Speech-based markers for posttraumatic stress disorder in US veterans

BACKGROUND

The diagnosis of posttraumatic stress disorder (PTSD) is usually based on clinical interviews or self-report measures. Both approaches are subject to under- and over-reporting of symptoms. An objective test is lacking. We have developed a classifier of PTSD based on objective speech-marker features that discriminate PTSD cases from controls.

METHODS

Speech samples were obtained from warzone-exposed veterans, 52 cases with PTSD and 77 controls, assessed with the Clinician-Administered PTSD Scale. Individuals with major depressive disorder (MDD) were excluded. Audio recordings of clinical interviews were used to obtain 40,526 speech features which were input to a random forest (RF) algorithm.

RESULTS

The selected RF used 18 speech features and the receiver operating characteristic curve had an area under the curve (AUC) of 0.954. At a probability of PTSD cut point of 0.423, Youden's index was 0.787, and overall correct classification rate was 89.1%. The probability of PTSD was higher for markers that indicated slower, more monotonous speech, less change in tonality, and less activation. Depression symptoms, alcohol use disorder, and TBI did not meet statistical tests to be considered confounders.

CONCLUSIONS

This study demonstrates that a speech-based algorithm can objectively differentiate PTSD cases from controls. The RF classifier had a high AUC. Further validation in an independent sample and appraisal of the classifier to identify those with MDD only compared with those with PTSD comorbid with MDD is required.

Learning diagnostic models using speech and language measures

We describe results that show the effectiveness of machine learning in the automatic diagnosis of certain neurodegenerative diseases, several of which alter speech and language production. We analyzed audio from 9 control subjects and 30 patients diagnosed with one of three subtypes of Frontotemporal Lobar Degeneration. From this data, we extracted features of the audio signal and the words the patient used, which were obtained using our automated transcription technologies. We then automatically learned models that predict the diagnosis of the patient using these features. Our results show that learned models over these features predict diagnosis with accuracy significantly better than random. Future studies using higher quality recordings will likely improve these results.

Short communication: renal tubular vacuolation in animals treated with polyethylene-glycol-conjugated proteins

During toxicologic evaluation of a dimeric PEG-linked protein, tumor necrosis factor binding protein (TNF-bp), vacuolation of renal cortical tubular epithelium was seen in male and female Sprague-Dawley rats (200-300 g) given i.v. doses of 40, 20, or 10 mg/kg every other day for 3 months. Tubular lesions in rats treated with 20 or 40 mg/kg for 3 months were only partially reversible after a 2-month recovery period. Despite the presence of marked vacuolation, there were no changes in BUN, creatinine, urinalysis parameters, urinary NAG, urinary B2-microglobulin, or fractional sodium excretion. Single i.v. doses > or = 20 mg/kg TNF-bp caused similar but milder changes. However, equivalent doses of PEG alone or the non-PEG-linked TNF-bp did not cause light microscopic evidence of vacuolation. Treatment of rats with another PEG-linked protein of similar molecular weight resulted in similar changes. Immunostaining for TNF-bp revealed positivity in the apical cytoplasm of renal tubular epithelium within 1 h of i.v. dosing. Immunostaining of kidneys from chronically dosed rats indicated that protein was present in some vacuoles as long as dosing continued; however, kidneys from animals on a reversibility study had vacuoles but no immunostaining for TNF-bp. These results, along with a study that showed more severe lesions with PEG-linked proteins of lower molecular weight and minimal if any lesions with PEG-linked proteins > 70 kDa, suggest that TNF-bp is filtered through the glomerulus and that the protein with attached PEG is reabsorbed by the proximal tubules. Vacuolation may be a result of fluid distension of lysosomes due to the hygroscopic nature of PEG. These studies demonstrated that PEG-linked proteins have the capacity to induce renal tubular vacuolation at high doses. However, the change was not associated with alteration of clinical pathology or functional markers.