Care Virtual Surgical Planning and 3D Printing in Oral and Cranio-Maxillofacial Surgery: A Narrative Review.

This paper provides an overview on the use of virtual surgical planning (VSP) and point-of-care 3D printing (POC 3DP) in oral and cranio-maxillofacial (CMF) surgery based on a literature review. The authors searched PubMed, Web of Science, and Embase to find papers published between January 2015 and February 2022 in English, which describe human applications of POC 3DP in CMF surgery, resulting in 63 articles being included. The main review findings were as follows: most used clinical applications were anatomical models and cutting guides; production took place in-house or as "in-house-outsourced" workflows; the surgeon alone was involved in POC 3DP in 36 papers; the use of free versus paid planning software was balanced (50.72% vs. 49.27%); average planning time was 4.44 h; overall operating time decreased and outcomes were favorable, though evidence-based studies were limited; and finally, the heterogenous cost reports made a comprehensive financial analysis difficult. Overall, the development of in-house 3D printed devices supports CMF surgery, and encouraging results indicate that the technology has matured considerably.

Proof of Concept in Artificial-Intelligence-Based Wearable Gait Monitoring for Parkinson's Disease Management Optimization.

Parkinson's disease (PD) is the second most common progressive neurodegenerative disorder, affecting 6.2 million patients and causing disability and decreased quality of life. The research is oriented nowadays toward artificial intelligence (AI)-based wearables for early diagnosis and long-term PD monitoring. Our primary objective is the monitoring and assessment of gait in PD patients. We propose a wearable physiograph for qualitative and quantitative gait assessment, which performs bilateral tracking of the foot biomechanics and unilateral tracking of arm balance. Gait patterns are assessed by means of correlation. The surface plot of a correlation coefficient matrix, generated from the recorded signals, is classified using convolutional neural networks into physiological or PD-specific gait. The novelty is given by the proposed AI-based decisional support procedure for gait assessment. A proof of concept of the proposed physiograph is validated in a clinical environment on five patients and five healthy controls, proving to be a feasible solution for ubiquitous gait monitoring and assessment in PD. PD management demonstrates the complexity of the human body. A platform empowering multidisciplinary, AI-evidence-based decision support assessments for optimal dosing between drug and non-drug therapy could lay the foundation for affordable precision medicine.

Analgesic efficacy of naproxen sodium versus hydrocodone/acetaminophen in acute postsurgical dental pain: a randomized, double-blind, placebo-controlled trial.

OBJECTIVES: Opioid/acetaminophen combinations may be overly prescribed in many post-surgical situations where a non-steroidal anti-inflammatory drug with equal or greater efficacy, fewer central nervous system side effects, and no risk for opioid abuse could be substituted. We compared a single, non-prescription dose of naproxen sodium 440 mg (NapS) against hydrocodone plus acetaminophen 10/650 mg (HYD+APAP) in post-impaction surgery pain. METHODS: Single-center, randomized, double-blind, placebo-controlled study in moderate-severe pain after surgical removal of impacted third molars (ClinicalTrials.gov: NCT04307940). Patients (n = 212) received NapS, HYD+APAP, or placebo and were assessed over 12 hours. Primary endpoint: summed pain intensity difference from 0 to 12 hours (SPID0-12). Secondary endpoints: pain intensity, pain relief, time to rescue medication, duration of pain at least half gone. Others: onset of pain relief, global assessment of treatment, adverse events. RESULTS: All 221 randomized patients formed the safety population and were included in the intention-to-treat sensitivity analysis. Nine patients discontinued treatment or had protocol violations, and 212 patients were included in the per-protocol, primary efficacy population. Both active treatments were significantly more effective than placebo. NapS was significantly more effective than HYD+APAP regarding SPID0-12 (p = 0.01; primary endpoint), total pain relief (0-6 and 0-12 hours; p < 0.05), time to rescue medication (p < 0.001), and duration of pain at least half gone (p < 0.001). HYD+APAP was not statistically superior to NapS for any endpoint. More adverse events were reported with HYD+APAP (n = 63) than NapS (n = 2) and placebo (n = 20), including nausea, vomiting, and dizziness. CONCLUSION: In moderate-to-severe postsurgical dental pain, a single dose of NapS was at least as effective as HYD+APAP in the early hours, significantly more effective at reducing pain intensity and providing greater pain relief over 12 hours, and was better tolerated. When not contraindicated, NapS should be considered a preferred alternative to opioid combinations for acute pain. (ClinicalTrials.gov, Identifier: NCT04307940; https://clinicaltrials.gov/ct2/show/NCT04307940).

Analgesic efficacy and safety of non-prescription doses of naproxen sodium in the management of moderate osteoarthritis of the knee or hip.

OBJECTIVES: Current osteoarthritis therapies aim to alleviate pain and maintain joint function. Non-prescription oral non-steroidal anti-inflammatory drugs are frequently used alone for pain relief in osteoarthritis. This post-hoc pooled analysis evaluated the analgesic efficacy and safety of two non-prescription doses of naproxen sodium for short-term use in patients with osteoarthritis of the knee or hip. A separate sub-group analysis of older patients who were administered a lower dose of naproxen sodium was performed. METHODS: In four multi-center, multi-dose, randomized, parallel, double-blind, placebo-controlled studies, oral naproxen sodium (age-based dosing regimen: <65 years, 660 mg/day; ≥65 years, 440 mg/day) or placebo was administered over 7 days. Data at baseline and after 7 days in 818 patients who received naproxen sodium or placebo (n = 409 in each group) was pooled and analyzed. Five-point rating scales were used to assess knee or hip joint pain, stiffness after rest, day and night pain, and patient and investigator assessment of treatment, while function was evaluated using a timed 50-foot walk test. RESULTS: Compared with placebo, there were significant improvements in pain and physical function with naproxen sodium (p < .05), and treatment was rated "good" to "excellent" significantly more often (p < .001) by investigators and patients. Efficacy results were similar among younger and older patients. There were no significant differences in adverse events between groups, regardless of age. CONCLUSIONS: For the acute management of underlying pain in patients with moderate osteoarthritis of the hip or knee, non-prescription naproxen sodium is effective and well tolerated in patients of all ages.

Efficacy of single-dose, extended-release naproxen sodium 660 mg in postsurgical dental pain: two double-blind, randomized, placebo-controlled trials.

OBJECTIVE: To evaluate the efficacy of a novel formulation of extended-release/immediate-release (ER) naproxen sodium over 24 h in a dental pain model. RESEARCH DESIGN AND METHODS: Two randomized, double-blind, placebo-controlled trials in moderate to severe pain after extraction of one or two impacted third molars (at least one partial mandibular bony impaction). Treatment comprised oral ER naproxen sodium 660 mg (single dose), placebo (both studies) or immediate-release (IR) naproxen sodium 220 mg tid (study 2). MAIN OUTCOME MEASURES: Primary efficacy endpoint: 24-h summed pain intensity difference (SPID). Secondary variables included total pain relief (TOTPAR), use of rescue medication. All treatment-emergent adverse events were recorded. CLINICAL TRIAL REGISTRATION: NCT00720057 (study 1), NCT01389284 (study 2). RESULTS: Primary efficacy analyses: pain intensity was significantly lower over 24 h with ER naproxen sodium vs. placebo (p < 0.001), with significant relief from 15 min (study 2). In study 2, ER naproxen sodium was non-inferior to IR naproxen sodium, reducing pain intensity to a comparable extent over 24 h. TOTPAR was significantly greater with ER and IR naproxen sodium vs. placebo at all time points, with generally comparable differences between active treatments. Significantly more placebo patients required rescue medication vs. ER and IR naproxen sodium from 2-24 h post-dose. Once daily ER naproxen sodium was generally safe and well tolerated, with a similar safety profile to IR naproxen sodium tid. LIMITATIONS: The studies were single dose, with limited ability to assess efficacy or safety of multiple doses over time. As the imputed pain score meant that estimated treatment differences may have been biased in favor of ER naproxen sodium, a post hoc analysis evaluated the robustness of the results for pain relief. CONCLUSIONS: A single dose of ER naproxen sodium 660 mg significantly reduced moderate to severe dental pain vs. placebo and was comparable to IR naproxen sodium 220 mg tid. Significant pain relief was experienced from 15 min and sustained over 24 h, resulting in a reduced need for rescue medication. ER naproxen sodium 660 mg once daily is a convenient and effective therapy providing 24 h relief of pain.

Efficacy and safety of epoetin alfa in critically ill patients.

BACKGROUND: Anemia, which is common in the critically ill, is often treated with red-cell transfusions, which are associated with poor clinical outcomes. We hypothesized that therapy with recombinant human erythropoietin (epoetin alfa) might reduce the need for red-cell transfusions. METHODS: In this prospective, randomized, placebo-controlled trial, we enrolled 1460 medical, surgical, or trauma patients between 48 and 96 hours after admission to the intensive care unit. Epoetin alfa (40,000 U) or placebo was administered weekly, for a maximum of 3 weeks; patients were followed for 140 days. The primary end point was the percentage of patients who received a red-cell transfusion. Secondary end points were the number of red-cell units transfused, mortality, and the change in hemoglobin concentration from baseline. RESULTS: As compared with the use of placebo, epoetin alfa therapy did not result in a decrease in either the number of patients who received a red-cell transfusion (relative risk for the epoetin alfa group vs. the placebo group, 0.95; 95% confidence interval [CI], 0.85 to 1.06) or the mean (+/-SD) number of red-cell units transfused (4.5+/-4.6 units in the epoetin alfa group and 4.3+/-4.8 units in the placebo group, P=0.42). However, the hemoglobin concentration at day 29 increased more in the epoetin alfa group than in the placebo group (1.6+/-2.0 g per deciliter vs. 1.2+/-1.8 g per deciliter, P<0.001). Mortality tended to be lower at day 29 among patients receiving epoetin alfa (adjusted hazard ratio, 0.79; 95% CI, 0.56 to 1.10); this effect was also seen in prespecified analyses in those with a diagnosis of trauma (adjusted hazard ratio, 0.37; 95% CI, 0.19 to 0.72). A similar pattern was seen at day 140 (adjusted hazard ratio, 0.86; 95% CI, 0.65 to 1.13), particularly in those with trauma (adjusted hazard ratio, 0.40; 95% CI, 0.23 to 0.69). As compared with placebo, epoetin alfa was associated with a significant increase in the incidence of thrombotic events (hazard ratio, 1.41; 95% CI, 1.06 to 1.86). CONCLUSIONS: The use of epoetin alfa does not reduce the incidence of red-cell transfusion among critically ill patients, but it may reduce mortality in patients with trauma. Treatment with epoetin alfa is associated with an increase in the incidence of thrombotic events. (ClinicalTrials.gov number, NCT00091910 [ClinicalTrials.gov].).