Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Rakshit Shah has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Readability, Accuracy, and Lexical Diversity of New ChatGPT Models for Common Carpal Tunnel Syndrome Questions

    by Romir P. Parmar, Sohail R. Daulat, Rakshit Shah, Tyler T. Brady, Michael Montague, Cameron Roth

    Background: Carpal tunnel syndrome (CTS) is a prevalent neuropathy in hand surgery that significantly affects people’s quality of life. Frequently, patients conduct research online before seeking medical care. Large language models (LLMs) like ChatGPT are increasingly used for health information, yet concerns remain regarding the accuracy, readability, and complexity of their responses. Previous studies have assessed older ChatGPT models but have not comprehensively compared newer versions. The purpose of this study is to compare ChatGPT-4-generated, ChatGPT-4o-generated, and ChatGPT-o1-generated answers to common CTS-related patient questions. Methods: Six frequently asked CTS questions were queried of each LLM. Responses were independently graded by 2 board-certified hand surgeons using evidence-based guidelines. Lexical diversity was assessed using the Measure of Textual Lexical Diversity, and readability was evaluated using the Flesch-Kincaid Grade Level, Flesch Reading Ease Score, and Simple Measure of Gobbledygook. Analysis of variance or Kruskal-Wallis with post hoc tests were conducted to compare LLMs and questions. Results: All 3 ChatGPT models averaged 93% accuracy with no significant differences between them, though a significant difference in accuracy was observed between questions 3 and 5. Readability scores between models varied significantly, with ChatGPT-4o generating the most readable responses and ChatGPT-o1 producing the most complex answers. Conclusions: While LLMs had similar accuracy, ChatGPT-4o offered the most patient-friendly content. Furthermore, the readability of all models remains above the recommended level for the general population. Future work should explore whether fine-tuning or advancements in model design can enhance accessibility for a broader audience.


  • Open Access

    Applications of Brain-Computer Interface in Action Observation and Motor Imagery

    by Rakshit Shah, Sohail Daulat, Vadivelan Ramu, Viashen Moodley, Puja Sengupta, Deepa Madathil, Yifei Yao, Kishor Lakshminarayanan

    Motor imagery (MI) and action observation (AO) are vital elements in brain-computer interface (BCI) applications. MI involves mentally simulating movements and physical execution, while AO involves observing others perform actions. Both activate crucial brain areas linked to movement, making them valuable for BCI-assisted motor rehabilitation. This chapter explores studies in sports, occupational therapy, and neurorehabilitation, focusing on combining AO and MI (AO + MI) in BCI applications. Results show the positive impact of AO + MI interventions on motor performance aspects such as imagery ability, reaction time, and muscle activation across various tasks. The fusion of virtual reality (VR) with MI proves potent in neurorehabilitation, especially in stroke and Parkinson’s disease rehab and cognitive enhancement. Additionally, VR-based AO combined with kinesthetic motor imagery (KMI) influences cortical activity, refining brain patterns and task performance. These findings suggest that combining VR-based action observation with KMI can significantly enhance BCI-assisted motor rehabilitation for individuals with motor deficits. This approach holds promise for improving motor control and fostering neuroplasticity.


  • Open Access

    Feasibility and usability of a virtual-reality-based sensorimotor activation apparatus for carpal tunnel syndrome patients

    by Kishor Lakshminarayanan, Rakshit Shah, Sohail R. Daulat, Viashen Moodley, Yifei Yao, Srignana Lokesh Ezhil, Vadivelan Ramu, Puja Sengupta, Deepa Madathil

    This study aimed to assess the usability of a virtual reality-assisted sensorimotor activation (VRSMA) apparatus for individual digit rehabilitation. The study had two main objectives: Firstly, to collect preliminary data on the expectations and preferences of patients with carpal tunnel syndrome (CTS) regarding virtual reality (VR) and an apparatus-assisted therapy for their affected digits. Secondly, to evaluate the usability of the VRSMA apparatus that was developed. The VRSMA system consists of an apparatus that provides sensory and motor stimulation via a vibratory motor and pressure sensor attached to a button, and a virtual reality-based visual cue provided by texts overlaid on top of a 3D model of a hand. The study involved 10 CTS patients who completed five blocks of VRSMA with their affected hand, with each block corresponding to the five digits. The patients were asked to complete a user expectations questionnaire before experiencing the VRSMA, and a user evaluation questionnaire after completing the VRSMA. Expectations for VRSMA were obtained from the questionnaire results using a House of Quality (HoQ) analysis. In the survey for expectations, participants rated certain attributes as important for a rehabilitation device for CTS, with mean ratings above 4 for attributes such as ease of use, ease of understanding, motivation, and improvement of hand function based on clinical evidence. The level of immersion and an interesting rehabilitation regime received lower ratings, with mean ratings above 3.5. The survey evaluating VRSMA showed that the current prototype was overall satisfactory with a mean rating of 3.9 out of 5. Based on the HoQ matrix, the highest priority for development of the VRSMA was to enhance device comfort and usage time. This was followed by the need to perform more clinical studies to provide evidence of the efficacy of the VRSMA. Other technical characteristics, such as VRSMA content and device reliability, had lower priority scores. The current study presents a potential for an individual digit sensorimotor rehabilitation device that is well-liked by CTS patients.


  • The Effects of Subthreshold Vibratory Noise on Cortical Activity During Motor Imagery

    by Kishor Lakshminarayanan, Rakshit Shah, Yifei Yao, Deepa Madathil

    Previous studies have demonstrated that both visual and proprioceptive feedback play vital roles in mental practice of movements. Tactile sensation has been shown to improve with peripheral sensory stimulation via imperceptible vibratory noise by stimulating the sensorimotor cortex. With both proprioception and tactile sensation sharing the same population of posterior parietal neurons encoding within high-level spatial representations, the effect of imperceptible vibratory noise on motor imagery-based brain–computer interface is unknown. The objective of this study was to investigate the effects of this sensory stimulation via imperceptible vibratory noise applied to the index fingertip in improving motor imagery–based brain–computer interface performance. Fifteen healthy adults (nine males and six females) were studied. Each subject performed three motor imagery tasks, namely drinking, grabbing, and flexion–extension of the wrist, with and without sensory stimulation while being presented a rich immersive visual scenario through a virtual reality headset. Results showed that vibratory noise increased event-related desynchronization during motor imagery compared with no vibration. Furthermore, the task classification percentage was higher with vibration when the tasks were discriminated using a machine learning algorithm. In conclusion, subthreshold random frequency vibration affected motor imagery–related event-related desynchronization and improved task classification performance.


  • Open Access

    The effect of combining action observation in virtual reality with kinesthetic motor imagery on cortical activity

    by Kishor Lakshminarayanan, Rakshit Shah, Sohail R. Daulat, Viashen Moodley, Yifei Yao, Deepa Madathil

    Introduction: In the past, various techniques have been used to improve motor imagery (MI), such as immersive virtual-reality (VR) and kinesthetic rehearsal. While electroencephalography (EEG) has been used to study the differences in brain activity between VR-based action observation and kinesthetic motor imagery (KMI), there has been no investigation into their combined effect. Prior research has demonstrated that VR-based action observation can enhance MI by providing both visual information and embodiment, which is the perception of oneself as part of the observed entity. Additionally, KMI has been found to produce similar brain activity to physically performing a task. Therefore, we hypothesized that utilizing VR to offer an immersive visual scenario for action observation while participants performed kinesthetic motor imagery would significantly improve cortical activity related to MI.Methods: In this study, 15 participants (9 male, 6 female) performed kinesthetic motor imagery of three hand tasks (drinking, wrist flexion-extension, and grabbing) both with and without VR-based action observation.Results: Our results indicate that combining VR-based action observation with KMI enhances brain rhythmic patterns and provides better task differentiation compared to KMI without action observation.Discussion: These findings suggest that using VR-based action observation alongside kinesthetic motor imagery can improve motor imagery performance.


  • Open Access

    Evaluation of EEG Oscillatory Patterns and Classification of Compound Limb Tactile Imagery

    by Kishor Lakshminarayanan, Rakshit Shah, Sohail R. Daulat, Viashen Moodley, Yifei Yao, Puja Sengupta, Vadivelan Ramu, Deepa Madathil

    Objective: The purpose of this study was to investigate the cortical activity and digit classification performance during tactile imagery (TI) of a vibratory stimulus at the index, middle, and thumb digits within the left hand in healthy individuals. Furthermore, the cortical activities and classification performance of the compound TI were compared with similar compound motor imagery (MI) with the same digits as TI in the same subjects. Methods: Twelve healthy right-handed adults with no history of upper limb injury, musculoskeletal condition, or neurological disorder participated in the study. The study evaluated the event-related desynchronization (ERD) response and brain–computer interface (BCI) classification performance on discriminating between the digits in the left-hand during the imagery of vibrotactile stimuli to either the index, middle, or thumb finger pads for TI and while performing a motor activity with the same digits for MI. A supervised machine learning technique was applied to discriminate between the digits within the same given limb for both imagery conditions. Results: Both TI and MI exhibited similar patterns of ERD in the alpha and beta bands at the index, middle, and thumb digits within the left hand. While TI had significantly lower ERD for all three digits in both bands, the classification performance of TI-based BCI (77.74 ± 6.98%) was found to be similar to the MI-based BCI (78.36 ± 5.38%). Conclusions: The results of this study suggest that compound tactile imagery can be a viable alternative to MI for BCI classification. The study contributes to the growing body of evidence supporting the use of TI in BCI applications, and future research can build on this work to explore the potential of TI-based BCI for motor rehabilitation and the control of external devices.


  • Open Access

    The Effect of Tactile Imagery Training on Reaction Time in Healthy Participants

    by Kishor Lakshminarayanan, Vadivelan Ramu, Janaane Rajendran, Kamala Prasanna Chandrasekaran, Rakshit Shah, Sohail R. Daulat, Viashen Moodley, Deepa Madathil

    Background: Reaction time is an important measure of sensorimotor performance and coordination and has been shown to improve with training. Various training methods have been employed in the past to improve reaction time. Tactile imagery (TI) is a method of mentally simulating a tactile sensation and has been used in brain–computer interface applications. However, it is yet unknown whether TI can have a learning effect and improve reaction time. Objective: The purpose of this study was to investigate the effect of TI on reaction time in healthy participants. Methods: We examined the reaction time to vibratory stimuli before and after a TI training session in an experimental group and compared the change in reaction time post-training with pre-training in the experimental group as well as the reaction time in a control group. A follow-up evaluation of reaction time was also conducted. Results: The results showed that TI training significantly improved reaction time after TI compared with before TI by approximately 25% (pre-TI right-hand mean ± SD: 456.62 ± 124.26 ms, pre-TI left-hand mean ± SD: 448.82 ± 124.50 ms, post-TI right-hand mean ± SD: 340.32 ± 65.59 ms, post-TI left-hand mean ± SD: 335.52 ± 59.01 ms). Furthermore, post-training reaction time showed significant reduction compared with the control group and the improved reaction time had a lasting effect even after four weeks post-training. Conclusion: These findings indicate that TI training may serve as an alternate imagery strategy for improving reaction time without the need for physical practice.


  • Three-Dimensional Carpal Arch Morphology Using Robot-Assisted Ultrasonography

    by Rakshit Shah, Zong-Ming Li

    Objective: The morphology of the carpal arch implicates the available space for the median nerve within the carpal tunnel. The purposes of this study were to 1) reconstruct the three-dimensional (3D) carpal arch by robot-assisted ultrasonography with a linear array transducer using cadaveric hands, and 2) investigate the 3D morphological properties of the carpal arch. Methods: An ultrasound probe with two-dimensional (2D) linear array was integrated on a robotic arm and maneuvered over the cadaveric carpal tunnels to scan the entire transverse carpal ligament and its osseous attachments to carpal bones. The acquired series of 2D ultrasound images together with robot positioning were utilized to reconstruct the 3D carpal arch for morphometric analyses. Results: Total carpal arch volume was 1099.4 ± 163.2 mm 3 with the distal, middle, and proximal regions contributing 18.2 ± 1.5%, 32.7 ± 1.2%, and 49.1 ± 2.3%, respectively. The ligament surface area was 420.1 ± 63.9 mm 2 . The carpal arch width, height, curvature, length, area, and palmar bowing index progressively increased from the distal to proximal locations within the tunnel (p < 0.01). Conclusion: The incorporation of the robot technology with the ultrasound system advanced the applications of traditional 2D ultrasound imaging for a 3D carpal arch reconstruction, allowing for comprehensive morphological assessment of the carpal arch. Significance: The developed workflow can be used for the reconstruction and analysis of other anatomical features in vivo.


  • Median nerve and carpal arch morphology changes in women with type 2 diabetes: a case–control study

    by Kishor Lakshminarayanan, Rakshit Shah

    Background The aim of this study is to investigate the changes in median nerve and transverse carpal ligament (TCL)-formed carpal arch morphology as possible risk factors for median nerve entrapment in women with type 2 diabetes. Methods The distal carpal tunnel was imaged using ultrasound in 30 female subjects (15 with type 2 diabetes, 15 controls). The morphological parameters of the median nerve and carpal arch were derived from the ultrasound images. One-way analysis of variance (ANOVA) was used for statistical analysis. Results Diabetic women had an enlarged median nerve area (p < 0.05), salong with a maller carpal arch size, as indicated by a reduced palmar bowing index of the TCL (p < 0.05), and arch area (p < 0.05) than controls. The distance from the median nerve centroid to the volar boundary of the TCL was reduced in diabetic women (p < 0.05) compared to the controls. Conclusions Women with type 2 diabetes have reduced available space for the median nerve within the carpal arch due to the enlarged nerve and reduced arch size, making the median nerve more susceptible to entrapment within the tunnel. The current study shows that presence of diabetes increases the risk of median nerve entrapment in women and requires early detection of symptoms to avoid carpal tunnel syndrome.


  • Ligament and Bone Arch Partition of the Carpal Tunnel by Three-Dimensional Ultrasonography

    by Rakshit Shah, Zong-Ming Li

    The carpal tunnel is geometrically irregular due to the complex composition of many carpal bones intercalated by numerous intercarpal ligaments. The purpose of the study was to investigate the relative contributions of the ligament and bone arches to carpal tunnel space at the proximal, middle, and distal tunnel regions. A catheter ultrasound probe acquired fan-like images inside cadaveric carpal tunnels for three-dimensional reconstruction of the tunnel. The total tunnel volume was 5367.6 ± 940.1 mm3 with contributions of 12.0%, 6.9%, and 4.1% by proximal, middle, and distal ligament arches, respectively, and 27.0%, 25.3%, and 24.7% by proximal, middle, and distal bone arches, respectively. The bone arch occupied more tunnel space than the ligament arch at all regions (p < 0.05). The ligament arch was largest at the proximal region of the tunnel and significantly decreased toward the distal region (p < 0.05). However, the bone arch significantly decreased only from the proximal to middle region (p < 0.05) but not from the middle to distal region (p = 0.311). Consequently, it was observed that the ligament arch was the key contributor to the unequal carpal tunnel space across regions. Partitional and regional tunnel morphometric information may provide a better understanding of tunnel abnormality associated with various wrist pathological conditions. The developed framework of ultrasonography and data processing can be applied to other areas of interest in the musculoskeletal system.