MKMohammed Khattak

Mohammed Khattak

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

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


Mohammed Khattak has a total of 33 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Navigating the barriers and facilitators to implementation of AI in healthcare

    by Mohammed Khattak, James S. Bowness, Rusul Yonis, Patrick Kierkegaard, Alison McGregor, Daniel C. Perry

    Aims: There is increasing emphasis on applying AI techniques to enhance healthcare delivery and decision-making. However, despite much interest and early promise, a major challenge is translation into clinical practice. To address the challenges of AI deployment, optimize implementation, and establish strategies for effective utilization of AI technology in healthcare, we aimed to answer the question: what are the key determinants influencing effective deployment of AI technology in healthcare?Methods: We followed PRISMA-ScR and the Joanna Briggs Institute Methodology guidelines for scoping reviews; the research protocol was published prospectively on Open Science Framework. We searched PubMed, Cochrane, Ovid MEDLINE, Scopus, and IEEE Xplore for papers published in English from 2000, including systematic/scoping reviews and meta-analyses with full text available.Results: The initial search was limited to AI medical imaging technology. It identified 1,511 papers, of which 523 met the eligibility criteria based on title and abstract screening. A total of 488 papers were excluded due to context or irrelevant content, leaving 35 papers for full-text review. No systematic/scoping reviews specifically addressing the deployment of AI medical imaging solutions were identified, prompting the inclusion criteria to be broadened to encompass any study designs related to all relevant technology. Overall, 15 papers were included in the final scoping review.Conclusion: The successful deployment of AI in healthcare is challenging, due to barriers which can be ethical, technological, regulatory, financial, or patient- and workforce-related. Facilitators to drive successful implementation include planning, organizational culture, patient involvement, stakeholder engagement, education, and leadership. Leveraging these essential barriers and facilitators provides a foundation for developing implementation strategies that streamline the deployment of AI technology in healthcare.Cite this article: Bone Joint J 2025;107-B(7):666–672.


  • Bridging innovation to implementation in artificial intelligence fracture detection

    by Mohammed Khattak, Patrick Kierkegaard, Alison McGregor, Daniel C Perry

    The deployment of AI in medical imaging, particularly in areas such as fracture detection, represents a transformative advancement in orthopaedic care. AI-driven systems, leveraging deep-learning algorithms, promise to enhance diagnostic accuracy, reduce variability, and streamline workflows by analyzing radiograph images swiftly and accurately. Despite these potential benefits, the integration of AI into clinical settings faces substantial barriers, including slow adoption across health systems, technical challenges, and a major lag between technology development and clinical implementation. This commentary explores the role of AI in healthcare, highlighting its potential to enhance patient outcomes through more accurate and timely diagnoses. It addresses the necessity of bridging the gap between AI innovation and practical application. It also emphasizes the importance of implementation science in effectively integrating AI technologies into healthcare systems, using frameworks such as the Consolidated Framework for Implementation Research and the Knowledge-to-Action Cycle to guide this process. We call for a structured approach to address the challenges of deploying AI in clinical settings, ensuring that AI’s benefits translate into improved healthcare delivery and patient care.Cite this article: Bone Joint J 2025;107-B(6):582–586.


  • Open Access

    Automating radiological measurements of the hip in children with cerebral palsy

    by Peter Thompson, Mohammed Khattak, P. J. Joseph, Daniel C. Perry, Timothy F. Cootes, Claudia Lindner

    Aims: The aims of this study were to develop an automatic system capable of calculating four radiological measurements used in the diagnosis and monitoring of cerebral palsy (CP)-related hip disease, and to demonstrate that these measurements are sufficiently accurate to be used in clinical practice.Methods: We developed a machine-learning system to automatically measure Reimer’s migration percentage (RMP), acetabular index (ACI), head shaft angle (HSA), and neck shaft angle (NSA). The system automatically locates points around the femoral head and acetabulum on pelvic radiographs, and uses these to calculate measurements. The system was evaluated on 1,650 pelvic radiographs of children with CP (682 females and 968 males, mean age 8.3 years (SD 4.5)). Each radiograph was manually measured by five clinical experts. Agreement between the manual clinical measurements and the automatic system was assessed by mean absolute deviation (MAD) from the mean manual measurement, type 1 and type 2 intraclass correlation coefficients (ICCs), and a linear mixed-effects model (LMM) for assessing bias.Results: The MAD scores were 5.7% (SD 8.5%) for RMP, 4.3° (SD 5.4°) for ACI, 5.0° (SD 5.2°) for NSA, and 5.7° (SD 6.1°) for HSA. Overall ICCs quantifying the agreement between the mean manual measurement and the automatic results were 0.91 for RMP, 0.66 for ACI, 0.85 for NSA, and 0.73 for HSA. The LMM showed no statistically significant bias.Conclusion: The results showed excellent agreement between the manual and automatic measurements for RMP, good agreement for NSA, and moderate agreement for HSA and ACI. The performance of the system is sufficient for application in clinical practice to support the assessment of hip migration based on RMP. The system has the potential to save clinicians time and to improve patient care by enabling more comprehensive, consistent, and reliable monitoring of hip migration in children with CP.Cite this article: Bone Joint J 2025;107-B(1):124–132.


  • Open Access

    Moyamoya phenomenon following clipping of intracranial aneurysm: case report

    by Masna B Inam, Ali Bakhsh, Mohammed Khattak, Arun Chandran, Jawad Yousaf

    Subarachnoid haemorrhage from aneurysmal rupture is a common emergency in neurosurgery. Depending on aneurysm position, morphology, size, associated clot, and symptoms, it is either managed by endovascular occlusion or by clipping. Here we report the first known case of secondary Moyamoya phenomenon following the clipping of a supraclinoid internal carotid artery Aneurysm. After making a complete recovery following clipping, this patient developed headaches 6 years later. Angiographic imaging revealing Moyamoya phenomenon characterized by total distal arterial occlusion and development of anastomotic collaterals. This phenomenon may be caused by neuroinflammation and suggests a tailored neuroimaging follow-up is required for such patients.

  • Open Access

    Artificial Intelligence Aided Ultrasound Detection of DDH: A Scoping Review Protocol

    by Rusul Yonis, Daniel Perry, James S Bowness, Mohammed Khattak, Natalie Hall

    Background Ultrasound imaging plays a pivotal role in the diagnosis and monitoring of developmental dysplasia of the hip (DDH). However, this step requires a formal referral to the radiology department for an ultrasound by an expert radiologist or sonographer. This process can delay diagnosis and treatment initiation due to long wait times caused by the high demand on NHS services. In recent years, there has been a growing interest in leveraging artificial intelligence (AI) in ultrasound imaging. AI has potential to assist in image acquisition and interpretation, to inform clinical decision-making. Further benefits may include improved accuracy, efficiency, and consistency in diagnosis, ultimately leading to better patient outcomes. This scoping review aims to review the evidence for AI to support ultrasound detection of DDH, including reviewing the methodologies employed, the accuracy and utility of algorithms, challenges and opportunities for clinical translation, and requirements for future research. Methods We will conduct a comprehensive search of the literature using multiple databases, including ACM Digital Library, EMBASE, OVID MEDLINE, PUBMED, COCHRANE Library, CINAHL, and IEEE Explore. These databases cover a wide range of academic disciplines, including computer science, and medical sciences, ensuring thorough coverage of relevant studies related to artificial intelligence (AI) in ultrasound for developmental dysplasia of the hip (DDH). In addition, we will explore the International Committee of Medical Journal Editors (ICMJE) approved clinical trial registries and the World Health Organization (WHO) clinical trials registry to identify ongoing or completed studies in this field. This will capture relevant research that may not yet be published in peer-reviewed journals. To supplement the research databases, we will search the websites of international societies in relevant fields, such as the British Society of Children’s Orthopaedic Surgery (BSCOS) and Paediatric Orthopaedic Society of North America (POSNA). As AI has a strong commercial interest, we will review product information and publicly available evidence from EXO Imaging (https://www.exo.inc), a commercial company with a known interest in this field and an established AI aided US device. Discussion This scoping review represents the first comprehensive attempt to gather the available evidence on the application of AI in ultrasound imaging for the diagnosis of DDH. By systematically reviewing and synthesizing a diverse range of studies, we aim to provide an overview of the current state of the art in this emerging field, identify gaps in the literature, and inform future research.


  • Open Access

    Radiological assessment of hip disease in children with cerebral palsy: development of a core measurement set

    by Prince J. S. Joseph, Mohammed Khattak, Sundas T. Masudi, Louise Minta, Daniel C. Perry

    Radiological assessment of hip disease in children with cerebral palsy: development of a core measurement set


  • Open Access

    Radiological hip shape and patient-reported outcome measures in healed Perthes’ disease

    by Mohammed S. Ali, Mohammed Khattak, David Metcalfe, Daniel C. Perry

    Aims: This study aimed to evaluate the relationship between hip shape and mid-term function in Perthes’ disease. It also explored whether the modified three-group Stulberg classification can offer similar prognostic information to the five-group system.Methods: A total of 136 individuals aged 12 years or older who had Perthes’ disease in childhood completed the Patient-Reported Outcomes Measurement Information System (PROMIS) Mobility score (function), Nonarthritic Hip Score (NAHS) (function), EuroQol five-dimension five-level questionnaire (EQ-5D-5L) score (quality of life), and the numeric rating scale for pain (NRS). The Stulberg class of the participants’ hip radiographs were evaluated by three fellowship-trained paediatric orthopaedic surgeons. Hip shape and Stulberg class were compared to PROM scores.Results: A spherical hip was associated with the highest function and quality of life, and lowest pain. Conversely, aspherical hips exhibited the lowest functional scores and highest pain. The association between worsening Stulberg class (i.e. greater deviation from sphericity) and worse outcome persisted after adjustment for age and sex in relation to PROMIS (predicted mean difference -1.77 (95% confidence interval (CI) -2.70 to -0.83)), NAHS (-5.68 (95% CI -8.45 to -2.90)), and NRS (0.61 (95% CI 0.14 to 1.08)), but not EQ-5D-5L (-0.03 (95% CI -0.72 to 0.11)).Conclusion: Patient-reported outcomes identify lower function, quality of life, and higher pain in aspherical hips. The magnitude of symptoms deteriorated with time. Hip sphericity (i.e. the modified three-group classification of spherical, oval, and aspherical) appeared to offer similar levels of detail to the five-group Stulberg classification.Cite this article: Bone Joint J 2023;105-B(6):711–716.


  • Open Access

    341 Alder Hey Experience of Paediatric Virtual Fracture Clinic During The COVID-19 Pandemic

    by L Stead, M Ashraf, S Gandham, M Khattak, C Talbot

    Introduction: The SARS-CoV2/COVID-19 pandemic represented an unprecedented emergency prompting a drive to minimise non-essential patient contact and the need for a virtual fracture clinic (VFC); an uncommon practice in paediatric units. Management of paediatric fractures requires a greater degree of vigilance to safeguard children. The current climate has created social challenges that theoretically increase the risk of harm and exploitation to children. This study investigates VFC in the management of paediatric fractures to determine the efficiency of such a process and the risk of safeguarding. Method: A protocol was devised in affiliation with BSCOS for the immediate management and streamlining of paediatric fractures into VFC. We retrospectively audited 235 VFC consults over a 1-month period. Patient sex was roughly evenly distributed, and age ranged from 9 months to 16 years (mean 8.4 years). Results: 42% of patients were recalled for a face-to-face (F2F) review (26% expedited), primarily for clinical assessment, plaster complaints and imaging requirements. 33% were discharged and 15% continued follow-up in VFC. All clavicle fractures were discharged. Forearm, hand, foot and elbow injuries were more likely to be discharged. Lower leg, upper arm and knee presentations more frequently required a F2F review. 2.3% of cases required safeguarding reviews. Conclusions: Given the rapid transition to VFC without the use of triage we have determined a number of non-complex fractures safely managed and discharged via VFC. The low percentage of recall due to safeguarding concern highlights this may not be a barrier to the continuation of virtual care outside of the context of a pandemic.

  • Kingella kingae septic arthritis

    by Mohammed Khattak, Sujith Vellathussery Chakkalakumbil, Robert A. Stevenson, David J. Bryson, Michael J. Reidy, Christopher L. Talbot, Harvey George

    Aims: The aim of this study was to determine the extent to which patient demographics, clinical presentation, and blood parameters vary in Kingella kingae septic arthritis when compared with those of other organisms, and whether this difference needs to be considered when assessing children in whom a diagnosis of septic arthritis is suspected. Methods: A prospective case series was undertaken at a single UK paediatric institution between October 2012 and November 2018 of all patients referred with suspected septic arthritis. We recorded the clinical, biochemical, and microbiological findings in all patients. Results: A total of 160 patients underwent arthrotomy for a presumed septic arthritis. Of these, no organism was identified in 61 and only 25 of these were both culture- and polymerase chain reaction (PCR)-negative. A total of 36 patients did not undergo PCR analysis. Of the remaining 99 culture- and PCR-positive patients, K. kingae was the most commonly isolated organism (42%, n = 42). The knee (n = 21), shoulder (n = 9), and hip (n = 5) were the three most commonly affected joints. A total of 28 cases (66%) of K. kingae infection were detected only on PCR. The mean age of K. kingae-positive cases (16.1 months) was significantly lower than that of those whose septic arthitis was due to other organisms (49.4 months; p < 0.001). The mean CRP was significantly lower in the K. kingae group than in the other organism group (p < 0.001). The mean ESR/CRP ratio was significantly higher in K. kingae (2.84) than in other infections (1.55; p < 0.008). The mean ESR and ESR/CRP were not significantly different from those in the 'no organism identified' group. Conclusion: K. kingae was the most commonly isolated organism from paediatric culture- and/or PCR-positive confirmed septic arthritis, with only one third of cases detected on routine cultures. It is important to develop and maintain a clinical suspicion for K. kingae infection in young patients presenting atypically. Routine PCR testing is recommended in these patients. Cite this article: Bone Joint J 2021;103-B(3):584–588.