Hearing recovery prediction and prognostic factors of idiopathic sudden sensorineural hearing loss: a retrospective analysis with a deep neural network model

Abstract Objective Idiopathic Sudden Sensorineural Hearing Loss (ISSHL) is an otologic emergency, and an early prediction of prognosis may facilitate proper treatment. Therefore, we investigated the prognostic factors for predicting the recovery in patients with ISSHL treated with combined treatment method using machine learning models. Methods We retrospectively reviewed the medical records of 298 patients with ISSHL at a tertiary medical institution between January 2015 and September 2020. Fifty-two variables were analyzed to predict hearing recovery. Recovery was defined using Siegel's criteria, and the patients were categorized into recovery and non-recovery groups. Recovery was predicted by various machine learning models. In addition, the prognostic factors were analyzed using the difference in the loss function. Results There were significant differences in variables including age, hypertension, previous hearing loss, ear fullness, duration of hospital admission, initial hearing level of the affected and unaffected ears, and post-treatment hearing level between recovery and non-recovery groups. The deep neural network model showed the highest predictive performance (accuracy, 88.81%; area under the receiver operating characteristic curve, 0.9448). In addition, initial hearing level of affected and non-affected ear, post-treatment (2-weeks) hearing level of affected ear were significant factors for predicting the prognosis. Conclusion The deep neural network model showed the highest predictive performance for recovery in patients with ISSHL. Some factors with prognostic value were identified. Further studies using a larger patient population are warranted. Level of evidence: Level 4.

Drug-induced Sleep Endoscopy: Are there Predictors for Failure of Oral Appliance Treatment?

Abstract Introduction In the literature, evidence is lacking on the predictive value of druginduced sleep endoscopy (DISE) for oral appliance treatment (OAT). Objectives The aim of the present study is to evaluate whether DISE with concomitant mandibular advancement maneuver can predict failure of OAT. Methods An observational retrospective study including patients diagnosed with obstructive sleep apnea (OSA) who previously received OAT. Results of DISE were analyzed in a group with documented OAT failure (apnea-hypopnea index [AHI] >10 events/hour or < 50% reduction) and a group with OAT benefit (AHI <10 events/hour or >50% reduction). The upper airway was assessed using the velum, oropharynx, tongue base, epiglottis (VOTE) classification. Additionally, a mandibular advancement maneuver, manually protruding the mandible by performing a jaw thrust, was performed to mimic the effect of OAT. Results The present study included 50 patients with OAT failure and 20 patients with OAT benefit. A subgroup analysis of patients with OAT failure and an AHI <30events/hour included 26 patients. In the OAT failure group, 74% had a negative jaw thrust maneuver. In the subgroup with an AHI <30 events/hour, 76.9% had a negative jaw thrust maneuver. In the OAT benefit group, 25% had a negative jaw thrust maneuver (p< 0.001). Conclusions A negative jaw thrust maneuver during DISE can be a valuable predictor for OAT failure, independent of AHI. Drug-induced sleep endoscopy should be considered as a diagnostic evaluation tool before starting OAT.

Prediction models of outcome for patients with prolonged disorders of consciousness: a systematic review / 中国康复理论与实践

@#Objective To systematicly evaluate the constituent factors and accuracy of prediction models of outcome for patients with prolonged disorders of consciousness. Methods Articles about prediction models of outcome for patients with prolonged disorders of consciousness were retrieved from PubMed, Web of Science, CNKI and Wanfang Data until September 30th, 2021. The authors, publishing times, subjects, predictive indicators, outcomes and conclusions were extracted. Results A total of 4 313 articles were returned and 37 included, comprising randomized controlled trials and cohort studies, which published mainly from 2012 to 2021. The subjects were patients with prolonged disorders of consciousness, and their predictions consisted of clinical assessment scales, neuroimaging, neuroelectrophysiology and laboratory indicators. Conclusion Prediction models may be valuable for the long-term outcomes of patients with prolonged disorders of consciousness. Most of the current prediction models are composed of only a limited number of technical means, and the accuracy is uneven. Coma Recovery Scale-revised, default mode network and multiple evoked potentials-related prediction models are accurate, but lack a unified adaptation standard.

Predictive role of the degree of prospective memory impairment on treatment response to SSRIs in patients with obsessive-compulsive disorder / 四川精神卫生

ObjectiveTo explore the predictive role of the degree of prospective memory impairment on the treatment response to Selective Serotonin Reuptake Inhibitors （SSRIs） in patients with obsessive-compulsive disorder. MethodsA total of 30 patients with obsessive-compulsive disorder who met the diagnostic criteria of the Diagnostic and Statistical Manual of Mental Disorders， fourth edition， text revision （DSM-IV-TR） were selected， and all patients were treated with SSRIs for 4 weeks. The severity of obsessive-compulsive symptom was assessed using Yale-Brown Obsessive Compulsive Scale （Y-BOCS）， and the efficacy was evaluated by the reduction rate of Y-BOCS score. Moreover， the performance of event-based， time-based and activity-based prospective memory tasks were compared before and after treatment. ResultsAfter treatment， the total Y-BOCS score of patients was lower than before treatment ［（27.07±4.63） vs. （24.87±5.93）， F（1，29）=4.984， P=0.033］， meantime， the performance of event- and time- based prospective memory tasks was improved ［（0.78±0.21） vs. （0.88±0.11）， F（1，29）=9.022， P=0.005； （0.81±0.17） vs. （0.91±0.11）， F（1，29）=9.063， P=0.005］. Correlation analysis showed that the performance of event-based prospective memory at baseline was positively correlated with the reduction of Y-BOCS score （r=0.478， P=0.014）. The event-based prospective memory performance at baseline could positively predict the treatment response to SSRIs treatment in patients （β=0.441， P=0.014）. ConclusionThe event-based prospective memory function of patients with obsessive-compulsive disorder can positively predict SSRIs treatment outcome， and patients with better prospective memory performance yield better treatment responses.

Artificial intelligence in radiotherapy: a technological review / 医学前沿

Radiation therapy (RT) is widely used to treat cancer. Technological advances in RT have occurred in the past 30 years. These advances, such as three-dimensional image guidance, intensity modulation, and robotics, created challenges and opportunities for the next breakthrough, in which artificial intelligence (AI) will possibly play important roles. AI will replace certain repetitive and labor-intensive tasks and improve the accuracy and consistency of others, particularly those with increased complexity because of technological advances. The improvement in efficiency and consistency is important to manage the increasing cancer patient burden to the society. Furthermore, AI may provide new functionalities that facilitate satisfactory RT. The functionalities include superior images for real-time intervention and adaptive and personalized RT. AI may effectively synthesize and analyze big data for such purposes. This review describes the RT workflow and identifies areas, including imaging, treatment planning, quality assurance, and outcome prediction, that benefit from AI. This review primarily focuses on deep-learning techniques, although conventional machine-learning techniques are also mentioned.

Validity of mannheim peritonitis index in predicting outcome of patients with perforative peritonitis in a tertiary care centre Kerala, India

Background: Perforation peritonitis is one of the most commonly encountered surgical emergencies in our country. The prognosis of secondary peritonitis remains poor despite development in diagnosis and management. Early identification of patients with severe peritonitis may help in selecting patients for aggressive surgical approach.Methods: The study was conducted in 128 cases of perforation peritonitis admitted and treated in the department of surgery in a tertiary care centre. Initial diagnosis was made on the basis of detailed history, clinical examination and presence of pneumoperitoneum on erect abdominal X-ray. Patients were first assessed using a predesigned Performa, then MPI score was calculated for each patient and the patients were followed-up till death or discharge from the hospital.Results: The ROC curve analysis shows area under the curve was 0.986 with a standard error of 0.008, 95% CI (0.971 to 1.001), p<0.0001. In our study authors found that for the MPI score of 26, sensitivity was 91.3% and specificity was 92.4%, with a positive likelihood ratio of 12.01 and a negative likelihood ratio of 0.09. Age of the patient, presence of organ failure, associated malignancy, generalised type of peritonitis and the original MPI Score has got a significant association with the final outcome (i.e. p value <0.05).Conclusions: MPI is an excellent prognostic index for peritonitis with high accuracy in individual prognosis that is cheap, cost effective, easily measurable and reproducible. The study accentuates that early diagnosis, appropriate resuscitation and prompt surgical intervention still remain the keystones in the management of perforation peritonitis.

Evaluation of six scoring systems and four laboratory tests in the prognostic assessment of severe acute pancreatitis / 中华消化杂志

Objective To evaluate the six scoring systems and four laboratory tests,including pancreatitis outcome prediction (POP),Ranson score,bedside index for severity in acute pancreatitis (BISAP),acute physiology and chronic health evaluation Ⅱ (APACHE Ⅱ),systemic inflammatory response syndrome (SIRS),and Glasgow score as well as four laboratory tests including C-reactive protein (CRP),hematocrit (HCT),blood urea nitrogen (BUN) and serum creatinine (Scr) in the prognostic assessment of severe acute pancreatitis (SAP).Methods From January 2016 to December 2017,at Sir Run Run Shaw Hospital,151 SAP patients who met the enrollment criteria were retrospectively analyzed.According to the time from onset to treatment,the patients were divided into less than three days group (n=102) and over three days group (n=49).The evaluation of six scoring systems and four laboratory tests,including CRP,HCT,BUN and Scr at 0,24 and 48 h after hospitalization in the prognostic assessment of SAP patients was measured by receiver-operating characteristic (ROC) curve.Results The Ranson score had the highest area under curve (AUC) value (0.916) in the evaluation of the prognosis of SAP patients less than three days group followed by BISAP,APACHE Ⅱ,Glasgow and POP score,and their AUC values were 0.832,0.823,0.793,and 0.787,respectively,all of them were statistically significant in the prognostic assessment of SAP patients in less than three days group (all P＜0.05).There were statistically significant of BISAP and APACHE Ⅱ scores in the prognostic evaluation of SAP patients in over three days group (both P＜0.05),and the AUC values were 0.751 and 0.735,respectively,which were less than those of SAP patients in less than three days group.There were statistical significance of BUN and Scr at 24 and 48 h after hospitalization in the prognostic assessment of SAP patients in less than three days group (all P＜0.05),and the AUC values were 0.856,0.853 and 0.793,0.874,respectively.There were statistical significance of BUN at 0,24,48 h and Scr at 48 h after hospitalization in the prognostic assessment of SAP patients in over three days group (all P＜0.05),and the AUC value was 0.709,0.754,0.742 and 0.716,respectively.Conclusions Ranson,POP and Glascow score systems are only suitable for patients with SAP less than three days.APACHE Ⅱ,BISAP score systems,BUN and Scr can be used to evaluate patients with SAP over three days,but are more suitable for patients with SAP less than three days group.

Effectiveness of the APACHE II Scoring System in an Intensive Care Unit: Results of a Prospective Study.

Background: The high cost of intensive care unit (ICU) services and limitations in health resources can prompt managers to use predictive scoring systems. Objective: To evaluate the role of APACHE II as a scoring system to predict outcomes and to compare actual and expected mortality rates. Methods: This prospective study was conducted in a10-bed, mixed ICU at Namazi University Hospital, a teaching hospital in Shiraz, Iran. All patients were included consecutively and data were collected during the first 24 h of admission. Statistical analyses were done with SPSS v.16 software. The differences were considered statistically significant at a P value of <0.05. Results: From June to November of 2013, data were available for 110 (61.4%) ICU admission. The patients’ mean (SD) age was 55.1 (17.7) years. Mean APACHE II score was 17.85±7.4. The total standardized mortality ratio (SMR) was 0.92, and the ratio ranged from 0.48 in medical patients to 1.22 in post-elective surgery patients. With the sensitivity 18.5% and specificity 92.8%, the highest correct classification was obtained at predicted death risk 0.6 (74.5%). Conclusion: We recommend the use of this outcome prediction score for decision-making and classifying patients based on the degree of severity of their diseases in our setting. Further work is needed with larger sample sizes to more precisely determine the generalisability of our results and evaluate validity of this outcome prediction score.

Artificial neural network models for predicting 1-year mortality in elderly patients with intertrochanteric fractures in China

The mortality rate of older patients with intertrochanteric fractures has been increasing with the aging of populations in China. The purpose of this study was: 1) to develop an artificial neural network (ANN) using clinical information to predict the 1-year mortality of elderly patients with intertrochanteric fractures, and 2) to compare the ANN's predictive ability with that of logistic regression models. The ANN model was tested against actual outcomes of an intertrochanteric femoral fracture database in China. The ANN model was generated with eight clinical inputs and a single output. ANN's performance was compared with a logistic regression model created with the same inputs in terms of accuracy, sensitivity, specificity, and discriminability. The study population was composed of 2150 patients (679 males and 1471 females): 1432 in the training group and 718 new patients in the testing group. The ANN model that had eight neurons in the hidden layer had the highest accuracies among the four ANN models: 92.46 and 85.79% in both training and testing datasets, respectively. The areas under the receiver operating characteristic curves of the automatically selected ANN model for both datasets were 0.901 (95%CI=0.814-0.988) and 0.869 (95%CI=0.748-0.990), higher than the 0.745 (95%CI=0.612-0.879) and 0.728 (95%CI=0.595-0.862) of the logistic regression model. The ANN model can be used for predicting 1-year mortality in elderly patients with intertrochanteric fractures. It outperformed a logistic regression on multiple performance measures when given the same variables.

Acid-base disarrangement and gastric intramucosal acidosis predict outcome from major trauma / Desarranjo ácido-base e acidose gástrica intramucosal predizem desfecho de trauma grave

INTRODUCTION: This prospective non-interventional study intended to assess the prognostic value of gastric intramucosal acidosis in patients with severe trauma admitted to a medical/surgical ICU. METHODS: Gastric tonometer catheters were introduced to measure air PCO2 level (Tonocap device) in forty consecutive critically ill trauma patients. Gastric intramucosal pH, air PCO2 gradient, lactate and acid-base parameters were measured at admission and at 6, 12 and 24 h thereafter. RESULTS: The median age, mean APACHE II and SOFA scores were higher in nonsurvivors than in survivors (p<0.05). There were significant differences in the PCO2 gradient between survivors and nonsurvivors at 12 and 24 hours (10±7 vs. 24±19 mmHg, 13±16 vs. 29±25 mmHg; p<0.05). Gastric intramucosal pH values were lower in nonsurvivors than in survivors, on admission and after 12 or 24 hours (p<0.05). Arterial pH and bicarbonate were lower, lactate concentration higher, and base excess more negative in nonsurvivors. Prediction of outcome (mortality and MODS) at 24 hours of ICU assessed by their ROC curves was similar (p=NS). At 24 hours, air PCO2 gradient > 18 mmHg carried a relative risk of 4.6 for death, slightly higher than a HCO3 <20 mEq/L (RR=4.29) or base excess of <-2 mmol/L (RR=3.65). CONCLUSION: Bicarbonate, base deficit, lactate, gastric intramucosal pH and PCO2 gradient discriminate survivors from nonsurvivors of major trauma. A critical air PCO2 gradient carried the greatest relative risk for death at 24 hours of ICU. Inadequate regional blood flow as detected by a critical PCO2 gradient seems to contribute to morbidity and mortality of severe trauma patients.

INTRODUÇÃO: O objetivo deste estudo prospectivo, não-intervencionista, foi avaliar o valor prognóstico da acidose gástrica intramucosal em pacientes com trauma grave admitidos numa UTI. MÉTODOS: Cateteres tonométricos gástricos foram introduzidos para medir o nível de PCO2 aéreo em 40 pacientes traumatizados. O pH gástrico intramucosal, o gradiente de PCO2 aéreo, o lactato e os parâmetros ácido-base foram medidos na admissão e 6, 12 e 24 h após a admissão. RESULTADOS: A idade mediana, o APACHE II e os escores SOFA médios foram maiores nos não-sobreviventes que nos sobreviventes (p<0.05). Não houve diferenças significativas para o gradiente de PCO2 entre sobreviventes e não-sobreviventes após 12 e 24 horas (10±7 vs. 24±19 mmHg, 13±16 vs. 29±25 mmHg; P<0.05). Os valores de pH gástrico intramucosal foram menores nos não-sobreviventes que nos sobreviventes na admissão e após 12 ou 24 horas (P<0.05). O pH arterial e o bicarbonato foram menores, a concentração de lactato maior, o excesso de base mais negativo nos não-sobreviventes. Predição do desfecho (mortalidade e FMOS) nas 24 horas de UTI acessada pelas curvas ROC foi similar (p=NS). Nas 24 horas, um gradiente de PCO2 aéreo >18 mmHg acarretou um risco relativo de 4.6 para óbito, um pouco maior que um HCO3 <20 mEq/L (RR=4.29) ou um excesso de base <-2 mmol/L (RR=3.65). CONCLUSÃO: Bicarbonato, déficit de base, lactato, pH gástrico intramucosal e o gradiente de PCO2 discriminaram os sobreviventes dos não-sobreviventes de trauma. Um gradiente crítico de PCO2 aéreo acarretou o maior risco relativo para óbito após 24 horas de UTI. Fluxo sangüíneo regional inadequado detectado por um gradiente crítico de PCO2 parece contribuir para a morbidade e mortalidade de pacientes traumatizados graves.

Outcome Prediction of Inpatients with First Heamorrhagic Apoplexy / 中国康复理论与实践

@#Ninety- five cases(49 male .46 female)with first heamorrhagic cerebral apoplexy. fromOct.1 . 1992 to Dec.31 .1993. were analyzed.The Average age was58.9. Patients were divided intotwo groups. the self care and the non- self care. Ninteen variables which were supposed likely to be relatedto functional outcome were chosed from the admitted record of each patient and analyzed with mutltiple lo-gistic regression. Results showed that the major predictors of poor outcome are coma. incontinent and hemi-plegia at onset and abnormal blood urea nitrogen. pulmonary infection and bleeding amount more than 3 0ml at admitted.Cases older than 70 years.high blood presure longer than 20 years have a tendency of moredependence in functional abilities.Factors that do not predict outcome after heamorrhagic stroke are sex.days in the hospital,cormorbidities. as well as level of blood surgar and cholestral.EKG changes at admitted time.