Identifying predictive factors for neuropathic pain after breast cancer surgery using machine learning.

INTRODUCTION: Neuropathic pain (NP) remains a major debilitating condition affecting more than 26% of breast cancer survivors worldwide. NP is diagnosed using a validated 10-items Douleur Neuropathique - 4 screening questionnaire which is administered 3 months after surgery and requires patient-doctor interaction. To develop an effective prognosis model admissible soon after surgery, without the need for patient-doctor interaction, we sought to [1] identify specific pain characteristics that can help determine which patients may be susceptible to NP after BC surgery, and 2) assess the utility of machine learning models developed in objective [1] as a knowledge discovery tool for downstream analysis. METHODS: The dataset is from a prospective cohort study of female patients scheduled to undergo breast cancer surgery for the first time at the Jewish General Hospital, Montreal, Canada between November 2014 and March 2019. NP was assessed at 3 months after surgery using Douleur Neuropathique - 4 interview scores (in short, DN4-interview; range: 0-7). For the primary analysis, we constructed six ML algorithms (least square, ridge, elastic net, random forest, gradient boosting, and neural net) to identify the most relevant predictors for DN4-interview score; and compared model performance based on root mean square error (RMSE). For the secondary analysis, we built a logistic classification model for neuropathic pain (DN4-interview score ≥ 3 versus DN4-interview score < 3) using the relevant-consensus-predictors from the primary analysis. RESULTS: Anxiety, type of surgery, preoperative baseline pain and acute pain on movement were identified as the most relevant predictors for DN4 - interview score. The least square regression model (RMSE = 1.43) is comparable in performance with random forest (RMSE = 1.39) and neural network model (RMSE = 1.50). The Gradient boosting model (RMSE = 1.16) outperformed the models compared including the penalized regression models (ridge regressions, RMSE = 1.28; and elastic net, RMSE = 1.31). In the secondary analysis, the preferred logistic regression classier for NP had an area under the curve (AUC) of 0.68 (95% CI = 0.57 to 0.79). Anxiety was significantly associated with the likelihood of NP (odds ratio = 2.18; 95% CI = 1.05-4.49). In comparison to their counterparts, the odds of NP were higher in participants with acute pain on movement or with present preoperative baseline pain or participants who performed total mastectomy surgery, but the differences were not statistically significant. CONCLUSIONS: Modern machine learning models show improvements over traditional least square regression in predicting of DN4-interview score. Penalized regression methods and the Gradient boosting model out-perform other models. As a predictor discovery tool, machine learning algorithms identify relevant predictors for DN4-interview score that remain statistically significant indicators of neuropathic pain in the classification model. Anxiety, type of surgery and acute pain on movement remain the most useful predictors for neuropathic pain.

The evolution of racial, ethnic, and gender diversity in US otolaryngology residency programs.

OBJECTIVE: To examine the evolution of racial, ethnic, and gender diversity in US otolaryngology-head and neck surgery residency programs and compare these figures with other residency programs. DESIGN: Retrospective database review. SETTING: US residency programs. METHODS: Information concerning minority and female representation in US residency programs was obtained from annually published graduate medical education reports by the Journal of the American Medical Association from 1975 to 2010. Minority representation among US population and university students was obtained from the US Census Bureau. The racial, ethnic, and gender diversity of otolaryngology residents was then compared with other medical fields (general surgery, family medicine, and internal medicine). RESULTS: Underrepresentation in otolaryngology-head and neck surgery is particularly disconcerting for African Americans (-2.3%/y, P = .09) and Native Americans (1.5%/y, P = .11) given their nonsignificant annual growth rates. Hispanic representation (17.3%/y, P < .0001) is growing in otolaryngology but is half the rate of growth of the Hispanic American population (32.8%/y, P < .0001). There is nonetheless promise for women (70.6%/y, P < .0001) and Asian Americans (63.0%/y, P < .0001), who demonstrated statistically significant growth trends. CONCLUSION: To our knowledge, this is the first study to describe the evolution of female and minority representation among US otolaryngology residents. Despite increasing gender, ethnic, and racial diversity among medical residents in general, female and certain minority group representation in US otolaryngology residency programs is lagging. These findings are in contrast to rising trends of diversity within other residency programs including general surgery.

Age is associated with self-reported sleep bruxism, independently of tooth loss.

PURPOSE: The aim of this study was to investigate whether the association between self-reported sleep bruxism (SB) and age is modified by the presence of tooth loss. METHODS: A cross-sectional study was done involving 1,930 residents, ranging from 18 to 89 years of age, who underwent health checkups at the rural health center in Japan. The data collection included oral examinations and self-administrated questionnaires. RESULTS: The prevalence of self-reported SB was 8% (n = 152). It was higher in the groups ranging from 30 to 39 and 40 to 49 years of age in comparison to the groups composed of individuals older than 60 years of age. In the crude analyses, the prevalence of self-reported SB was associated with tooth loss, male, smoking, snoring, sleep talking and a history of childhood teeth grinding. A multiple logistic regression confirmed a significant relationship between self-reported SB and the groups of 30-39 years of age (OR: 2.78, P = 0.003) and 40-49 years of age (OR: 2.31, P = 0.005). Snoring (OR: 2.58, P = 0.001) and known (OR: 8.09, P < 0.001) or unknown (OR: 3.03 P < 0.001%) childhood teeth grinding also showed to be related to self-reported SB. CONCLUSIONS: The present study demonstrates that self-reported SB is associated with age, independently of tooth loss. The associations between SB and age will await further physiological investigations.

Salivary DNA, lipid, and protein oxidation in nonsmokers with periodontal disease.

Reactive oxygen species (ROS) are implicated in the destruction of the periodontium during periodontitis. The imbalance in oxidant activity may be a key factor. The aim of this paper is to determine whether periodontitis is associated with increased oxidative damage to DNA, lipids, and proteins and modification of total antioxidant capacity (TAC) in saliva. Saliva was collected from 58 periodontitis patients and 234 healthy controls, all nonsmokers. Periodontal disease status was characterized using the Community Periodontal Index of Treatment Needs (CPITN). Assays for 8-OHdG (ELISA), 8-epi-PGF2alpha (ELISA), and total protein carbonyls (ELISA), and oxy-blotting (Western)/mass spectrometry were performed to quantify oxidative damage to nucleic acids, lipids, total and individual proteins, respectively, in whole nonstimulated saliva. Salivary TAC was measured by inhibition of ABTS oxidation by metmyoglobin. We observed (i) significantly higher levels of 8-OHdG, 8-epi-PGF2alpha, and carbonylated proteins in saliva of periodontal patients as compared with controls (P=0.0003, <0.0001 and <0.0001); (ii) 8-OHdG, 8-epi-PGF2alpha, and carbonylated proteins were independently negatively associated with CPITN (P=0.004, 0.02, and <0.0001); (iii) a positive correlation between salivary TAC and periodontal disease status in the study group (P<0.0001); and (iv) specific oxidation of transferrin, human IgG1 heavy chain fragment, and salivary amylase in periodontitis. Periodontal disease is associated with increased oxidative modification of salivary DNA, lipids, and proteins. Augmented salivary total antioxidant capacity may represent an adaptive response to oxidative stress. Salivary amylase, transferrin, and human IgG1 heavy chain fragments are particularly prone to enhanced oxidation in periodontitis.

Single-dose dexamethasone reduces dynamic pain after total hip arthroplasty.

BACKGROUND: Preoperative glucocorticoids reduce postoperative nausea but may also improve analgesia and decrease opioid consumption. METHODS: Fifty consecutive patients undergoing elective, unilateral, primary total hip arthroplasty under spinal anesthesia with propofol sedation received in a randomized, double-blind, placebo-controlled manner either 40 mg of dexamethasone or saline placebo i.v. before the start of surgery. I.v. patient-controlled analgesia morphine, ibuprofen 400 mg p.o. q6 h and acetaminophen 650 mg p.o. q6 h were given for 48 h. Pain (0-10 numeric rating scale, NRS) at rest, side effects, and total cumulative patient-controlled analgesia morphine consumption were recorded q4 h for 48 h. Dynamic pain NRS score was recorded at 24 h. C-reactive protein levels were measured in a subgroup of 25 patients at 48 h. RESULTS: The intraoperative sedation requirement with propofol was significantly increased in the dexamethasone group (234.6 +/- 160.1 vs 138.8 +/- 122.7 mg, P = 0.02). Dynamic pain was greatly reduced in the dexamethasone group (NRS score: 2.7, 95% CI: 2.2-3.1 vs 6.8, 6.4-7.2; P < 0.0001). There was no significant effect on pain at rest or cumulative morphine consumption at any time. C-reactive protein levels at 48 h were markedly reduced by dexamethasone (52.4 mg/mL, 28.2-76.6 vs 194.2, 168.9-219.4; P < 0.0001). Seven patients in the control group, but only one in the dexamethasone group, were treated for nausea (P = 0.05). CONCLUSIONS: A single, preoperative i.v. dose of dexamethasone 40 mg has a prolonged suppressive effect on the inflammatory response and decreases dynamic pain 24 h after total hip arthroplasty.

Neurovascular pains: implications of migraine for the oral and maxillofacial surgeon.

Epidemiologic studies have shown that migraine headaches are a common finding in the general population, often associated with a high degree of disability. Additionally, migraine has a reported comorbidity with other medical conditions, most notably with chronic pains, such as temporomandibular disorders. The pathophysiologic mechanisms involved with migraine are suggestive of an increased and prolonged hyperexcitability to stimuli, especially within the trigeminal distribution. Because migraine is mediated by branches of the trigeminal nerve it has the potential to mimic other types of pains, such as toothache or sinusitis. It is therefore recommended that oral and maxillofacial surgeons be familiar with the diagnostic criteria for migraine headaches to identify and appropriately treat such individuals who present to their clinics.

Double-blind randomized, placebo-controlled study of pilocarpine to salvage salivary gland function during radiotherapy of patients with head and neck cancer.

OBJECTIVE: The efficacy of pilocarpine given during radiotherapy for head-neck cancer to reduce xerostomia was assessed. STUDY DESIGN: 58 patients receiving 5000 cGy radiotherapy (RT) involving salivary glands bilaterally were selected at the Jewish General Hospital, Montreal, Canada. Patients were randomly assigned to pilocarpine (5 mg, PILO, n=29) or placebo group (PLA, n=29). These drugs were taken 5 times daily during radiotherapy (first study phase) and 4 times daily for 5 weeks thereafter (second study phase). Saliva was collected and estimated for not stimulated and stimulated patients using the SAXON method. RESULTS: At the conclusion of the first phase, PILO patients reported a better global quality of life (P=.02) and less oral discomfort (P=.001) when compared to PLA. No significant difference was noted in the level of saliva, xerostomia, and other symptoms between patients in PILO and PLA. At the end of the second phase, a difference between groups was observed only for xerostomia and mucosal pain; both were significantly higher in PILO when compared to PLA (P <.05). CONCLUSION: Pilocarpine 5mg given 5 times daily did not appear to improve the production of saliva and global quality of life assessments, nor to decrease the symptoms of xerostomia 5 weeks after completion of RT in patients who were taking pilocarpine post-RT. There was a slight improvement in the quality of life and a decrease in the level of discomfort noted only after the first study phase. The limitations of this study are discussed.