Journal of Clinical Orthopaedics and Trauma 49 (2024) 102356

Contents lists available at ScienceDirect

Journal of Clinical Orthopaedics and Trauma

journal homepage: www.elsevier.com/locate/jcot

Artificial intelligence-based orthopaedic perpetual design

Md Nahid Akhtar a, Abid Haleem a, Mohd Javaid a, *, Sonu Mathur b, Abhishek Vaish c,
Raju Vaishya c
a
Department of Mechanical Engineering, Jamia Millia Islamia, New Delhi, India
b
Department of Mechanical Engineering GJUS &T Hisar Haryana, India
c
Department of Orthopaedics, Indraprastha Apollo Hospital, Sarita Vihar, Mathura Road, New Delhi, India

A R T I C L E I N F O A B S T R A C T

Keywords: Background and aims: Integrating Artificial Intelligence (AI) methodologies in orthopaedic surgeries is becoming
Bone grafting increasingly important as it optimises implant designs and treatment procedures. This research article introduces
Humerus an innovative approach using an AI-driven algorithm, focusing on the humerus bone anatomy. The primary focus
3D reconstruction
of this work is to determine implant dimensions tailored to individual patients.
CT
Methodology: We have utilised Python’s DICOM library, which extracts rich information from medical images
MRI
Implant obtained through CT and MRI scans. The algorithm generates precise three-dimensional reconstructions of the
AI bone, enabling a comprehensive understanding of its morphology.
Design Results: Using algorithms that reconstructed 3D bone models to propose optimal implant geometries that adhere
Fracture to patients’ unique anatomical intricacies and cater to their functional requirements. Integrating AI techniques
Orthopaedic promotes enhanced implant designs that facilitate enhanced integration with the host bone, promoting improved
patient outcomes.
Conclusion: A notable breakthrough in this research is the ability of the algorithm to predict implant physical
dimensions based on CT and MRI data. The algorithm can infer implant specifications that align with patient-
specific bone characteristics by training the AI model on a diverse dataset. This approach could revolutionise
orthopaedic surgery, reducing patient waiting times and the duration of medical interventions.

1. Introduction (NLP) is a widely utilised AI instrument within the healthcare sector,

which extracts variables and performs classifications.1
1.1. Background and gaps in the literature AI-driven medical imaging analysis like MRI and X-rays has
empowered orthopaedic experts to precisely identify and diagnose is­
Orthopaedics specialises in diagnosing, treating, preventing, and sues such as fractures, joint irregularities, and tumours. Rapid analysis of
rehabilitating musculoskeletal disorders and injuries. This surgical extensive imaging data by AI algorithms supports medical professionals
branch has witnessed significant advancements and potential future in making highly accurate diagnoses and devising targeted treatment
scope, addressing various musculoskeletal diseases and injuries; in­ strategies.
terventions, such as joint replacements/arthroplasty, spine surgeries, The spotlight turns toward (AI) in orthopaedics, where research
fracture fixation, and deformity corrective procedures, are being formed primarily centres on spinal, knee, and hip-related matters. However,
faster healing to minimise long-term complications. Reconstructive or­ using AI in therapeutic applications and sub-specialities still exhibits
thopaedic surgery is a highly specialised field that requires a profound constraints. In orthopaedics, conventional joint replacement surgery is
understanding of medical imaging, anatomy, and orthopaedics. Such based on some specific standards that are not personalised. However,
software development typically involves close collaboration with med­ the patterns of fractures from patient to patient may pose constraints for
ical professionals, engineering, and software professionals to ensure its implant selection. These constraints are strict regulations, difficulty
accuracy and suitability for clinical use. Natural language processing accessing high-quality data, regulatory approval, compatibility with

* Corresponding author.
E-mail addresses: md2301180@st.jmi.ac.in (M.N. Akhtar), ahaleem@jmi.ac.in (A. Haleem), mjavaid@jmi.ac.in (M. Javaid), sonu.mathur87@gmail.com
(S. Mathur), drabhishekvaish@gmail.com (A. Vaish), raju.vaishya@gmail.com (R. Vaishya).

https://doi.org/10.1016/j.jcot.2024.102356
Received 30 August 2023; Received in revised form 26 January 2024; Accepted 2 February 2024
Available online 3 February 2024
0976-5662/© 2024 Delhi Orthopedic Association. All rights reserved.
M.N. Akhtar et al. Journal of Clinical Orthopaedics and Trauma 49 (2024) 102356

existing systems, and resistance to change. There is an imminent intelligence, aiding in real-time suggestions and vaccine development. It
requirement for establishing standardised reporting for AI research and aids in screening, analysing, and tracking patients, including confirmed,
initiating prospective trials to address this gap.2 Advancements in sur­ recovered, and death cases.19 3D printing aids in complex trauma
gical techniques and technology, such as robotic-assisted surgeries management by accurately reducing implant placement, reducing sur­
(RAS) and arthroscopy, are expected to reduce invasiveness, promote gical time, and improving outcomes. Although initial learning curves
faster recovery, and minimise scarring. However, many Orthopaedic exist, practice and experience make these techniques easier.20–23 Recent
surgeons are aware of AI use but are still determining its safety, and research and publications show a surge in interest in 3D printing in
hence, research is needed to assess its usefulness and safety.3 orthopaedic surgery despite its primitive stage due to insufficient
Biomedical agents, personalised medicine AI, implant technology, knowledge, high costs, and learning curve, suggesting its potential for
remote monitoring, tissue engineering, nanotechnology, preventive future orthopaedics and trauma cases.24,25 This review explores the need
strategies, and global access to care are also expected to revolutionise for technological advancements and the critical challenges in finding
orthopaedic treatments. AI integration in orthopaedic surgery focuses innovative solutions.
on ethical and legal considerations, patient autonomy, privacy, and
workforce shifts.4 Combining AI algorithms, data analytics, and inno­ 1.2. Aims
vative technology can improve patient outcomes, increase efficiency,
and transform care delivery, which is the importance of AI in delivering We aim to highlight the areas where orthopaedic practices can be
value-based healthcare.5 Additive manufacturing (AM) is revolutionis­ reshaped by investigating manufacturing techniques, streamlined pro­
ing the medical industry with customised orthotics, 3D printing, and cesses, and regulatory enhancements and the integration of AI-based
biocompatibility.6 technology with the following principal objectives.
Newer orthopaedic implants pose challenges due to their biocom­
patibility, durability, time-consuming manufacturing, and sensory • To enhance the orthopaedic prosthesis selection process by devel­
feedback. Emerging technologies like smart prosthetics, 3D printing and oping an algorithm to improve decision-making efficiency and
AI can enhance functionality. Interdisciplinary collaboration, increased accuracy.
research investment, component standardisation, and improved access • To develop a technique to regenerate the numerous bone structures
are crucial for success.7 Prosthetic joint infection (PJI) after total hip using CT and MRI data.
arthroplasty (THA) may require debridement, implant retention, and • To create a 3D reconstruction of the humerus bone and develop a
antibiotic therapy, with atypical microorganisms challenging.8 A study method for accurate implantation.
analysed 145 orthopaedic surgeons’ intentions to integrate new medical
technologies, revealing that perceived advantages, risks, quality, expe­ 2. Methodology
rience, and receptivity to digital tools influence their use.9 In modern
Orthopaedic treatments, options include various innovative surgical Data collection involves gathering a diverse dataset of medical im­
techniques and technological innovations involving multidisciplinary ages and preprocessing them to enhance quality and standardised for­
approaches.10 Industry 5.0 is particularly appealing in highlighting its mats. Image segmentation uses AI-based techniques to identify target
transformative technologies that enable personalised treatments by structures and generate accurate 3D models of the patient’s
seamlessly integrating machinery and human expertise.11 Industry 5.0 anatomy.26,27
helps develop individualised products for diagnosing, treating, and Extracts of relevant features from the models and clinical data are
managing various orthopaedic conditions. AI has significantly impacted achieved by feature extraction, while data labelling and annotation
Orthopaedics with technological advancements and access to handheld serve as the foundation for training and validating the AI algorithm
devices. Industry 4.0, through smart manufacturing, can meet mass (Fig. 1). Machine learning model development uses convolutional neural
production needs, but it may only partially meet personalised implan­ networks (CNN) or recurrent neural networks (RNN) to develop pre­
tation. Through the integration of automation and the enhancement of dictive models, and personalised design optimisation involves inputting
labour efficiency, Industry 5.0 has facilitated the creation of a patient’s specific anatomical data into the trained model.28
patient-tailored tools, instruments, and implants aimed at enhancing Validation and testing are conducted using real-world patient cases
clinical outcomes, functional improvements, and Patient-Related and clinical scenarios, evaluating factors like implant stability, align­
Outcome Measures (PROMs).12–14 Computer technology and implant ment accuracy, and surgical outcomes. Continuous learning and
design advancements have led to developing smart instruments and improvement mechanisms are implemented, with feedback from or­
intelligent implants in trauma and orthopaedics, improving thopaedic surgeons and refinement based on new data to enhance ac­
patient-related functional outcomes. Sensor technology uses embedded curacy and effectiveness.
devices to detect physical, chemical, and biological signals, offering Integration into the surgical workflow involves user-friendly in­
diagnostic capabilities and therapeutic benefits. These implants have terfaces, seamless integration into existing software, and adherence to
applications in total knee arthroplasty, hip arthroplasty, spine surgery, medical device regulations and ethical guidelines. Python is a versatile
fracture healing, early detection of infection, and implant loosening. programming language widely employed in various fields, including
Smart sensor implant technology objectively assesses ligament and soft medical imaging. Regarding medical imaging, the Digital Imaging and
tissue balancing, maintains sagittal and coronal alignment, and achieves Communications in Medicine (DICOM) standard is crucial for storing
desired kinematic targets. Post-implantation data can monitor implant and transmitting medical images.29
performance and patient clinical recovery during rehabilitation.15 MRI Python’s libraries, Pydicom, MONAI, Vedo, and Nibabel, enable
and PET scans are used to evaluate articular cartilage integrity, with seamless interaction with medical image files, allowing for efficient
PET-MRI combining them for detailed joint imaging, potentially aiding manipulation and analysis.30 Python’s integration with DICOM plays a
in understanding OA pathophysiology.16 The Internet of Medical Things pivotal role in image reconstruction. It facilitates data extraction from
(IoMT) combines medical devices and applications with healthcare in­ DICOM files, reconstructing three-dimensional images from a series of
formation technology systems, offering improved care and satisfaction DICOM slices. This capability is pivotal in diverse medical applications,
for orthopaedic patients during the COVID-19 pandemic. It enables data from CT scans to magnetic resonance imaging (MRI), enhancing diag­
sharing, patient tracking, and remote-location healthcare, transforming nosis and treatment planning.
healthcare facilities and improving patient satisfaction.17,18 Healthcare Fig. 2 shows the trans-axial view, sagittal view and coronal view
organisations require AI-driven decision-making technologies to representing partial bone structure, and the skeleton part generated
manage COVID-19 and prevent its spread. AI mimics human using the algorithm is shown in Fig. 3.

2
M.N. Akhtar et al. Journal of Clinical Orthopaedics and Trauma 49 (2024) 102356

Fig. 1. Artificial Intelligence (AI)-based design Algorithm.

Fig. 2. View generated from DICOM data (A-Trans-axial view; B-Sagittal view; C-Coronal view).

the skeleton structure, and it is further processed for surface modelling.

The rough surface model thus generated from point cloud data is shown
in Fig. 4(b), and after further processing for a smooth surface, the bone
model is seen in Fig. 4(c). The quality of the surface depends upon the
density of point cloud data.
This approach optimises patient-specific solutions, offering multiple
options for joint support and expediting treatment selection based on
real-time data, ultimately enhancing healthcare outcomes.

3. Results and discussion

The design and implementation of orthopaedic implants are time-

consuming processes, alignment and external support design prob­
lems, instant design and specialised design availability. Time-taking
processes can delay timely treatment, especially in urgent cases like
fractures and malignancies. Customised implant designs may be neces­
sary due to patient anatomy or complex injuries, and the lack of these
designs can compromise treatment outcomes. Proper alignment is
Fig. 3. Skeleton generated using Artificial Intelligence (AI) algorithm crucial for implant success, and issues like joint instability, limited range
in Python.
of motion (ROM), and premature implant failure can arise. Designing
implants that integrate seamlessly with external supports can be chal­
After generating the skeleton bone structure, for example, humerus lenging, and the immediate availability of appropriate designs is
bone may be extracted from the generated surface, as shown in Fig. 4. essential for avoiding complications in urgent cases. Specialised implant
Fig. 4(a) represents the point cloud data of humerus bone extracted from designs tailored to unique patient needs may be available slowly.31

3
M.N. Akhtar et al. Journal of Clinical Orthopaedics and Trauma 49 (2024) 102356

Fig. 4. Humerus bone structure from Artificial Intelligence (AI) - generated surface.

3.1. AI-based 3D reconstruction algorithm’s safety, accuracy, and clinical effectiveness.37 The cost and
the delay time for implant manufacturing in the case of personalised
AI-based methods excel in rapidly and precisely reconstructing bones implants can be further calculated with the process and the machinery
using patient-specific DICOM or CT scan images, streamlining the pro­ availability with its capacity for precision and degree of flexibility. We
cess compared to manual programming. The resultant 3D models play a understand that entering the Orthopaedic ‘market’ with AI-based per­
crucial role across various applications, from crafting 3D-printed pro­ petual designs involves considerations in cost, technological advance­
totypes for fracture treatment to supporting diverse analyses, research ment, and practicality. The initial development cost of advanced AI
and clinical decision-making. These breakthroughs significantly technologies may be high, however, as technology advances, costs could
contribute to refining bone implant design and optimisation, ensuring a decrease, making it more feasible for the users.
better fit and enhanced functionality for patients.
These innovations empower surgeons to conduct surgeries more 3.3. Radiological aspects
precisely, improving patient outcomes. Surgeons can utilise precise 3D
models to meticulously plan and execute procedures, thereby increasing Imaging studies are pivotal in Orthopaedic care. Manifestations.
success rates and diminishing associated surgical risks. The convergence Baseline radiological assessments rely on plain radiographs, whereas
of programming and AI-driven techniques in 3D reconstruction catalyses Computed Tomography (CT) and Magnetic Resonance Imaging (MRI)
reshaping healthcare practices, effectively bridging the gap between scans are employed to assess deeper clinical aspects such as bony fusion,
technical expertise and medical advancements. The future of this hardware integrity, and the presence of implant loosening.38 The im­
research imagines an instantaneous implant recommendation system aging is immensely useful for spinal problems in preoperative diagnosis
bolstered by cloud-based data infrastructure, which would harness the and intra-operative and postoperative imaging.39,40 Thirty patients who
power of AI and cloud computing to process and analyze medical im­ had metallic implants were assessed using CT scans along with multi­
aging data rapidly, expediting treatment decisions.32 planar reconstruction (MPR), and the results indicated that the appli­
The progressive transformation of implantation techniques can be cation of MPR substantially decreased metal-related artefacts in
discerned as a reflection of the burgeoning medical cognisance and the transaxial images.41 The Syngo Explorer is a new clinical X-ray
concurrent advancement of technological capabilities. The 21st century computed tomography software application for routine and scientific
has witnessed a paradigm shift in the assimilation of digital paradigms, work. It allows users to reconstruct, process, and view CT images
advanced imaging modalities, and the application of personalised independently, using the Syngo platform for patient data management
medical treatments. This transformative era engendered the integration and visualisation.42 The advanced single-slice rebinning (ASSR) algo­
of computer-assisted surgery (CAS), patient-specific implants (PSI), ad­ rithm is proposed for medical spiral cone-beam CT systems with large
ditive manufacturing (AM) through 3D printing, and the deployment of detector rows. It uses virtual reconstruction planes tilted to fit 180◦
AI-informed surgical planning. Cumulatively, these advancements are spiral segments, achieving high image quality, low patient dose, and low
instrumental in the recalibration of modern orthopaedic practices, reconstruction times. The algorithm’s computational complexity is
thereby fostering a dynamic milieu that is attuned to the amelioration of comparable to standard single-slice CT, allowing for available 2D back
patient outcomes and an overall improvement in the quality of life.33 projection hardware.43

3.2. Personalised implant design 3.4. Comparison of programming-based techniques vs. AI-based methods

Personalised solutions ensure that implant designs and surgical Programming-based approaches necessitate substantial proficiency
guides are optimised to fit each patient’s distinct anatomy, reducing and knowledge in 3D reconstruction techniques, making them less
design time and workload during surgery.34 In making evidence-based accessible to individuals without specialised training. Traditional pro­
decisions, the algorithm utilises data-driven insights to guide surgical gramming methods can be intricate and time-consuming, potentially
choices, enhancing precision and minimising complications. Innovative leading to errors in the reconstruction process due to the complexity of
design solutions employ advanced computational techniques, and the the algorithms. Programming-based approaches often require more
algorithm continually learns from real-world cases to improve its rec­ automation and adaptability than AI-based methods, potentially
ommendations.35 Advancements in cloud, internet, AI imaging, and 5G requiring manual adjustments and interventions during reconstruction.
technologies have made digital healthcare relevant in various clinical Table 1 compares Programming-based techniques and AI-based
indications and applications.36 A successful implementation necessitates methods.44
close collaboration between orthopaedic surgeons, medical device en­ These breakthroughs permeate various medical contexts, ultimately
gineers, data scientists, and regulatory experts, guaranteeing the offering support to surgeons in executing procedures with heightened

4
M.N. Akhtar et al. Journal of Clinical Orthopaedics and Trauma 49 (2024) 102356

Table 1 Technologically, AI-driven perpetual designs in Orthopaedics can

Salient features of comparison of Programming-based techniques vs. AI-based enhance diagnostic accuracy, treatment planning, and personalised
methods. care. The balance lies in ensuring that the technology aligns with reg­
PRE-REQUISITES PROS CONS ulatory standards and provides tangible benefits over traditional ap­
Programming- Necessitate Precise Control Less accessible to
proaches. Implementing AI in Orthopaedics requires collaboration with
based substantial most healthcare professionals, integration into existing systems. Striking a
techniques proficiency and Clear Debugging Time-consuming balance between innovation and practicality is also crucial for successful
knowledge in 3D and complex market adoption.
reconstruction Domain Likely errors
techniques. Knowledge possible
Artificial Can efficiently -The resulting Data 5. Conclusion
Intelligence- reconstruct bones model serves as a Dependency,
based using patient- foundational bvbv The programming-based techniques demand an exhaustive
methods specific DICOM or element for many comprehension and skillset for reconstructing from DICOM or other
CT scan images applications, from
creating 3D-
medical images. They also come with the accessibility challenge, often
printed prototypes confined to individuals with specialised training. Their complexity and
for fracture time-consuming nature can render them prone to errors in the recon­
mending to struction process due to intricate algorithms. Absence of automation and
facilitating diverse
adaptability intrinsic to AI-based methods can necessitate manual in­
analyses and
elevating the terventions and adjustments throughout the reconstruction process.
design and Conversely, AI-based methods can efficiently reconstruct bones using
optimisation of patient-specific DICOM or CT scan images. The resulting model serves as
bone implants. a foundational element for many applications, from creating 3D-printed
-AI can automate Ethical issues,
prototypes for fracture mending to facilitating diverse analyses and
and create a similar
design of bone that elevating the design and optimisation of bone implants.
is difficult to
program explicitly, Conflict of interest
leading to
increased
efficiency. Nothing to disclose.
-AI can identify Interpretability
complex patterns problems Funding
of bone from CT or
MRI scan images
None.
and correlations in
large datasets that
might be too Ethical approval
challenging for
humans to discern.
Not required.

precision and seamless ease. As the landscape of medical advancements Use of AI tools
progresses, the convergence of programming and AI-driven techniques
in 3D reconstruction emerges as a driving force, reshaping the equilib­ None.
rium between technical expertise and the evolution of medical practices
toward a more accessible and adaptive horizon. Authors’ contribution
Creating AI-based orthopaedic perpetual designs involve integrating
AI algorithms to continuously optimize orthopaedic implants, pros­ MNA: Manuscript Writing, Programming and processing, Editing and
thetics, or devices for enhanced performance and patient outcomes. The Final approval, AH: Manuscript Writing, Literature Search, Con­
AI system can analyze patient data, biomechanics, and material science ceptulaization, Editing and Final approval, MJ: Manuscript Writing,
to iteratively refine designs, ensuring adaptability to evolving medical Organisation and Data collection, Editing and Final approval, SK:
knowledge and individual patient needs. Entering the market with AI- Manuscript Writing, Data Collection, Methodology, Editing and Final
based perpetual designs in Orthopaedics necessitates managing costs, approval, AV: Manuscript Writing, Conceptualization, Technical modi­
leveraging technological advancements, and ensuring practicality for fications Editing and Final approval, RV: Manuscript Writing, Concep­
seamless integration into the healthcare landscape. tualization, Literature search, Technical modifications, Editing and Final
approval.
4. Limitations and future scope
Declaration of competing interest
This paper discusses AI-based orthopaedic implant designs, which
highlights the potential benefits of this approach. We acknoweldge its None.
limitations such as machine variability, accuracy, and challenges in
scalability and standardisation. This paper also emphasises the need for Acknowledgement
rigorous validation through ANSYS or other software simulations to
accurately represent real-world performance. The need for clear devel­ None.
opment criteria for personalised implants, acknowledging clinical
implementation challenges, and addressing 3D reconstruction, References
manufacturing time and cost, including the need for ethical and legal
1. Pruneski JA, Pareek A, Nwachukwu BU, et al. Natural language processing: using
considerations, patient consent, data privacy, and liability, to ensure artificial intelligence to understand human language in orthopaedics. Knee Surg
responsible implementation of personalised implant technologies. Sports Traumatol Arthrosc. 2023;31(4):1203–1211. https://doi.org/10.1007/s00167-
022-07272-0.

5
M.N. Akhtar et al. Journal of Clinical Orthopaedics and Trauma 49 (2024) 102356

2. Kamal AH, Zakaria OM, Majzoub RA, Nasir EWF. Artificial intelligence in 23. Haleem A, Javaid M, Vaish A, Vaishya R. Three-dimensional-printed polyether ether
orthopedics: a qualitative exploration of the surgeon perspective. Medicine. 2023; ketone implants for orthopedics. Indian J Orthop. 2019;53(2):377–379. https://doi.
102(24), e34071. https://doi.org/10.1097/md.0000000000034071. org/10.4103/ortho.ijortho_499_18.
3. Kurtz MA, Yang R, Elapolu MSR, et al. Predicting corrosion damage in the human 24. Haleem A, Javaid M, Vaishya R. 4D printing and its applications in Orthopaedics.
body using artificial intelligence. Orthop Clin N Am. 2023;54(2):169–192. https:// Journal of Clinical Orthopaedics and Trauma. 2018;9(3):275–276. https://doi.org/
doi.org/10.1016/j.ocl.2022.11.004. 10.1016/j.jcot.2018.08.016.
4. Tariq A, Gill AY, Hussain HK. Evaluating the potential of artificial intelligence in 25. Vaishya R, Vijay V, Vaish A, Agarwal AK. Computed tomography based 3D printed
orthopedic surgery for value-based healthcare. International Journal of patient specific blocks for total knee replacement. Journal of Clinical Orthopaedics
Multidisciplinary Sciences and Arts. 2023;2(1):27–35. https://doi.org/10.47709/ and Trauma. 2018;9(3):254–259. https://doi.org/10.1016/j.jcot.2018.07.013.
ijmdsa.v2i1.2394. 26. Vaishya R, Patralekh MK, Vaish A, Agarwal AK, Vijay V. Publication trends and
5. Kumar A, Chhabra D. Parametric topology optimisation approach for sustainable knowledge mapping in 3D printing in orthopaedics. Journal of Clinical Orthopaedics
development of customised orthotic appliances using additive manufacturing. Mech and Trauma. 2018;9(3):194–201. https://doi.org/10.1016/j.jcot.2018.07.006.
Adv Mater Struct. 2023:1–14. https://doi.org/10.1080/15376494.2023.2214908. 27. Maini L, Vaishya R, Lal H. Will 3D printing take away surgical planning from
Published online May 22. doctors? Journal of Clinical Orthopaedics and Trauma. 2018;9(3):193. https://doi.
6. Kumar A, Chhabra D. Parametric topology optimisation approach for sustainable org/10.1016/j.jcot.2018.06.013.
development of customised orthotic appliances using additive manufacturing. Mech 28. Yi PH, Garner HW, Hirschmann A, et al. Clinical applications, challenges, and
Adv Mater Struct. 2023:1–14. https://doi.org/10.1080/15376494.2023.2214908. recommendations for artificial intelligence in musculoskeletal and soft tissue
Published online May 22. ultrasound: AJR expert panel narrative review. Am J Roentgenol. 2023. https://doi.
7. Lara-Taranchenko Y, Corona PS, Rodríguez-Pardo D, et al. Prosthetic joint infection org/10.2214/ajr.23.29530. Published online July 12.
caused by an atypical gram-negative bacilli: odoribacter splanchnicus. Anaerobe. 29. Flores-Balado Á, Castresana Méndez C, Herrero González A, et al. Using artificial
2023;82, 102740. https://doi.org/10.1016/j.anaerobe.2023.102740. intelligence to reduce orthopaedic surgical site infection surveillance workload:
8. Lara-Taranchenko Y, Corona PS, Rodríguez-Pardo D, et al. Prosthetic joint infection algorithm design, validation, and implementation in 4 Spanish hospitals. Am J Infect
caused by an atypical gram-negative bacilli: odoribacter splanchnicus. Anaerobe. Control. 2023. https://doi.org/10.1016/j.ajic.2023.04.165. Published online April.
2023;82, 102740. https://doi.org/10.1016/j.anaerobe.2023.102740. 30. Kumar NH, Ashwin PS, Ananthakrishnan H. Mellis AI - an AI-generated music
9. Bones & joints-orthopedic. ORTHOPEDIC. Ann Surg. 1894;19:746–755. https://doi. composer using RNN-LSTMs. International Journal of Machine Learning and
org/10.1097/00000658-189401000-00083. Computing. 2020;10(2):247–252. https://doi.org/10.18178/ijmlc.2020.10.2.927.
10. Vaishya R, Haleem A. Technology and orthopaedic surgeons. J Orthop. 2022;34: 31. Li Z. Digital orthopedics: the future developments of orthopedic surgery.
414–415. https://doi.org/10.1016/j.jor.2022.08.018. J Personalized Med. 2023;13(2):292. https://doi.org/10.3390/jpm13020292.
11. Kumar V, Patel S, Baburaj V, Vardhan A, Singh PK, Vaishya R. Current 32. Iqbal Shahid MZ, Ullah SI, Khalid Muhammad, Shair NA, Mahmood T, Iqbal M.
understanding on artificial intelligence and machine learning in orthopaedics – a Open reduction and internal fixation of proximal humerus with proximal humeral
scoping review. J Orthop. 2022;34:201–206. https://doi.org/10.1016/j. locking plate. JAIMC: Journal of Allama Iqbal Medical College. 2023;21(1). https://
jor.2022.08.020. doi.org/10.59058/jaimc.v21i1.92.
12. Iyengar KP, Zaw Pe E, Jalli J, et al. Industry 5.0 technology capabilities in trauma 33. Girão MMV, Miyahara LK, Dwan VSY, et al. Imaging features of the postoperative
and orthopaedics. J Orthop. 2022;32:125–132. https://doi.org/10.1016/j. spine: a guide to basic understanding of spine surgical procedures. Insights into
jor.2022.06.001. Imaging. 2023;14(1). https://doi.org/10.1186/s13244-023-01447-0.
13. Vaishya R, Scarlat MM, Iyengar KP. Will technology drive orthopaedic surgery in the 34. Ortiz AO, de Moura A, Johnson BA. Postsurgical spine: techniques, expected
future? Int Orthop. 2022;46(7):1443–1445. https://doi.org/10.1007/s00264-022- imaging findings, and complications. Seminars Ultrasound, CT MRI. 2018;39(6):
05454-6. 630–650. https://doi.org/10.1053/j.sult.2018.10.017.
14. Iyengar KP, Gowers BTV, Jain VK, RajuS Ahluwalia, Botchu R, Vaishya R. Smart 35. Rutherford EE, Tarplett LJ, Davies EM, Harley JM, King LJ. Lumbar spine fusion and
sensor implant technology in total knee arthroplasty. Journal of Clinical Orthopaedics stabilization: hardware, techniques, and imaging appearances. Radiographics. 2007;
and Trauma. 2021;22, 101605. https://doi.org/10.1016/j.jcot.2021.101605. 27(6):1737–1749. https://doi.org/10.1148/rg.276065205.
15. Jena A, Taneja S, Rana P, et al. Emerging role of integrated PET-MRI in 36. Fishman EK, Magid D, Robertson DD, Brooker AF, Weiss P, Siegelman SS. Metallic
osteoarthritis. Skeletal Radiol. 2021;50(12):2349–2363. https://doi.org/10.1007/ hip implants: CT with multiplanar reconstruction. Radiology. 1986;160(3):675–681.
s00256-021-03847-z. https://doi.org/10.1148/radiology.160.3.3737905.
16. Pratap Singh R, Javaid M, Haleem A, Vaishya R, Ali S. Internet of medical Things 37. Sennst DA, Kachelriess M, Leidecker C, Schmidt B, Watzke O, Kalender WA. An
(IoMT) for orthopaedic in COVID-19 pandemic: roles, challenges, and applications. extensible software-based platform for reconstruction and evaluation of CT images.
Journal of Clinical Orthopaedics and Trauma. 2020;11(4):713–717. https://doi.org/ Radiographics. 2004;24(2):601–613. https://doi.org/10.1148/rg.242035119.
10.1016/j.jcot.2020.05.011. 38. Kachelrieß M, Schaller S, Kalender WA. Advanced single-slice rebinning in cone-
17. Javaid M, Haleem A, Vaishya R, Bahl S, Suman R, Vaish A. Industry 4.0 technologies beam spiral CT. Med Phys. 2000;27(4):754–772. https://doi.org/10.1118/1.598938.
and their applications in fighting COVID-19 pandemic. Diabetes Metabol Syndr: Clin 39. Pareek P, Jayaswal R, Patil S, Vyas K. A bone fracture detection using AI-based
Res Rev. 2020;14(4):419–422. https://doi.org/10.1016/j.dsx.2020.04.032. techniques. Scalable Comput Pract Exp. 2023;24(2):161–171. https://doi.org/
18. Vaishya R, Javaid M, Khan IH, Haleem A. Artificial Intelligence (AI) applications for 10.12694/scpe.v24i2.2081.
COVID-19 pandemic. Diabetes Metabol Syndr: Clin Res Rev. 2020;14(4):337–339. 40. Soydan Z, Saglam Y, Key S, et al. An AI-based classifier model for lateral pillar
https://doi.org/10.1016/j.dsx.2020.04.012. classification of Legg–Calve–Perthes. Sci Rep. 2023;13(1). https://doi.org/10.1038/
19. Vaishya R, Javaid M, Khan IH, Haleem A. Artificial Intelligence (AI) applications for s41598-023-34176-x.
COVID-19 pandemic. Diabetes Metabol Syndr: Clin Res Rev. 2020;14(4):337–339. 41. Twomey-Kozak J, Hurley E, Levin J, Anakwenze O, Klifto C. Technological
https://doi.org/10.1016/j.dsx.2020.04.012. innovations in shoulder replacement: current concepts and the future of robotics in
20. Mishra A, Verma T, Vaish A, Vaish R, Vaishya R, Maini L. Virtual preoperative total shoulder arthroplasty. J Shoulder Elbow Surg. 2023. https://doi.org/10.1016/j.
planning and 3D printing are valuable for the management of complex orthopaedic jse.2023.04.022. Published online May.
trauma. Chin J Traumatol. 2019;22(6):350–355. https://doi.org/10.1016/j. 42. Flohr T, Stierstorfer K, Schaller S, Kachelriess M, Bruder H. Single-slice rebinning
cjtee.2019.07.006. reconstruction in spiral cone-beam computed tomography. IEEE Trans Med Imag.
21. Haleem A, Javaid M, Vaishya R. 5D printing and its expected applications in 2000;19(9):873–887. https://doi.org/10.1109/42.887836.
Orthopaedics. Journal of Clinical Orthopaedics and Trauma. 2019;10(4):809–810. 43. Mason D. SU-E-T-33: Pydicom: an open source DICOM library. Med Phys. 2011;38
https://doi.org/10.1016/j.jcot.2018.11.014. (6Part10):3493. https://doi.org/10.1118/1.3611983, 3493.
22. Haleem A, Javaid M, Vaishya R. Industry 4.0 and its applications in orthopaedics. 44. Clunie DA. Dual-personality DICOM-TIFF for whole slide images: a migration
Journal of Clinical Orthopaedics and Trauma. 2019;10(3):615–616. https://doi.org/ technique for legacy software. J Pathol Inf. 2019;10(1):12. https://doi.org/10.4103/
10.1016/j.jcot.2018.09.015. jpi.jpi_93_18.