AI in ECG: Validating an ambulatory semiology labeller and predictor.

OBJECTIVES: Early prediction of epileptic seizures can help reduce morbidity and mortality. In this work, we explore using electrocardiographic (ECG) signal as input to a seizure prediction system and note that the performance can be improved by using selected signal processing techniques. METHODS: We used frequency domain analysis with a deep neural network backend for all our experiments in this work. We further analysed the effect of the proposed system for different seizure semiologies and prediction horizons. We explored refining the signal using signal processing to enhance the system's performance. RESULTS: Our final system using the Temple University Hospital's Seizure (TUHSZ) corpus gave an overall prediction accuracy of 84.02 %, sensitivity of 87.59 %, specificity of 81.9 %, and an area under the receiver operating characteristic curve (AUROC) of 0.9112. Notably, these results surpassed the state-of-the-art outcomes reported using the TUHSZ database; all findings are statistically significant. We also validated our study using the Siena scalp EEG database. Using the frequency domain data, our baseline system gave a performance of 75.17 %, 79.17 %, 70.04 % and 0.82 for prediction accuracy, sensitivity, specificity and AUROC, respectively. After selecting the optimal frequency band of 0.8-15 Hz, we obtained a performance of 80.49 %, 89.51 %, 75.23 % and 0.89 for prediction accuracy, sensitivity, specificity and AUROC, respectively which is an improvement of 5.32 %, 10.34 %, 5.19 % and 0.08 for prediction accuracy, sensitivity, specificity and AUROC, respectively. CONCLUSIONS: The seizure information in ECG is concentrated in a narrow frequency band. Identifying and selecting that band can help improve the performance of seizure detection and prediction. SIGNIFICANCE: EEG is susceptible to artefacts and is not preferred in a low-cost ambulatory device. ECG can be used in wearable devices (like chest bands) and is feasible for developing a low-cost ambulatory device for seizure prediction. Early seizure prediction can provide patients and clinicians with the required alert to take necessary precautions and prevent a fatality, significantly improving the patient's quality of life.

Alberta Stroke Program Early CT Score can Predict Severity of Spasticity and Functional Outcome in Ischemic Stroke Survivors.

Background: Post-stroke spasticity is common and an early predictor of the severity of spasticity can help track recovery trajectory helping to modify rehabilitation plans. Objectives: We explored the utility of the Alberta Stroke Program Early CT Score (ASPECTS) to predict functional motor capacity in patients after acute ischemic stroke. Methods: One hundred and one patients (mean age of 58.6 ± 7.6 years; M:F = 72: 29) with the first documented acute ischemic stroke were followed up for three to twelve months after the stroke. Cerebral lesions within the territory of the middle cerebral artery were evaluated using the ASPECTS. Spasticity was assessed using the Modified Ashworth Score (MAS) and walking with Timed Up and Go test (TUG). The associations between severity of spasticity and size/extent of infarct as derived from ASPECTS and between spasticity and functional walking in post-stroke survivors were analyzed. Results: Among the patients studied, 61.3% (n = 62) had infarct in the region of supply of the left middle cerebral artery (MCA) and 38.7% (n = 39) had infarct in the region supplied by the right MCA. Three percent (n = 3) had a low ASPECTS, 53.6% (n = 54) had an intermediate score and 44.4% (n = 44) had a high score. The majority of patients with no to mild spasticity had high ASPECTS. Worse spasticity was significantly associated with low ASPECTS (P = 0.001). High scores in Timed Up and Go test (TUG) were associated with low ASPECTS (P < 0.001). Patients with high ASPECTS had the propensity to have subcortical infarcts (P < 0.001) when compared to those with moderate ASPECTS, who had a mix of cortical and subcortical infarcts. Conclusion: ASPECTS at admission in patients with acute ischemic stroke is a good predictor of post-stroke spasticity and functional walking. Low ASPECTS is associated with higher spasticity and lower functional walking status on follow-up after stroke.

Predictors of Co-activation in Erb's Palsy: A Retrospective Study.

Context: Three per thousand births have Erb's palsy. Spontaneous recovery is 50%. Co-activation yields poor outcomes. There are no objective indicators of its emergence. Aims: Analyze if 1 month Axon Viability Index (AVI) of the axillary nerve and which active movement score (AMS) measures can predict co-activation. Settings and Design: Tertiary level rehabilitation center, retrospective design. Methods and Material: The electronic medical record (EMR) was reviewed for patients with Erb's palsy with Narakas grade 2 lesions, as having co-activation or not. The one-month Axillary AVI was used with monthly AMS scores. The inclusion criteria were an AVI greater than ten percent. Exclusion criteria were bi-brachial palsy, congenital anomalies, concomitant or subsequent neurological injuries, and orthopedic injuries. Statistical Analysis Used: Descriptive statistics were used to calculate the median and interquartile values for AMS scores at each respective time point. Statistical significance for each time point was determined using a student's t-test. Results: Regarding the t-test on the AVI data, a significant P value of 0.001 was found favoring the co-activation group. AVI of the Axillary nerve between 0.1 and 0.5 at 1 month is a reliable indicator of future development of co-activation. The following were strong indicators of the emergence of co-activation respectively: month three Wrist Extension in sitting, Shoulder Abduction in supine, Shoulder Abduction in sitting, Elbow Flexion in sitting, month six Elbow Flexion in sitting, month seven Elbow Flexion in sitting. Conclusions: The axillary AVI at one month is a good predictor of future development of co-activation. The mentioned AMS items are the earliest indicators of co-activation.

Role of Artificial Intelligence and Machine Learning in the prediction of the pain: A scoping systematic review.

Artificial Intelligence in healthcare is growing quickly in diagnostics and treatment management. Despite the quantity and variety of studies its role in clinical care is not clear. To identify the evidence gaps and characteristics of the Artificial Intelligence and Machine Learning techniques in predicting/diagnosing the pain? Pubmed/Embase were searched from the inception to October 2021 for articles without any language restrictions specifically addressing the following: the accuracy of AI in pain considering Brain Imaging, Patient-reported measures, and Electrophysiology, the ability of AI to differentiate stratify severity/types of pain, the ability of AI to predict pain and lastly the most accurate AI technique for given inputs. All the included studies were on humans. Eight hundred forty abstracts were reviewed, and 23 articles were finally included. Identified records were independently screened and relevant data was extracted. We performed conceptual synthesis by grouping the studies using available concepts of AL/ML techniques in diagnosing pain. Then we summarized the number of features/physiological measurements. Structured tabulation synthesis was used to show patterns predictions along with a narrative commentary. A total of 23 articles, published between 2015 and 2020 from 12 countries were included. Most studies were experimental in design. The most common design was cross sectional. Chronic or acute pains were predicted more often. Compared to control, the pain prediction was in the range of 57%-96% by AI techniques. Support Vector Machine and deep learning showed higher accuracy for classifying pain. From this study, it can be inferred that AI/ML can be used to differentiate healthy controls from patients. It can also facilitate categorizing them into new and different clinical subgroups. Lastly, it can predict future pain. The limitations are with respect to studies done after the search period. AL/ ML has a supportive role in pain diagnostics.

A Comparison of Treatment Options in Focal Post-Stroke Spasticity of the Upper Extremity: A Prospective Longitudinal Cohort Study from Kerala, India.

Background: Post-stroke 20%-40% of patients develop spasticity which can quadruple total cost of care. This impact can be reduced by affordable treatment options for focal spasticity. Objectives: The primary objective of the study was to compare changes in Passive Range of Movements in patients with focal post-stroke spasticity from pre-treatment to end of 1 month of treatment with anti-spastic agents. The secondary objectives were to measure the changes in Modified Ashworth, and Brunnstrom Recovery Staging during the same period. Materials and Methods: This prospective longitudinal cohort study was conducted in a tertiary level rehabilitation center. One hundred and three adults with post-stroke spasticity participated. The patients received one of the four options: Phenol, Onabotulinum toxin, Bupivacaine and Hyaluronidase.The main outcome measures were the following: Changes in Passive Range of Movement (PRoM), Brunnstrom staging (BRS) and Modified Ashworth Scale (MAS). Result: Post intervention testing at 1 month was done. Each agent significantly improved BRS (1.10, 95% CI 0.8-1.4, P = 0.001) and PRoM (32.28, 95% CI 27.66- 36.89, P = 0.001), while reducing MAS (0.39, 95% CI 0.01-0.77, P = 0.05). In addition, subgroup comparisons were done with phenol as a reference for all three outcome measures. There was a significant difference in the improvement of Brunnstrom staging for Bupivacaine (0.52, 0.094-0.95, 0.02) compared to phenol. Similarly, Hyaluronidase showed better improvement in MAS (0.39, 0.01-0.77, 0.05) compared to Phenol. Conclusion: There was a significant difference in PRoM, MAS and Brunnstrom staging from baseline to end of 1 month long anti-spasticity treatment.

Hyperbaric oxygen therapy in patients with hypoxic ischemic encephalopathy.

BACKGROUND AND AIM: To assess the efficacy of hyperbaric oxygen therapy (HBOT) in patients with hypoxic ischemic encephalopathy (HIE). DESIGN: Non-randomized case-control observational study. SETTING: Tertiary level neurorehabilitation unit. POPULATION: Twenty-five patients with HIE seen between 1 to 12 months after the injury and having a coma recovery scale-revised (CRS-R) score less than 7 at entry were recruited. METHODS: Out of the patients who received HBOT, 20 received 20 sessions of HBOT at two absolute atmosphere pressure (ATA), and two received 60 sessions at 2 ATA over three different treatment intervals. We compared the outcomes between cases (who received HBOT) and controls (who did not receive HBOT).Cases and controls were allocated to three groups based on the time interval after injury following which they were recruited to the study: 1-3 months (9 cases and 16 controls), 4-8 months (9 cases and 9 controls) and 9-12 months (8 cases and 3 controls). OUTCOME MEASURES: CRS-R, Karnofsky performance scale, and change in disorder of consciousness (DOC) at admission and discharge were assessed. RESULTS: We observed a significant difference in CRS-R favoring the HBOT group at time intervals of 1-3 and 4-8 months. More patients in the HBOT group improved in DOC than the control group. CONCLUSIONS: HBOT given in the first nine months post-HIE can result in a better recovery and functional outcome.

Design, analysis and performance evaluation of a hand gesture platform for navigation.

Prevailing technological solutions that address the problems that are experienced by the infirm and elderly people in terms of locomotion needs, offer limited options when it comes to control mechanism and customization. For more than a decade, joysticks have served the purpose of steering and navigation of autonomous wheelchairs. An alternative gesture-based method for navigation of wheelchairs by the physically impaired could very well replace the conventional joystick controls. A prototype system, 'Mudra' (Sanskrit word for gesture), incorporates a gesture capture module, developed for recognition and identification of hand gestures. Mudra is a no-nonsense user-friendly system that enables control of the navigational platform, merely by four gestures of the human hand. This paper presents a comprehensive report on the implementation of the Mudra system's hardware and software, performance analysis and safety evaluation. Verification tests of the conceptual design show promising results, where 97.8% of the hand gestures were recognized accurately. Furthermore, the response timings of wheelchairs with Mudra controls were noticeably faster than the joystick-based wheelchairs, as affirmed by live testing with wheelchair-users. Pursuant to the positive feedback from the wheelchair-user experience, we conclude that Mudra's gesture controlled wheelchairs would be a preferable alternative to joystick-controlled wheelchairs.

A prospective study on the effects of Ayurvedic massage in post-stroke patients.

BACKGROUND: Few stroke patients have reported improvements after Ayurvedic massage. Unfortunately, there is a dearth of indexed literature to support the use of this in rehabilitation. OBJECTIVES: To objectively measure the differences between patients with stroke who received Ayurvedic massage in addition to standard Physiotherapy (PT) versus those who received only standard PT. MATERIALS AND METHODS: The study was a prospective case control study, retrospectively analysed. The setting was a tertiary level hospital with neuro-rehabilitation unit. Fifty-two patients undergoing acute inpatient rehabilitation were prospectively followed post stroke. They were self-selected one month from the event for Ayurvedic massage with regular PT or PT alone. Twenty five received Ayurvedic massage with PT and twenty seven received only PT. All participants completed treatment. Information related to age, gender, National Institute of Health Stroke Scale result, number of co-morbidities, and whether cases were deemed simple or complex were taken at baseline. All patients received 6 hours of physical therapy averaged over a week. Massage was delivered daily for a total of 10 sessions followed by steam application. RESULTS: Patients were categorized as simple or complicated stroke based on events prior to rehabilitation. Both simple and complicated patients who received Ayurvedic massage had lower MAS and need for antispastic drugs, achieved standing with minimal assistance sooner, and had better locomotion at discharge. All these differences were significant. CONCLUSION: Utilizing Ayurvedic massage in post stroke patients with flaccidity can promote faster standing with minimal assistance and lead to less need for antispastic drugs at discharge.

First two bilateral hand transplantations in India (Part 3): Rehabilitation and immediate outcome.

INTRODUCTION: This report covers the strategies adopted for rehabilitation for the first and second dual hand transplants performed in India. MATERIALS AND METHODS: The team, under a trained physiatrist, including physiotherapy and occupational therapy personnel, was involved in the management of both these patients. The management protocol was developed considering previous reports as well as our management strategies in the rehabilitation of the replanted hands. The involvement of the team with the patients started in the 1st week itself and continued on a daily basis for the entire year. RESULTS: Outcome analysis was performed at 6 months and 1 year using the disability of shoulder and hand evaluation and hand transplant scoring system. Functional magnetic resonance imaging was done at the end of 1 year to assess the cortical integration of the transplanted hand. CONCLUSION: Despite more than 110 hands being transplanted worldwide, hand transplant remains an experimental procedure. It is still not considered the "standard of care" for hand amputees. Outcome analyses performed worldwide do indicate that the procedure can provide a substantial improvement in the quality of life for the hand amputee, especially the bilateral amputees.

Congenital subaxial cervical subluxation presenting as a bilateral Erb's palsy: surgical management, rehabilitation, and outcome.

INTRODUCTION: Subaxial spine injuries during infancy are uncommon. CASE REPORT: We present the case of an infant referred to our brachial plexus clinic with proximal weakness of both arms noted immediately following a complicated breech delivery. Nerve conduction studies were consistent with bilateral proximal upper plexus injury; however, radiological evaluation revealed a C4-C5 subluxation and MRI features of bilateral C5 root avulsions. He was immobilized in a cervical-body orthosis and underwent open reduction and posterior C4-C5-C6 fixation at 10 weeks age using luque rods, sublaminar wires, and rib graft. The spine was immobilized in a custom molded cervicothoracic brace for a total of 3 months, and a home exercise program prescribed. Follow-up radiographic evaluation showed good posterior bony fusion by 2 months but persistent bilateral proximal upper limb weakness with reduced compound motor action potential (CMAP) amplitudes of the axillary and musculocutaneous nerves. Bilateral supraclavicular exploration and C5 root neurotization using the ipsilateral C7 nerve roots were performed at 7 months of age. Voluntary biceps activity followed by voluntary external rotation with gravity eliminated was noted within the next 2-3 months. He progressed to develop near normal motor control of bilateral upper limbs within 1 year. CONCLUSIONS: We wish to report this rare entity and our favorable outcome using a strategy of early spinal stabilization and neurotization repair to restore function following proximal nerve root injury.