PMPraharsha Mulpur

Praharsha Mulpur

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Praharsha Mulpur has a total of 75 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Technical Feasibility of a Multimodal Electro-Optical and Infrared Imaging Pipeline for Postoperative Wound Assessment After Total Knee Arthroplasty: Formative Evaluation Study

    by Tej S Ranade, Emily Hu, Kadambari Beelwar, Sandeep Boddeda, Praharsha Mulpur, Adarsh Annapareddy, A V Gurava Reddy

    Background: Early detection and monitoring of wound-related complications after total knee arthroplasty (TKA) are critical to optimize outcomes and preserve implants. Conventional postoperative monitoring relies on in-person assessment and patient-reported symptoms, which may delay recognition. Noncontact imaging acquired in the clinic or at home offers a potential route to earlier and more consistent assessment. Objective: This study aimed to evaluate the technical feasibility and performance of a multimodal AI system integrating electro-optical (EO) and infrared imaging for postoperative wound assessment following TKA and to explore clinical factors associated with early complications. Methods: We conducted a single-center prospective cohort study of 749 patients undergoing primary TKA. Patients underwent standardized multimodal data collection at scheduled postoperative visits. EO-based models localized surgical landmarks and segmented complication-oriented tissue states; a fine-tuned vision-language model provided protocol verification and contextual visual reasoning. EO landmarks mapped to thermal space via deterministic alignment, followed by infrared region-of-interest segmentation and thermal classification. Each module was evaluated on a defined held-out set. The thermal classifier was assessed out-of-fold under 5-fold cross-validation with folds grouped by patient, in knees imaged on postoperative day 14 or later. Discrimination for clinician-adjudicated infection-related complications served as the primary outcome. Comorbidities and baseline laboratory values were explored for associations with complications. Results: Among 749 patients, 26 (3.5%) had a clinician-adjudicated infection-related complication. On held-out evaluation, the EO landmark detector reached a sensitivity of 0.967 (95% CI 0.954-0.979) and positive predictive value of 0.955 (95% CI 0.940-0.970), and the wound-tissue segmentation model reached a sensitivity of 0.845 (95% CI 0.833-0.857) and positive predictive value of 0.759 (95% CI 0.744-0.772). Infrared region-of-interest extraction isolated the surgical field with a mean intersection-over-union of 0.985 (SD 0.008; 95% CI 0.984-0.986) across 178 held-out patients. The trained thermal classifier discriminated infected scans with an area under the receiver operating characteristic curve (AUROC) of 0.978 (95% CI 0.959-0.992) in out-of-fold, patient-grouped cross-validation. At a representative operating point, sensitivity was 0.808 (95% CI 0.65-0.92), specificity 0.974 (95% CI 0.96-0.99), positive predictive value 0.618 (95% CI 0.49-0.78), and negative predictive value 0.990 (95% CI 0.98-1.00). Exploratory analyses showed nominal associations of chronic kidney disease and diabetes mellitus with postoperative complications that did not remain significant after multiplicity correction. Conclusions: In this formative study, a multimodal EO and infrared imaging pipeline demonstrated technical feasibility for postoperative wound assessment following TKA, providing noncontact discrimination of infection-related complications that compared favorably with established adjuncts. This work provides proof-of-concept for multimodal imaging-based assessment and defines the technical requirements for the prospective, multicenter external validation needed to establish clinical utility.

  • Robotic-assisted versus conventional total hip arthroplasty: a three-year comparative analysis of patient-reported outcomes and complications

    by Adarsh Annapareddy, Tarun Jayakumar, Vijay Krishna Adusumalli, Praharsha Mulpur, Vemaganti Badri Narayana Prasad, Mujtaba Ansari, A V Gurava Reddy


  • Jumbo Acetabular Cup in the Indian Population: Is It Time to Reconsider Existing Thresholds?

    by Akshaya Gadekar, Adarsh Annapareddy, Tarun Jayakumar, Praharsha Mulpur, Raja Bhaskara Rajasekaran, Ravikumar Mukartihal, Sharan S. Patil, Vijay C. Bose, Shanmuganathan Rajasekaran, A V Gurava Reddy

  • Open Access

    Technical Feasibility of a Multimodal Electro-Optical and Infrared Imaging Pipeline for Postoperative Wound Assessment After Total Knee Arthroplasty: Formative Evaluation Study (Preprint)

    by Tej S Ranade, Emily Hu, Kadambari Beelwar, Sandeep Boddeda, Praharsha Mulpur, Adarsh Annapareddy, A V Gurava Reddy

    BACKGROUND Early detection and monitoring of wound-related complications after total knee arthroplasty (TKA) are critical to optimize outcomes and preserve implants. Conventional postoperative monitoring relies on in-person assessment and patient-reported symptoms, which may delay recognition. Noncontact imaging acquired in the clinic or at home offers a potential route to earlier and more consistent assessment. OBJECTIVE This study aimed to evaluate the technical feasibility and performance of a multimodal AI system integrating electro-optical (EO) and infrared imaging for postoperative wound assessment following TKA and to explore clinical factors associated with early complications. METHODS We conducted a single-center prospective cohort study of 749 patients undergoing primary TKA. Patients underwent standardized multimodal data collection at scheduled postoperative visits. EO-based models localized surgical landmarks and segmented complication-oriented tissue states; a fine-tuned vision-language model provided protocol verification and contextual visual reasoning. EO landmarks mapped to thermal space via deterministic alignment, followed by infrared region-of-interest segmentation and thermal classification. Each module was evaluated on a defined held-out set. The thermal classifier was assessed out-of-fold under 5-fold cross-validation with folds grouped by patient, in knees imaged on postoperative day 14 or later. Discrimination for clinician-adjudicated infection-related complications served as the primary outcome. Comorbidities and baseline laboratory values were explored for associations with complications. RESULTS Among 749 patients, 26 (3.5%) had a clinician-adjudicated infection-related complication. On held-out evaluation, the EO landmark detector reached a sensitivity of 0.967 (95% CI 0.954-0.979) and positive predictive value of 0.955 (95% CI 0.940-0.970), and the wound-tissue segmentation model reached a sensitivity of 0.845 (95% CI 0.833-0.857) and positive predictive value of 0.759 (95% CI 0.744-0.772). Infrared region-of-interest extraction isolated the surgical field with a mean intersection-over-union of 0.985 (SD 0.008; 95% CI 0.984-0.986) across 178 held-out patients. The trained thermal classifier discriminated infected scans with an area under the receiver operating characteristic curve (AUROC) of 0.978 (95% CI 0.959-0.992) in out-of-fold, patient-grouped cross-validation. At a representative operating point, sensitivity was 0.808 (95% CI 0.65-0.92), specificity 0.974 (95% CI 0.96-0.99), positive predictive value 0.618 (95% CI 0.49-0.78), and negative predictive value 0.990 (95% CI 0.98-1.00). Exploratory analyses showed nominal associations of chronic kidney disease and diabetes mellitus with postoperative complications that did not remain significant after multiplicity correction. CONCLUSIONS In this formative study, a multimodal EO and infrared imaging pipeline demonstrated technical feasibility for postoperative wound assessment following TKA, providing noncontact discrimination of infection-related complications that compared favorably with established adjuncts. This work provides proof-of-concept for multimodal imaging-based assessment and defines the technical requirements for the prospective, multicenter external validation needed to establish clinical utility.

  • Enhanced and express workflows in robotic total hip arthroplasty: A paired accuracy study using radiographic validation

    by Adarsh Annapareddy, Praharsha Mulpur, Tarun Jayakumar, Dhruv Paul, Vemaganti Badri Narayana Prasad, A. V. Gurava Reddy

  • Robotic-arm assisted total hip arthroplasty correlates with superior acetabular bone preservation: a cup-to-head ratio and volumetric analysis

    by Adarsh Annapareddy, Praharsha Mulpur, Tarun Jayakumar, Mujtaba Ansari, Vemaganti Badri Narayana Prasad, A. V. Gurava Reddy


  • Enhanced Bone Healing in Tibial Osteogenesis Using the Distraction Holiday Protocol in Ilizarov Fixation

    by Pappu Rajasekhar, Tarun Jayakumar, Praharsha Mulpur, Rajeev Reddy Kikkuri, A. V. Gurava Reddy

  • Open Access

    Clinical Audit of Hip Fracture Management in Elderly Patients (Aged 70 Years and Above): A Focus on Improving Standards of Care

    by Praharsha Mulpur, Sachin Chidrawar, G. V. Subramaniam, Kamalakar Rao Rachakonda, Harsha Takkalapally, Annapareddy Venkata Guravareddy

    Background: Hip fractures in the elderly constitute a significant public health burden in India, with reported in-hospital mortality of 3.8% and morbidity rates of up to 40%. The concept of comprehensive orthogeriatric care is largely absent across India, particularly in rural and semi-urban settings, where management remains predominantly fracture-centric. This gap is compounded by the catastrophic out-of-pocket healthcare cost burden faced by patients in low- and middle-income countries, a critical shortage of trained geriatric and rehabilitation personnel, and the near-total absence of dedicated orthogeriatric infrastructure. This audit evaluates compliance with evidence-based care standards at a Level 1 trauma center in Hyderabad and highlights the urgent need for a nationally coordinated orthogeriatric care framework in India. Materials and Methods: A retrospective clinical audit was conducted on 86 patients aged 70 years and above who sustained a hip fracture and were admitted to Sunshine Hospitals, Secunderabad, between January 1 and December 31, 2022. Key audit parameters included time to admission, pain assessment, comorbidity optimization, time to surgery, early mobilization, nutritional and cognitive assessment, bone mineral density (BMD) evaluation, and fall prevention measures. Results: The mean patient age was 77.4 years (range 70–90 years); 56 of 86 patients were female. All 86 patients received analgesics on admission; however, formal pain documentation was inconsistent. Only 52% underwent surgery within 48 h of admission, 31% within 72 h, and 17% beyond 72 h. Comorbidities were present in 84% of patients (20% with one, 64% with two or more). BMD assessment was not performed in any patient. Fall risk assessment was not documented in any case. Significant gaps were identified in the documentation of cognitive function, prefracture ambulatory status, and the cause of the fall. Conclusion: Management of hip fractures in the elderly requires a coordinated multidisciplinary orthogeriatric approach that goes beyond fracture fixation. Critically, the deficiencies identified in this audit were observed at a Level 1 trauma center with substantial resources, underscoring the scale of the problem at district and rural hospitals across India. There is an urgent need for national-level awareness and policy action to establish comprehensive orthogeriatric care as the standard of practice in India, to improve the quality of life and reduce preventable mortality in this population. Comprehensive orthogeriatric care is the need of the hour.

  • Impact of femoral component flexion on gap balancing in varus knees using robotic technology: a comparative study of single-radius and multi-radius designs

    by Ratnakar Vecham, Paramanantham Madhavan, Tarun Jayakumar, Kishore Karumuri, Praharsha Mulpur, Adarsh Annapareddy, A. V. Gurava Reddy

    Accurate flexion–extension gap balancing is critical in total knee arthroplasty (TKA), influencing postoperative stability and longevity. Femoral component flexion in the sagittal plane has been suggested as a means to adjust gap balance; however, its impact across different implant designs remains unclear. This study compares the influence of femoral component flexion on gap balancing between single-radius and multi-radius femoral components using robotic-assisted TKA. A prospective observational cohort study was conducted on 200 patients (100 in each cohort) undergoing primary robotic-assisted TKA for varus deformity with end-stage osteoarthritis. Patients were randomized to receive either single-radius (Stryker MAKO with Stryker Triathlon implants) or multi-radius (Meril CUVIS with Maxx-Freedom implants) femoral components. Intraoperative medial and lateral flexion–extension gaps were assessed at femoral flexion increments from 0° to 6° using robotic measurement software, and statistical analyses were done. Femoral component flexion had distinct impacts on gap balancing depending on implant design. Multi-radius implants showed significant variability with extension medial gaps progressively loosened (mean Change 0.19 mm/degree of flexion, p < 0.001), and flexion medial and lateral gaps progressively tightened (mean Changes 0.21 mm/degree, p < 0.001 and 0.24 mm/degree, p < 0.05, respectively). Conversely, single-radius implants demonstrated minimal variability in all gap measurements across degrees of femoral flexion (p > 0.05). Femoral component flexion significantly affects gap balancing during robotic-assisted TKA, particularly in multi-radius femoral components. Multi-radius designs require careful sagittal alignment to prevent undesirable gap variations, whereas single-radius implants exhibit more predictable gap balancing profiles, potentially simplifying intraoperative adjustments. Future research should evaluate long-term clinical outcomes related to these findings.


  • Sleep quality after total knee arthroplasty: a comparative analysis of robotic-assisted and conventional techniques

    by A. B. Suhas Masilamani, Tarun Jayakumar, Praharsha Mulpur, Rajeev Reddy Kikkuri, Shravya Vaddiparthi, A. V. Gurava Reddy

    Total knee arthroplasty (TKA) significantly alleviates pain and improves functionality in patients with end-stage knee osteoarthritis. However, postoperative sleep disturbances remain a common issue affecting quality of life (QOL) and rehabilitation. This study aimed to compare postoperative sleep quality between robotic-assisted TKA (RATKA) and conventional TKA (CTKA). This observational study enrolled 200 consecutive patients undergoing primary unilateral TKA, divided equally into RATKA and CTKA cohorts. All surgeries were performed by a single surgeon using cemented TKA, either conventionally or with the MAKO® robotic system. Standardized pain management and rehabilitation protocols were followed in both cohorts. Preoperative and postoperative sleep quality were evaluated weekly for the first month and subsequently at 3 and 6 months post-operatively, utilizing the Pittsburgh Sleep Quality Index (PSQI). Pain scores were recorded using the Visual Analog Scale (VAS). Preoperative PSQI scores showed no significant differences between the RATKA (5.55 ± 2.05) and conventional TKA (5.70 ± 2.26) groups. Postoperative sleep disturbances peaked at 1 week post-surgery in both cohorts (RATKA: 12.42 ± 1.75, TKA: 12.59 ± 2.42), with gradual improvement observed over 6 months, although baseline sleep quality was not fully restored. Pain scores (VAS) were significantly lower in the RATKA cohort at all postoperative intervals (p < 0.001). No significant correlation was found between sleep quality and age, BMI, gender, or surgical approach. Both RATKA and conventional TKA resulted in similar patterns of postoperative sleep disturbances, peaking shortly after surgery and progressively improving over 6 months without fully returning to pre-operative levels. Despite significantly better pain control in the RATKA cohort, postoperative sleep quality did not differ significantly between the two surgical techniques. Future research should explore comprehensive perioperative management strategies to address the multifactorial nature of sleep disturbances post-TKA.