Development and validation of a machine learning-based vocal predictive model for major depressive disorder.

BACKGROUND: Variations in speech intonation are known to be associated with changes in mental state over time. Behavioral vocal analysis is an algorithmic method of determining individuals' behavioral and emotional characteristics from their vocal patterns. It can provide biomarkers for use in psychiatric assessment and monitoring, especially when remote assessment is needed, such as in the COVID-19 pandemic. The objective of this study was to design and validate an effective prototype of automatic speech analysis based on algorithms for classifying the speech features related to MDD using a remote assessment system combining a mobile app for speech recording and central cloud processing for the prosodic vocal patterns. METHODS: Machine learning compared the vocal patterns of 40 patients diagnosed with MDD to the patterns of 104 non-clinical participants. The vocal patterns of 40 patients in the acute phase were also compared to 14 of these patients in the remission phase of MDD. RESULTS: A vocal depression predictive model was successfully generated. The vocal depression scores of MDD patients were significantly higher than the scores of the non-patient participants (p < 0.0001). The vocal depression scores of the MDD patients in the acute phase were significantly higher than in remission (p < 0.02). LIMITATIONS: The main limitation of this study is its relatively small sample size, since machine learning validity improves with big data. CONCLUSIONS: The computerized analysis of prosodic changes may be used to generate biomarkers for the early detection of MDD, remote monitoring, and the evaluation of responses to treatment.

Visual outcome of mega-dose intravenous corticosteroid treatment in non-arteritic anterior ischemic optic neuropathy - retrospective analysis.

BACKGROUND: To date, non arteritic anterior ischemic optic neuropathy (NAION) is still incurable. We wish to evaluate the effect of intravenous (IV) corticosteroids on the visual outcome of NAION patients. METHODS: Visual parameters were retrospectively compared between NAION patients treated with IV corticosteroids and untreated NAION patients (control). Visual acuity (VA) and Humphrey automated static perimetry visual field (VF) defects of the affected eye were compared between groups at baseline, 1, 3, 6 months, and end of follow-up visits. The VF analysis consisted of number of quadrant involvements and mean deviation (MD). RESULTS: Each group comprised 23 patients (24 eyes). Mean initial VA was similar in the control and treatment groups (p = 0.8). VA at end of follow-up did not improve in either groups (p = 0.8 treated group, p = 0.1 control group). No improvement and no difference in VF defects were found by either quadrant analysis (p = 0.1 treated group, p = 0.5 control group) or MD analysis (p = 0.2, treated group, p = 0.9 control group). VA and VF parameters tended to be worse in the treated group, although without statistical significance. CONCLUSIONS: Our results suggest that IV corticosteroids may not improve the visual outcome of NAION patients. Since intravenous corticosteroids could potentially cause serious adverse effects, this treatment for NAION is questionable.

Risk assessment of simple phacoemulsification in patients on combined anticoagulant and antiplatelet therapy.

PURPOSE: To assess the safety of phacoemulsification cataract extraction in patients on combined anticoagulant and antiplatelet treatment. SETTING: Goldschleger Eye Institute, Sheba Medical Center, Tel Hashomer, Israel. DESIGN: Prospective interventional case series. METHODS: Consecutive patients with simple cataract on combined anticoagulant (warfarin) and antiplatelet (aspirin or clopidogrel) treatment who were unable to discontinue the treatment because of a high risk for thromboembolic events were included. Patients had cataract extraction under topical anesthesia with a clear corneal incision (CCI), phacoemulsification, and implantation of a foldable posterior chamber intraocular lens. Prothrombin time-international normalized ratio and platelet functions were evaluated immediately before surgery. Patients were also examined 1 day and 7 days postoperatively. Intraoperative and postoperative ocular bleeding and other related complications were assessed. RESULTS: Forty patients (51 eyes) with a mean age of 72 years (range 51 to 90 years) had phacoemulsification. Hemorrhagic complications were not observed at surgery or during the 1-week follow-up. Surgical complications included 1 rupture of the capsulorhexis and 1 implantation of a capsular tension ring due to partial zonulysis. No patient had a thromboembolic event. CONCLUSIONS: In patients with uncomplicated cataract at high risk for thromboembolic events, phacoemulsification cataract surgery using a CCI under topical needle-free anesthesia was safely performed without discontinuing systemic anticoagulant and antiplatelet treatment.

Phacoemulsification of cataract in patients receiving Coumadin therapy: ocular and hematologic risk assessment.

PURPOSE: To assess the risks of intra- and postoperative bleeding tendency associated with uncomplicated cataract surgery by phacoemulsification in patients receiving Coumadin treatment. DESIGN: Prospective, nonrandomized, interventional, consecutive case series. METHODS: Sixty-three consecutive patients underwent cataract extraction with lens implantation in 75 eyes. All patients were receiving Coumadin therapy at the time of surgery, and nine patients (14.3%) were also taking antiaggregants. The operations were performed by phacoemulsification technique under topical anesthesia. All patients underwent a hemostatic work-up before intervention. Structured questionnaires were completed by the surgeon immediately after the operation. In 18 (24%) eyes, the surgery was videotaped, and the tapes were reviewed subsequently for any bleedings by an independent observer. RESULTS: Twelve patients (19%) underwent surgery in both eyes, not simultaneously. The mean prothrombin time international normalized ratio (INR) was 2.03 at the time of the surgery. No significant intraoperative bleeding occurred. Four (6.3%) patients had minor postoperative ocular bleeding. A microscopic hyphema and a dot retinal hemorrhage were each seen in one eye on the first postoperative day, and small iris hemorrhages were identified in two additional eyes at the one-week visit. All bleedings disappeared within one week without affecting the visual acuity. The mean INR of the four patients with minor bleedings was 2.1. CONCLUSIONS: Cataract surgery by phacoemulsification in uncomplicated eyes can be performed safely in patients receiving Coumadin treatment. However, a large clinical trial is required to assess the safety of continuous Coumadin treatment associated with phacoemulsification in eyes with complicated cataract.

Herpes simplex keratitis after cataract surgery.

PURPOSE: Herpetic keratitis is a rare complication of cataract surgery. We describe 3 cases of herpes simplex keratitis after cataract surgery in eyes with no clinical history of this disease. METHODS: Three patients underwent uneventful phacoemulsification of cataract with intraocular lens implantation. All were treated postoperatively with topical steroids. On subsequent development of corneal dendritic epithelial lesions in the operated eyes, the corticosteroids were replaced by treatment with topical acyclovir. RESULTS: The first postoperative day was uneventful. Corneal dendritic epithelial lesions were observed 1-5 weeks postoperatively and healed without sequelae after topical acyclovir treatment. CONCLUSIONS: In view of the surgical trauma along with the topical corticosteroid treatment commonly prescribed after cataract surgery, physicians should be aware of the possible development of herpetic epithelial keratitis even in patients with no clinical history of this disease.