Facia-fix: mobile application for bell's palsy diagnosis and assessment using computer vision and deep learning.

Facial paralysis (FP) is a condition characterized by the inability to move some or all of the muscles on one or both sides of the face. Diagnosing FP presents challenges due to the limitations of traditional methods, which are time-consuming, uncomfortable for patients, and require specialized clinicians. Additionally, more advanced tools are often uncommonly available to all healthcare providers. Early and accurate detection of FP is crucial, as timely intervention can prevent long-term complications and improve patient outcomes. To address these challenges, our research introduces Facia-Fix, a mobile application for Bell's palsy diagnosis, integrating computer vision and deep learning techniques to provide real-time analysis of facial landmarks. The classification algorithms are trained on the publicly available YouTube FP (YFP) dataset, which is labeled using the House-Brackmann (HB) method, a standardized system for assessing the severity of FP. Different deep learning models were employed to classify the FP severity, such as MobileNet, CNN, MLP, VGG16, and Vision Transformer. The MobileNet model which uses transfer learning, achieved the highest performance (Accuracy: 0.9812, Precision: 0.9753, Recall: 0.9727, F1 Score: 0.974), establishing it as the optimal choice among the evaluated models. The innovation of this approach lies in its use of advanced deep learning models to provide accurate, objective, non-invasive and real-time comprehensive quantitative assessment of FP severity. Preliminary results highlight the potential of Facia-Fix to significantly improve the diagnostic and follow-up experiences for both clinicians and patients.

The Systemic Inflammatory Response Index as a Novel Diagnostic Indicator for Bell's Palsy.

Aims/Background The systemic inflammatory response index (SIRI), an emerging hematological marker of inflammation, has shown promise as a promising biomarker for a variety of inflammatory conditions. This study aims to explore the diagnostic role of SIRI in Bell's palsy (BP). Methods For this retrospective study, 73 people diagnosed with BP between January 2021 and December 2023 were recruited, along with 73 healthy controls who were age- and sex-matched. The SIRI and other blood inflammatory markers, including the systemic immune-inflammation index (SII), neutrophil-to-lymphocyte ratio (NLR), and platelet-to-lymphocyte ratio (PLR), were determined for all participants, by enumerating their peripheral blood cell counts. Facial nerve function was assessed upon admission and after one month of treatment using the House-Brackmann Facial Nerve Grading System (H-B). According to this system, patients with an H-B grade of 1-2 are considered recovered, while those with an H-B grade of 3-6 are regarded as not recovered. Results The SIRI (0.94 vs 0.48, p < 0.001), SII (480.3 vs 329.12, p < 0.001), NLR (2.42 vs 1.41, p < 0.001), and PLR (141.05 vs 117.28, p = 0.001) showed a significant increase in the BP group compared to the control group. The receiver operating characteristic (ROC) curve analysis revealed that the area under the curve (AUC) for SIRI was higher than those for SII, NLR, and PLR, respectively. Upon one-month follow-up, significant differences in the values of SIRI, SII, and NLR were observed between the favorable prognosis group and the poor prognosis group (SIRI: 1.07 vs 0.87, p = 0.011; SII: 647.85 vs 422.11, p = 0.005; NLR: 3.31 vs 2.11, p = 0.013). The AUC of ROC curve for SIRI was found to be lower than that of SII but higher than that of NLR. Conclusion The SIRI has the potential to be an important BP diagnostic and prognostic marker.

Motor unit number index in Bell's palsy: A potential electrophysiological biomarker for early evaluation.

INTRODUCTION: Reliable, noninvasive early diagnostics of neuromuscular function in Bell's palsy, which causes facial paralysis and reduced quality of life, remain to be established. Here, we aimed to evaluate the utility of the motor unit number index (MUNIX) for the quantitative electrophysiological assessment of early-stage Bell's palsy, its correlation with clinical assessments, changes following treatment, and association with clinical prognosis. METHODS: MUNIX measures were recorded from the bilateral zygomaticus, orbicularis oculi, and orbicularis oris muscles of 10 healthy individuals and 64 patients with Bell's palsy. The patients were assessed by two specialist neurologists using the House-Brackmann and Sunnybrook Facial Grading Systems. Repeat assessments were performed on 20 patients with Bell's palsy who received treatment. Additionally, the 64 patients were reassessed using clinical scales after a 1-month interval. RESULTS: The MUNIX values of the main affected muscles on the affected side were lower than those on the healthy side in patients with Bell's palsy (p < .05). The MUNIX measurements significantly correlated with the clinical facial nerve palsy scale scores (p < .05). Significant improvements were observed in the MUNIX values on repeat testing following treatment (p < .05). The baseline motor unit size index (the compound muscle action potential amplitude divided by MUNIX) was positively associated with improved clinical presentation after 1 month (p < .05). CONCLUSION: MUNIX can be used as an electrophysiological biomarker for the quantitative assessment of facial nerve palsy and treatment response, and as a prognostic biomarker, in patients with early Bell's palsy, and is recommended as a complement to conventional neurophysiological examinations.

[Bilateral facial palsy: an atypical presentation of Lyme disease (a case report)]. / Paralysie faciale bilatérale : une présentation atypique d'une maladie de Lyme (cas clinique).

Lyme neuroborreliosis is a rare zoonosis which can be difficult to diagnose, in particular in low endemic areas. We here report the case of a 35-year-old man presenting with disabling back pain preceded by facial monoplegia, which was wrongly treated as Bell's palsy (paralysis a frigore) and then as post-traumatic lumbosciatica. The onset of facial diplegia allowed for a definitive diagnosis. The patient was treated with ceftriaxone and symptoms gradually improved.

Development of a clinical diagnostic model for Bell's palsy in patients with facial muscle weakness.

Early diagnosis of Bell's palsy is crucial for effective patient management in primary care settings. This study aimed to develop a simplified diagnostic tool to enhance the accuracy of identifying Bell's palsy among patients with facial muscle weakness. Data from 240 patients were analyzed using seven potential clinical evaluation indicators. Two diagnostic benchmarks were established: one based on clinical assessment and the other incorporating magnetic resonance imaging (MRI) findings. A multivariate logistic regression model was developed based on these benchmarks, resulting in the construction of a predictive tool evaluated through latent class models. Both models retained four key clinical indicators: absence of forehead wrinkles, accumulation of food and saliva inside the mouth on the affected side, presence of vesicular rash in the ear or pharynx, and lack of pain or symptoms associated with tick exposure, rash, or joint pain. The first model demonstrated excellent discriminative ability (area under the curve [AUC] = 0.96, 95% confidence interval [CI] 0.94 - 0.99) and calibration (P < 0.001), while the second model also showed good performance (AUC = 0.88, 95% CI 0.83 - 0.92) and calibration (P = 0.005). Bootstrap validation indicated no significant overfitting. The latent class defined by the first model significantly aligned with the clinical diagnosis group, while the second model showed lower consistency.

Intelligent bell facial paralysis assessment: a facial recognition model using improved SSD network.

With the continuous progress of technology, the subject of life science plays an increasingly important role, among which the application of artificial intelligence in the medical field has attracted more and more attention. Bell facial palsy, a neurological ailment characterized by facial muscle weakness or paralysis, exerts a profound impact on patients' facial expressions and masticatory abilities, thereby inflicting considerable distress upon their overall quality of life and mental well-being. In this study, we designed a facial attribute recognition model specifically for individuals with Bell's facial palsy. The model utilizes an enhanced SSD network and scientific computing to perform a graded assessment of the patients' condition. By replacing the VGG network with a more efficient backbone, we improved the model's accuracy and significantly reduced its computational burden. The results show that the improved SSD network has an average precision of 87.9% in the classification of light, middle and severe facial palsy, and effectively performs the classification of patients with facial palsy, where scientific calculations also increase the precision of the classification. This is also one of the most significant contributions of this article, which provides intelligent means and objective data for future research on intelligent diagnosis and treatment as well as progressive rehabilitation.

Elevated TRPV2 expression in the facial nerve of rats by cold stimulation: Implications for Bell's palsy.

OBJECTIVE: Bell's palsy, also referred to as clinical manifestations of unilateral facial nerve palsy, encompasses downward angling of the corners of the mouth, the absence of forehead creases, and unilateral incomplete eyelid closure. The incidence of Bell's palsy has increased progressively in recent years, but the underlying mechanism of its occurrence remains unknown; therefore, it is essential to investigate both the cause and treatment of Bell's palsy. Member 2 of the Subfamily V Transient Receptor Potential Cation Channel is a mechanically and thermally sensitive ion channel that plays a crucial role in neural growth and development. Using a novel modeling technique, we endeavored to develop an animal model of Bell's palsy and determine whether TRPV2 expression is altered throughout the course of a facial nerve injury. MATERIALS AND METHODS: The rats were categorized into 3 groups, and their facial nerve function was assessed using RT-qPCR, WB, and pathologic testing, respectively, after undergoing unilateral cold air stimulation for 1, 3, and 7 days. TRPV2 expression was identified using these techniques. RESULTS: In response to cold stimulation, rats exhibited facial nerve paralysis symptoms, demyelinating lesions in the facial nerve, and increased TRPV2 expression. CONCLUSIONS: Extended cold stimulation of the facial nerve in rats may lead to an imbalance in facial nerve homeostasis and increased TRPV2 expression. These findings will contribute to the understanding of the potential mechanism by which cold stimulation affects the facial nerve. Moreover, this finding implies that TRPV2 could possibly function as an additional diagnostic marker or therapeutic target in the context of Bell's palsy.

Prognostic value of electroneurography using the midline method for predicting the development of synkinesis after peripheral facial palsy.

OBJECTIVE: The prognostic value of electroneurography (ENoG) for predicting the incidence of synkinesis is reportedly about 40 % using the formal standard method (ENoG-SM). However, the prognostic value of ENoG using the newly developed midline method (ENoG-MM) has not been determined. The aim of this study was to demonstrate the optimal prognostic value and advantages of ENoG-MM for predicting the incidence of synkinesis. METHODS: Participants were 573 patients treated for peripheral facial palsy including Bell's palsy or Ramsay Hunt syndrome. We investigated the clinical presence of any oral-ocular or ocular-oral synkinesis from the medical records. ENoG-MM and ENoG-SM were performed 10-14 days after symptom onset. In ENoG-MM, compound muscle action potentials were recorded by placing the anode on the mental protuberance and the cathode on the philtrum. In ENoG-SM, electrodes were placed on the nasolabial fold. Synkinesis was clinically assessed at the end of follow-up or at >1 year after onset. The sensitivity and specificity of ENoG values for predicting the incidence of synkinesis were compared between ENoG-MM and ENoG-SM at every 5 % around 40 % (range, 30-50 %). RESULTS: At every 5 % of ENoG values around 40 %, ENoG-MM provided higher sensitivity and lower specificity for predicting the incidence of synkinesis compared with ENoG-SM. In particular, when the cut-off value was set at 45 %, sensitivity was 100 % and 95.3 % with ENoG-MM and ENoG-SM, respectively. CONCLUSION: In peripheral facial palsy, ENoG-MM offered higher sensitivity than ENoG-SM for predicting synkinesis. ENoG-MM is useful for screening patients at risk of developing synkinesis. In clinical practice, an ENoG-MM cut-off value of 45 % must be the optimal prognostic value because of the 100 % sensitivity.

Adult-onset congenital cholesteatoma in the hypotympanum initially presenting as Bell's palsy: A case report.

INTRODUCTION: Cholesteatoma is a rare disease characterized by the accumulation of keratinized squamous epithelial cells in the middle ear or mastoid cavity. Vertigo and facial palsy, which are rare complications, may indicate erosion into the semicircular canals or the fallopian canal. PATIENT CONCERNS: A 40-year-old woman presented to our clinic with progressive right-sided hearing loss over 5 years (primary concern). Approximately 10 years ago, the patient had developed acute right-sided facial weakness with no additional symptoms. A neurologist at another hospital had diagnosed her condition as Bell's palsy and treated it accordingly. DIAGNOSIS: Adult-onset congenital cholesteatoma in the hypotympanum. INTERVENTION: Combined endoscopic and microscopic removal of the cholesteatoma. OUTCOMES: Physical examination revealed slight improvement in right-sided peripheral facial palsy. LESSON: Routine eardrum examination is recommended for patients presenting with isolated peripheral facial palsy. If necessary, a patient should be referred to an otologist for further evaluation and treatment.

Facial Function in Bell Palsy in a Cohort of Children Randomized to Prednisolone or Placebo 12 Months After Diagnosis.

BACKGROUND: Information on the medium-term recovery of children with Bell palsy or acute idiopathic lower motor neuron facial paralysis is limited. METHODS: We followed up children aged 6 months to <18 years with Bell palsy for 12 months after completion of a randomized trial on the use of prednisolone. We assessed facial function using the clinician-administered House-Brackmann scale and the modified parent-administered House-Brackmann scale. RESULTS: One hundred eighty-seven children were randomized to prednisolone (n = 93) or placebo (n = 94). At six months, the proportion of patients who had recovered facial function based on the clinician-administered House-Brackmann scale was 98% (n = 78 of 80) in the prednisolone group and 93% (n = 76 of 82) in the placebo group. The proportion of patients who had recovered facial function based on the modified parent-administered House-Brackmann scale was 94% (n = 75 of 80) vs 89% (n = 72 of 81) at six months (OR 1.88; 95% CI 0.60, 5.86) and 96% (n = 75 of 78) vs 92% (n = 73 of 79) at 12 months (OR 3.12; 95% CI 0.61, 15.98). CONCLUSIONS: Although the vast majority had complete recovery of facial function at six months, there were some children without full recovery of facial function at 12 months, regardless of prednisolone use.

Bell's palsy: a case report of unusual presentation in a patient with rhino-orbital cerebral mucormycosis.

BACKGROUND: Mucormycosis is a fungal infection caused by the Mucorales order of fungi. This fungus is commonly found in soil and can cause disease in immunocompromised patients. On the other hand, Bell's palsy is an idiopathic condition that results in the sudden onset of unilateral facial muscle weakness, affecting the facial nerve. CASE PRESENTATION: A 51-year-old Persian housewife with a history of poorly controlled diabetes mellitus presented with a splitting headache that had been ongoing for 1 week and an inability to close her left eye or make facial expressions on the left side of her face. The patient's vital signs were normal, but physical examination revealed a yellow-grey scar on the left side of her hard palate and Bell's palsy on the left side. A neurological examination showed that she could move both eyes but could not close her left eye, move up her left eyebrow, or smile. Further investigations were performed, including laboratory tests, radiologic imaging, and functional endoscopic sinus surgery. The patient underwent three rounds of debridement for bony erosion in the medial and posterior walls of the left maxillary sinus and the hard palate. Pathological examination confirmed mucormycosis infection in the hard palate and mucosa. CONCLUSION: Fungal infection must be considered a potential diagnosis for immunocompromised adults who exhibit symptoms of Bell's palsy.

Bell's Palsy and COVID-19: Insights from a Population-Based Analysis.

Background: Coronavirus disease 2019 (COVID-19) has been linked to Bell's palsy and facial paralysis. Studies have also shown increased risk of Bell's palsy in unvaccinated COVID-19 patients. Objective: To compare the relationship between Bell's palsy and COVID-19 infection and vaccination. Design: This is a retrospective longitudinal study. Methods: The COVID-19 research network was used to identify patients with facial palsy presenting to 70 health care organizations in the United States. The incidence of Bell's palsy was measured within an 8-week window after COVID-19 test or vaccination event in identified patients. Results: Incidence of facial palsy diagnosis (0.99%) was higher than the background rate within 2 months of COVID-19 infection. When compared with their negative counterparts, patients with COVID-19 infection had significantly higher risk of Bell's palsy (risk ratio [RR] = 1.77, p < 0.01) and facial weakness (RR = 2.28, p < 0.01). Risk ratio was also amplified when evaluating Bell's palsy (RR = 12.57, p < 0.01) and facial palsy (RR = 44.43; p < 0.01) in COVID-19-infected patients against patients who received COVID-19 vaccination. Conclusion: In our patient population, there is a higher risk of developing facial palsy within 2 months of COVID-19 infection versus vaccination. Vaccinated patients are not at higher risk of developing facial palsy.

Comparison of Objective Facial Metrics on Both Sides of the Face Among Patients with Severe Bell's Palsy Treated with Mirror Effect Plus Protocol Rehabilitation Versus Controls.

Objective: The extent to which the healthy hemiface dynamically contributes to facial synchronization during facial rehabilitation has been largely unstudied. This study compares the synchronization of both hemifaces in severe Bell's palsy patients who either received facial rehabilitation called "Mirror Effect Plus Protocol" (MEPP) or basic counseling. Methods: Baseline and 1-year postonset data from 39 patients (19 = MEPP and 20 = basic counseling) were retrospectively analyzed using Emotrics+, a software that generates facial metrics with artificial intelligence (AI) algorithms. Paired t-tests were used for intrasubject comparisons of hemifaces, and mixed model analysis were used to compare between groups. Results: For voluntary movements, a significant difference in favor of the MEPP group was only found for smiling (p = 0.025*). However, at 1-year postonset, the control group showed significant variability between hemifaces for most synkinesis measurements [nasolabial fold (p = 0.029*); eye area (p = 0.043*); palpebral fissure (p = 0.011*)]. Conclusion: In this study, a better synchronization of both hemifaces was found in the MEPP group. Interestingly, motor adaptation in movement amplitude of the healthy hemiface seemed to contribute to this synchronization in MEPP patients. Further studies are needed to standardize the procedure of AI measurements and to adapt it for clinical use.

Comparison of oral versus intravenous steroid in the management of Bell's palsy: a systematic review and meta-analysis of randomized clinical trials.

BACKGROUND: Bell's palsy is a condition affecting cranial nerve VII that results in acute peripheral unilateral facial weakness or paralysis of unclear etiology. Corticosteroids are the primary therapy choice, because they improve outcomes. According to a recent study, prednisolone effectively treats Bell's palsy in the short and long term. This study aimed to assess the effectiveness and safety of Single-Dose Intravenous Methylprednisolone to Oral Prednisolone in treating Bell's palsy patients. METHODS: PRISMA statement guidelines were used to design and conduct this systemic review. MEDLINE, Cochrane Library, and EMBASE databases were used in our search. We conducted the database search in November 2022. RESULTS: Thirty-three publications were reviewed as a result of the literature review. Three studies were included in the meta-analysis after applying our criteria. 317 Bell's palsy patients were included in our study. Regarding complete recovery to grade 1 in 1 month, IV methylprednisolone was higher than oral prednisolone; (log OR = 0.52, 95% CI [0.08, 0.97], P = 0.022). However, at 3 months, the two groups had no significant difference. Patients with grade 4 Bell's palsy were more likely to fully recover to grade 1 in 1 month with IV methylprednisolone than with oral prednisolone (log OR = 0.73, 95% CI [0.19, 1.26], P = 0.008), but not for patients with grade 3 or grade 2 Bell's palsy. CONCLUSION: This study shows evidence that patients with Bell's palsy can fully recover to grade 1 in 1 month when IV methylprednisolone is used instead of oral prednisolone. At 3 months, however, there was no discernible difference between the two treatments. Within 3 days of the onset of symptoms, IV methylprednisolone treatment can be started, which may help patients recover fully to grade 1 in 1 month. However, administering IV methylprednisolone may not always have long-term advantages compared to oral prednisolone.

The Rate of Occult Lesion Diagnosis in a Large Bell's Palsy Cohort.

OBJECTIVES: We characterize occult lesion diagnosis rates after initial Bell's palsy diagnoses. METHODS: A de-identified database of all facial palsy patients who presented to an extensive health care system across 22 years was created using Epic SlicerDicer. Among patients with Bell's palsy diagnoses, we extracted demographic and any subsequent occult lesion diagnosis data across various clinical sites. Descriptive and multivariable regression analyses comparing patients with occult lesion diagnoses made at different time points were included. RESULTS: Among the total 3912 facial palsy patients, 2240 had Bell's palsy diagnoses, of which 217 (9.7%) had subsequent lesion diagnoses at a median (IQR) of 12.3 (4.2, 23.8) months, consisting of cranial nerve neoplasms (62.2%), parotid gland neoplasms (34.1%), and cholesteatomas (3.7%). Although a large proportion of total lesions were diagnosed within the first 3 months (19.8%), 69.5% were diagnosed after 6 months. There were no demographic differences among patients diagnosed with different lesion types, but Asian patients were more likely to be diagnosed with occult lesions after 12 months after Bell's palsy diagnosis compared with white patients (odds ratio = 6.2, p = 0.001). CONCLUSIONS: In one of the largest Bell's palsy cohorts to date, we identified a 9.7% occult lesion diagnosis rate at a median of 12.3 months after Bell's palsy diagnosis. These data underscore the importance of timely workup for occult lesions in cases of facial palsy with no signs of recovery after 3-4 months. LEVEL OF EVIDENCE: 4 Laryngoscope, 134:911-918, 2024.

Variations in the treatment of acute peripheral facial paralysis. A nationwide survey.

BACKGROUND: Acute peripheral facial paralysis may be diagnosed and treated by different specialists. OBJECTIVE: The aim of this study was to explore the variability in the treatment of Bell's palsy (BP) and Ramsay Hunt Syndrome (RHS) among different medical specialties. METHODS: An anonymous nationwide online survey was distributed among the Spanish Societies of Otorhinolaryngology (ORL), Neurology (NRL) and Family and Community Medicine (GP). RESULTS: 1039 responses were obtained. 98% agreed on using corticosteroids, ORL using higher doses than NRL and GP. Among all, only 13% prescribed antivirals in BP routinely, while 31% prescribed them occasionally. The percentage of specialists not using antivirals for RHS was 5% of ORL, 11% of NRL, and 23% of GP (GP vs. NRL p = 0.001; GP vs. ORL p < 0.0001; NRL vs. ORL p = 0,002). 99% recommended eye care. Exercises as chewing gum or blowing balloons were prescribed by 45% of the participants with statistically significant differences among the three specialties (GP vs. NRL p = 0.021; GP vs. ORL p < 0.0001; NRL vs. ORL p = 0.002). CONCLUSION: There is general agreement in the use of corticosteroids and recommending eye care as part of the treatment of acute peripheral facial paralysis. Yet, there are discrepancies in corticosteroids dosage, use of antivirals and recommendation of facial exercises among specialties.

Complete Hemifacial Paralysis Post-facelift: Making Sense of a Plastic Surgeon's Worst Nightmare.

BACKGROUND: Postrhytidectomy hemifacial paralysis is a frightening clinical condition affecting the proximal facial nerve and most often associated with Bell's palsy. Associated symptoms are common and include auditory, salivary, vestibular, and gustatory complaints. OBJECTIVES: The aim of the study was to provide increased awareness of postrhytidectomy hemifacial paralysis secondary to Bell's palsy in the plastic surgery community. METHODS: Following a roundtable discussion with the senior author's (J.C.G.) plastic surgery colleagues located all over the world, 8 surgeons reported having had firsthand experience with hemifacial paralysis in patients following facelift. Descriptions of their cases, including preoperative, intraoperative, and postoperative courses were collected and reported. RESULTS: A total of 10 cases of postrhytidectomy hemifacial paralysis were analyzed based on results of a clinical questionnaire. Eight of the 10 cases involved all facial nerve branches, with 2 cases sparing the marginal mandibular branch. The vast majority of cases were referred to a neurologist and steroids initiated. Two patients were returned to the operating room for exploration. Associated symptoms reported included pain in the ear, hearing loss, ocular symptoms such as tearing or dryness, vestibular symptoms such as vertigo, changes in taste, and in 1 patient an electric-shock type sensation to the face. CONCLUSIONS: Hemifacial paralysis associated with Bell's palsy following rhytidectomy is a rare but known clinical entity that should be included in the preoperative informed consent process before facelift. Current management trends are neurology referral and steroid initiation.

Monocyte to high-density lipoprotein ratio as a novel-potential biomarker for predicting prognosis of Bell's palsy.

OBJECTIVES: In several disorders, the monocyte to high-density lipoprotein ratio (MHR) has been considered a biomarker of systemic inflammation and oxidative stress. However, its role in Bell's palsy (BP) remains unclear. This study investigates the relationship between elevated MHR and poor recovery in BP patients. METHODS: The clinical data of 729 BP patients were analyzed retrospectively. The House-Brackmann Facial Nerve Grading System (H-B) was utilized to assess the severity of facial motor dysfunction during admission and the follow-up period after discharge. According to the 6 months follow-up data, H-B grades 1-2 were classified as recovered (n = 557), and H-B grades 3-6 as unrecovered (n = 172). The patients were split into MHR ≤ 0.26 (n = 361) and MHR > 0.26 (n = 368) groups based on the median MHR to further analyze the connection between different MHRs and prognosis. RESULTS: The level of MHR was substantially greater in the unrecovered group of BP patients than in the restored group (medians[interquartile range], 0.32[0.20, 0.49] vs 0.24[0.11, 0.39], P < 0.001). MHR was an independent risk factor for BP prognosis as indicated by the multivariate logistic regression analysis (OR = 4.467, 95% CI = 1.875-10.646, P = 0.001). The area under the curve (AUC) was 0.615 (95% CI = 0.566-0.664, P < 0.001). The initial H-B score did not differ significantly between MHR ≤ 0.26 (n = 361) and MHR > 0.26 (n = 368) groups. However, after 6 months of follow-up, the high-MHR group's H-B score was considerably greater than the low-MHR group's. CONCLUSIONS: MHR is expected to be an accessible and effective biomarker of BP. In BP patients, elevated MHR is related to an increased chance of poor recovery.