Search

Diagnosis classification in the emergency room (ER) is a complex task. We developed several natural language processing classification models, looking both at the full classification task of 132 diagnostic categories and at several clinically applicable samples consisting of two diagnoses that are hard to distinguish.

Machine learning and artificial intelligence are generating significant attention in the scientific community and media. Such algorithms have great potential in medicine for personalizing and improving patient care, including in the diagnosis and management of heart failure. Many physicians are familiar with these terms and the excitement surrounding them, but many are unfamiliar with the basics of these algorithms and how they are applied to medicine. Within heart failure research, current applications of machine learning include creating new approaches to diagnosis, classifying patients into novel phenotypic groups, and improving prediction capabilities. In this paper, we provide an overview of machine learning targeted for the practicing clinician and evaluate current applications of machine learning in the diagnosis, classification, and prediction of heart failure.

Unter dem Begriff Cholangiokarzinom werden diverse maligne epitheliale Neoplasien unterschiedlicher Differenzierung, Atiologie und Pathogenese zusammengefasst. In dieser Arbeit sollen die Atiologie, Pathogenese, Diagnostik, Klassifikation und molekulare Alterationen intra- und extrahepatischer Cholangiokarzinome dargestellt werden. Grundlage hierfur sind die derzeit verfugbare Fachliteratur sowie eigene Erkenntnisse. Cholangiokarzinome sind morphologisch und molekular vielgestaltige maligne epitheliale Neoplasien, die ubiquitar im Gallengangsystem entstehen konnen. Da histologisch und immunhistochemisch breite Uberlappungen zu den haufigen metastatischen Absiedelungen in der Leber bestehen, sollte die definitive Diagnose nur im klinischen Kontext gestellt werden. Nach makroanatomischen Kriterien werden Cholangiokarzinome in intrahepatische (iCCA), perihilare (pCCA) und distale (dCCA) Tumore subklassifiziert. Wie sich durch neuere Untersuchungen abzeichnet, bestehen insbesondere zwischen den iCCA und den extrahepatischen CCA (eCCA, diese umfassen pCCA und dCCA) deutliche molekulare Unterschiede. Zudem konnten mittlerweile morphologisch gut charakterisierte Vorlauferlasionen identifiziert werden, die sich in verschiedenen Haufigkeiten nicht nur der anatomischen Klassifikation, sondern auch distinkten Atiologien zuordnen lassen. Eine exakte Klassifikation der CCA ist somit essenziell, vor allem im Hinblick auf die Entwicklung innovativer, zielgerichteter Therapieansatze.

Careful clinical evaluation differentiates epileptic seizures from syncope (vasovagal and cardiogenic), dissociative seizures (non-epileptic attack disorder) and other rarer causes of paroxysmal events. The initial diagnosis of epilepsy is incorrect in 20–30% of patients. Investigations can include blood tests, electrocardiograms, electroencephalograms and neuro-imaging. Patients should be informed and counselled about the diagnosis. Anti-epileptic drugs are the first-line treatment for epilepsy, the choice depending on the epilepsy syndrome, the seizure type, the patient and their co-morbidities. Surgical options are available for refractory epilepsy. Status epilepticus is a medical emergency and all clinicians should be aware of the treatment algorithm.

For the diagnosis of diseases, modern medicine usually searches for diseases in the disease database to find the type of disease that matches them. The diagnosis of diseases is the first step in treatment. Then the classification of diseases is the basis of disease diagnosis. Disease classification plays an extremely important role in the scientific management of medical records and the development of modern medicine, and is a bridge connecting modern medical science. Therefore, the classification of diseases is very necessary. Based on this, this article establishes a K-means model for disease diagnosis, and combines the internationally unified disease type code ICD statistics table to classify the sample data set into infectious and parasitic diseases, tumors, diabetes and circulatory diseases The training is perfect, and finally the diagnosis classification of the disease is realized.

Narcissistic personality disorder (NPD) remains a controversial diagnosis, with lack of consensus on essential features of the disorder and its boundaries. Within the framework of object relations theory (ORT), core organizing, structural features define NPD and provide a coherent conceptual framework for understanding clinical features of the disorder. In the ORT model, both grandiose and vulnerable presentations of NPD are characterized by a specific form of self-pathology, reflecting the impact of a grandiose self-structure in the setting of borderline personality organization. The grandiose self-structure provides some stability of self-functioning but does not confer the self-regulatory capacities provided by normal identity formation and is reliant on maintaining a sense of the self as exceptional. We compare the ORT model of NPD to diagnostic criteria in the Alternative Model for Personality Disorders (AMPD) of the DSM-5, highlighting significant correspondence between the two models as well as conceptual differences.

Pulmonary hypertension (PH), defined by increased pressure within the pulmonary vasculature, is a hemodynamic and pathophysiologic state present in a wide variety of cardiovascular, respiratory, and systemic diseases. The purpose of this consensus statement is to provide a multidisciplinary approach to guidelines for the diagnosis, classification, treatment, and monitoring of PH in dogs. Comprehensive evaluation including consideration of signalment, clinical signs, echocardiographic parameters, and results of other diagnostic tests supports the diagnosis of PH and allows identification of associated underlying conditions. Dogs with PH can be classified into the following 6 groups: group 1, pulmonary arterial hypertension; group 2, left heart disease; group 3, respiratory disease/hypoxia; group 4, pulmonary emboli/pulmonary thrombi/pulmonary thromboemboli; group 5, parasitic disease (Dirofilaria and Angiostrongylus); and group 6, disorders that are multifactorial or with unclear mechanisms. The approach to treatment of PH focuses on strategies to decrease the risk of progression, complications, or both, recommendations to target underlying diseases or factors contributing to PH, and PH‐specific treatments. Dogs with PH should be monitored for improvement, static condition, or progression, and any identified underlying disorder should be addressed and monitored simultaneously.

In March 2021, the Radiological Society of North America hosted a virtual panel discussion with members of the Medical Image Computing and Computer Assisted Intervention Society. Both organizations share a vision to develop radiologic and medical imaging techniques through advanced quantitative imaging biomarkers and artificial intelligence. The panel addressed how radiologists and data scientists can collaborate to advance the science of AI in radiology. Keywords: Adults and Pediatrics, Segmentation, Feature Detection, Quantification, Diagnosis/Classification, Prognosis/Classification © RSNA, 2021

Text-based diagnosis classification is a critical problem in AI-enabled healthcare studies, which assists clinicians in making correct decision and lowering the rate of diagnostic errors. Previous studies follow the routine of sequence based deep learning models in NLP literature to deal with clinical notes. However, recent studies find that structural information is important in clinical contents that greatly impacts the predictions. In this paper, a novel sequence-to-subgraph framework is introduced to process clinical texts for classification, which changes the paradigm of managing texts. Moreover, a new classification model under the framework is proposed that incorporates subgraph convolutional network and hierarchical diagnostic attentive network to extract the layered structural features of clinical texts. The evaluation conducted on both the real-world English and Chinese datasets shows that the proposed method outperforms the state-of-the-art deep learning based diagnosis classification models.

Author(s): Schaller, M; Almeida, LMC; Bewley, A; Cribier, B; Del Rosso, J; Dlova, NC; Gallo, RL; Granstein, RD; Kautz, G; Mannis, MJ; Micali, G; Oon, HH; Rajagopalan, M; Steinhoff, M; Tanghetti, E; Thiboutot, D; Troielli, P; Webster, G; Zierhut, M; van Zuuren, EJ; Tan, J | Abstract: BackgroundA transition from a subtyping to a phenotyping approach in rosacea is underway, allowing individual patient management according to presenting features instead of categorization by predefined subtypes. The ROSacea COnsensus (ROSCO) 2017 recommendations further support this transition and align with guidance from other working groups.ObjectivesTo update and extend previous global ROSCO recommendations in line with the latest research and continue supporting uptake of the phenotype approach in rosacea through clinical tool development.MethodsNineteen dermatologists and two ophthalmologists used a modified Delphi approach to reach consensus on statements pertaining to critical aspects of rosacea diagnosis, classification and management. Voting was electronic and blinded.ResultsDelphi statements on which the panel achieved consensus of ≥ 75% voting 'Agree' or 'Strongly agree' are presented. The panel recommends discussing disease burden with patients during consultations, using four questions to assist conversations. The primary treatment objective should be achievement of complete clearance, owing to previously established clinical benefits for patients. Cutaneous and ocular features are defined. Treatments have been reassessed in line with recent evidence and the prior treatment algorithm updated. Combination therapy is recommended to benefit patients with multiple features. Ongoing monitoring and dialogue should take place between physician and patients, covering defined factors to maximize outcomes. A prototype clinical tool (Rosacea Tracker) and patient case studies have been developed from consensus statements.ConclusionsThe current survey updates previous recommendations as a basis for local guideline development and provides clinical tools to facilitate a phenotype approach in practice and improve rosacea patient management. What's already known about this topic? A transition to a phenotype approach in rosacea is underway and is being recommended by multiple working groups. New research has become available since the previous ROSCO consensus, necessitating an update and extension of recommendations. What does this study add? We offer updated global recommendations for clinical practice that account for recent research, to continue supporting the transition to a phenotype approach in rosacea. We present prototype clinical tools to facilitate use of the phenotype approach in practice and improve management of patients with rosacea.

Raynaud's phenomenon (RP) is used to describe a symptom complex caused by digital vascular compromise. RP is a clinical diagnosis. The typically episodic nature of RP has resulted in a reliance upon patient self-report for diagnosis. The term 'primary RP' is generally applied when no underlying pathology can be demonstrated. Whilst 'primary RP' is currently considered a distinct disorder, there is evidence that the term may comprise several entities that include a functional vasospastic disorder, a physiologically appropriate thermoregulatory response, subclinical atherosclerosis and 'cold intolerance'. Optimal management may differ depending on cause. The term 'secondary RP' encompasses a broad range of rheumatological, haematological, endocrinological and vascular pathology. RP can range from relatively benign but intrusive vasospasm, to the progressive obliterative microangiopathy of systemic sclerosis (SSc), in which severe digital ischaemia can threaten tissue viability. SSc has formed the focus of much of the research into RP but, consistent with most medical symptom complexes, the aetiopathogenesis of RP varies greatly dependent on cause. Vasospasm within the digital macro- and microvasculature occurs in SSc, but digital ischaemia is further compounded by a progressive obliterative microangiopathy. Recent work exploring the patient experience of SSc-RP is challenging the 'episodic' paradigm of 'Raynaud's', with important implications for clinical trials utilising diary-based patient-reported outcome instruments for assessing Raynaud's symptoms. This review shall examine the causes, pathogenesis, clinical features, classification and management of RP. A practical approach to the evaluation and management of RP is outlined, highlighting important knowledge gaps and unmet research needs where applicable. Key Points • Raynaud's phenomenon is a symptom complex related to digital vascular compromise secondary to broad-ranging pathology. • Raynaud's phenomenon, as currently classified, likely encompasses a number of aetiopathogenic processes. • Raynaud's phenomenon causes significant disease-related morbidity in autoimmune rheumatic diseases such as systemic sclerosis.

The purpose of this review is to summarize and highlight recent critical advances in the diagnosis, classification, and management of adenomyosis.Recent studies have clarified the specific mechanism through which adenomyotic lesions invade the underlying myometrium by epithelial-mesenchymal transition. Correlation studies using diagnostic MRI also strongly support the hypothesis of a different pathogenesis between the inner and outer myometrium forms of adenomyosis. Given advances in diagnostic imaging, several international organizations have also highlighted the importance of classification systems for adenomyosis. Finally, selective progesterone receptor modulators and gonadotropin-releasing hormone antagonists have demonstrated significant promise for treating pelvic pain and bleeding associated with adenomyosis, whereas novel fertility-preserving surgical techniques have been introduced to excise diffuse adenomyotic pathology while maintaining adequate uterine integrity.Recent attempts at a uniform and reproducible classification system likely represent the first step for the development of a staging system for adenomyosis that can be correlated with the severity of clinical symptoms and promote an individualized therapeutic approach. Simultaneously, further insights into the etiology and pathogenesis as outlined in this review may also help in the development of targeted medical therapies.

Mastocytosis is a heterogeneous group of hematologic neoplasms defined by an accumulation of neoplastic mast cells (MC) in the skin, bone marrow, and other visceral organs [...]

Smartwatches provide technology-based assessments in Parkinson’s disease (PD). It is necessary to evaluate their reliability and accuracy in order to include those devices in an assessment. We present unique results for sensor validation and disease classification via machine learning (ML). A comparison setup was designed with two different series of Apple smartwatches, one Nanometrics seismometer and a high-precision shaker to measure tremor-like amplitudes and frequencies. Clinical smartwatch measurements were acquired from a prospective study including 450 participants with PD, differential diagnoses (DD) and healthy participants. All participants wore two smartwatches throughout a 15-min examination. Symptoms and medical history were captured on the paired smartphone. The amplitude error of both smartwatches reaches up to 0.005 g, and for the measured frequencies, up to 0.01 Hz. A broad range of different ML classifiers were cross-validated. The most advanced task of distinguishing PD vs. DD was evaluated with 74.1% balanced accuracy, 86.5% precision and 90.5% recall by Multilayer Perceptrons. Deep-learning architectures significantly underperformed in all classification tasks. Smartwatches are capable of capturing subtle tremor signs with low noise. Amplitude and frequency differences between smartwatches and the seismometer were under the level of clinical significance. This study provided the largest PD sample size of two-hand smartwatch measurements and our preliminary ML-evaluation shows that such a system provides powerful means for diagnosis classification and new digital biomarkers, but it remains challenging for distinguishing similar disorders.

There have been considerable advances in the classification and assessment of psoriatic arthritis (PsA). In this report, we give an overview of historic and current classification criteria and discuss its role and limitations in research and clinical practice. We discuss the most commonly used assessment instruments for arthritis, psoriasis, onychodystrophy, enthesitis, dactylitis and axial PsA with a focus on clinical practice. We pay particular attention to the current evidence for the use of composite outcome measures, and their use in randomised controlled trials and routine care.

In disease diagnosis classification, ensemble learning algorithms enable strong and successful models by training more than one learning function simultaneously. This study aimed to eliminate the irrelevant variable problem with the proposed new feature selection method and compare the ensemble learning algorithms’ classification performances after eliminating the problems such as missing observation, classroom noise, and class imbalance that may occur in the disease diagnosis data. According to the findings obtained; In the preprocessed data, it was seen that the classification performance of the algorithms was higher than the raw version of the data. When the algorithms’ classification performances for the new proposed advanced t-Score and the old t-Score method were compared, the feature selection made with the proposed method showed statistically higher performance in all data sets and all algorithms compared to the old t-Score method (p = 0.0001).

Background: Primary progressive aphasias (PPA) have been investigated by clinical, therapeutic, and fundamental research but examiner-consistent language tests for reliable reproducible diagnosis and follow-up are lacking.Methods: We developed and evaluated a rapid language test for PPA (“PARIS”) assessing its inter-examiner consistency, its power to detect and classify PPA, and its capacity to identify language decline after a follow-up of 9 months. To explore the reliability and specificity/sensitivity of the test it was applied to PPA patients (N = 36), typical amnesic Alzheimer's disease (AD) patients (N = 24) and healthy controls (N = 35), while comparing it to two rapid examiner-consistent language tests used in stroke-induced aphasia (“LAST”, “ART”).Results: The application duration of the “PARIS” was ~10 min and its inter-rater consistency was of 88%. The three tests distinguished healthy controls from AD and PPA patients but only the “PARIS” reliably separated PPA from AD and allowed for classifying the two most frequent PPA variants: semantic and logopenic PPA. Compared to the “LAST” and “ART,” the “PARIS” also had the highest sensitivity for detecting language decline.Conclusions: The “PARIS” is an efficient, rapid, and highly examiner-consistent language test for the diagnosis, classification, and follow-up of frequent PPA variants. It might also be a valuable tool for providing end-points in future therapeutic trials on PPA and other neurodegenerative diseases affecting language processing.

In clinical psychology, burnout is regarded as a mental disorder assessed in patients who apply for psychological treatment and no longer work because of their symptoms or experience of serious problems in functioning at work. This definition of burnout is mostly referred to as ‘clinical burnout’. The purpose of this article is to provide insight into how clinicians in The Netherlands establish a diagnosis of clinical burnout and how they fit it in their classification systems. An outline is given on how psychological interventions for burnout are applied in therapies. The different phases in the treatment of clinical burnout – crisis, recovery, prevention, and post burnout growth, as well as their accompanying interventions are described. It may be relevant for work and organizational psychologists to realize that biological processes may play a role in the development of clinical burnout. For the physiology of stress, it does not matter whether the stress is work-related or the result of stress in private life or both. Central to understanding clinical burnout is the lack of recovery of the (physiological) stress system. It is also argued that the relevance of questionnaires, for detecting who is at serious health risk, is limited.

International audience; Diagnosis classification system of Temporomandibular disorders (TMD) is based on the biopsychosocial model of pain. The pathogenesis is poorly understood, leading to difficulties in treating these multifactorial conditions. The predisposing factors are pathophysiological, psychological or structural processes that alter the masticatory system and lead to an increase in the risk of development of TMD. The purpose of this integrative review was then to point out the specific mechanisms of TMD in the oral oncologic context to optimize the TMJ functional results in the management of patients with oral oncologic conditions. We explored in this paper the role of Axis II assessment of the biopsychosocial model of pain, the involvement of mechanical concepts such as dental occlusion, mandibular condyle positioning and related-structures reconstruction, and the stomatognathic changes induced by radiation.

Fibromyalgia (FM) is a syndrome that does not present a well-defined underlying organic disease. FM is a condition which has been associated with diseases such as infections, diabetes, psychiatric or neurological disorders, rheumatic pathologies, and is a disorder that rather than diagnosis of exclusion requires positive diagnosis. A multidimensional approach is required for the management of FM, including pain management, pharmacological therapies, behavioral therapy, patient education, and exercise. The purpose of this review is to summarize the recent advances in classification criteria and diagnostic criteria for FM as well as to explore pharmacotherapy and the use of alternative therapies including the use of plant bioactive molecules.

This chapter discusses DSM and non-DSM definitions and approaches to mood illness. Before 1980, the concept of manic–depressive illness (MDI) meant both bipolar illness and recurrent unipolar depression. Evidence on diagnostic validators since 1980 has not strengthened that claim and may be interpreted to support the original MDI concept, that is, that bipolar illness and unipolar depression are part of the same overall disease (MDI). As a corollary, the concept of major depressive disorder (MDD) may represent a spectrum of different depressive subtypes: mixed (depression with manic symptoms), melancholic, pure, vascular, and neurotic depression. Each subtype differs from the other, based on diagnostic validators of course, genetics, and biological aspects and/or treatment effects. The scientific evidence for this heterogeneity of MDD appears to weaken the claim dating to DSM-III in 1980 that this condition is a different diagnosis/illness from bipolar disorder. The differential diagnosis of mood conditions is described.

Morbus Perthes ist eine multifaktoriell bedingte idiopathische Huftkopfnekrose des Kindesalters. Regional ungleich verteilt, manifestiert sich das Krankheitsbild zwischen dem 3.–12. Lebensjahr. Die arztliche Kunst besteht in der stadienadaptierten, befundgerechten Behandlung. Ziel der Behandlung ist die Herstellung bzw. der Erhalt des arthrogenen Containments des Femurkopfes. Die vorliegende Arbeit beschreibt die komplexe Therapiesteuerung des Morbus Perthes. Dazu werden die klinisch relevanten Untersuchungsparameter, die gebrauchlichsten radiologischen Klassifikationen sowie die sich daraus ableitende Therapie im Uberblick dargestellt.

Acromioclavicular (AC) joint injury is a frequent diagnosis after an acute shoulder trauma – often found among athletes and people involved in contact sports. This injury occurs five times more frequently in men than in women, with the highest incidence in the 20- to 30-year-old age group. Patients usually complain of pain and tenderness over the shoulder, particularly over the AC joint. Depending on the degree of injury, the clavicle may become prominent on the injured site. The original classification was described by Rockwood and Green according to the injured ligament complex and degree and direction of clavicular displacement. Many surgical procedures have been described; among these are screws, plates, muscle transfer, ligamentoplasty procedures and ligament reconstruction using either autograft or allografts. With the advancement of shoulder arthroscopy, surgeons are much more capable of performing mini-open or arthroscopically-assisted procedures, allowing patients an earlier return to their daily living activities. However, the results of conventional open techniques are still comparable. The introduction of new arthroscopic equipment provides a great variety of surgical procedures, though every new technique has its own advantages and pitfalls. Currently there is no gold standard for the surgical treatment of any type of AC injury, though it should be remembered that whenever an arthroscopic technique is chosen, the surgeon’s expertise is likely to be the most significant factor affecting outcome. Cite this article: EFORT Open Rev 2018;3:426-433. DOI: 10.1302/2058-5241.3.170027

Our objective was to assess the generalizability, across sites and cognitive contexts, of schizophrenia classification based on functional brain connectivity. We tested different training-test scenarios combining fMRI data from 191 schizophrenia patients and 191 matched healthy controls obtained at 6 scanning sites and under different task conditions. Diagnosis classification accuracy generalized well to a novel site and cognitive context provided data from multiple sites were used for classifier training. By contrast, lower classification accuracy was achieved when data from a single distinct site was used for training. These findings indicate that it is beneficial to use multisite data to train fMRI-based classifiers intended for large-scale use in the clinical realm.

Cerebral β-amyloid burden can be measured by positron emission tomography (PET) tracers, including 11C-Pittsburgh Compound B (11C-PiB) and three fluorinated tracers that have been approved by regulatory agencies. This review focuses on the current clinical use of amyloid PET and the added utility of quantifying β-amyloid deposition. Using systematic review methods, a PubMed search identified studies on the added value of standardized uptake value ratio (SUVR) to visual reads. PubMed search was also performed to identify studies that illustrate important factors that cause variability in SUVR results, as well as key papers in the initial development of 11C-PiB. Among studies comparing visual interpretation and SUVR, there is high concordance between visual reads and SUVR for diagnosis classification, with evidence that SUVR decreases inter-reader variability in visual interpretation and improves accuracy. The variability among results of studies utilizing SUVR is likely multifactorial, including choice of reference regions, choice of target regions, and methods for determining SUVR thresholds. The initial 11C-PiB studies illustrate the importance of rigorous pharmacokinetic modeling and stepwise simpler quantitative methods when translating radiotracers. There is increasing evidence of the added value of SUVR in the clinic, in particular in borderline cases or for detection of subtle changes. SUVR provides a reasonably accurate measurement of amyloid plaque deposition compared to pharmacokinetic modeling methods.

Peritoneal mesothelioma (PM) is an uncommon but a serious, and often, fatal primary peritoneal tumour, with increasing incidence worldwide. Conventional systemic chemotherapy, generally based on experience with pleural mesothelioma, usually has disappointing results considering PM as a terminal condition. Patients usually present with non-specific symptoms of abdominal distension and pain making the diagnosis challenging. As PM is confined to the abdomen for all, or much, of its clinical course, a multimodality treatment combining cytoreductive surgery (CRS) with hyperthermic intraperitoneal chemotherapy (HIPEC) has emerged as a new standard of care, and has been reported to achieve promising survival outcomes and local disease control in selected patients with PM. This review updates the presentation, diagnosis, classification and treatment strategies for PM.

In-stent restenosis is a pervasive challenge to the durability of stenting for the treatment of lower extremity ischemia. There is considerable controversy about the criteria for diagnosis, indications for treatment, and preferred algorithm for addressing in-stent restenosis. This evidence summary seeks to review existing information on strategies for the treatment of this difficult problem.

For the old intelligent malfunction diagnosis method has the problem of low diagnostic precision in the malfunction diagnosis of scrolling bearings, a heuristic search algorithm, cuckoo searching algorithm (CS) is proposed to optimize the BP network, so as to improve the diagnostic precision. First, utilize the BP network to construct scrolling bearings’ malfunction diagnosis classification model, secondly, utilize the cuckoo searching algorithm to optimize the BP’s weight and finally, utilize the optimized BP network for malfunction diagnosis. Simulating effects indicate that this means has better sort effect and is suitable for malfunction diagnosis of scrolling bearing. It has certain practicability.

The Poincare plot is a method to reflect heart rate variability, which has its unique advantages in the diagnosis of arrhythmias. At present, the research on automatic classification of Poincare plots is still in its early stage, which greatly affects the clinical application of Poincare plots. Therefore, a new algorithm is proposed in this paper, which makes comprehensive use of the Modified Hausdorff Distance and support vector machine method to do multiple classification of Poincare plots. Then the arrhythmia data in MIT-BIH ECG database were used to test the algorithm. The results showed that the classification accuracy was 90.2%, indicating that the algorithm was basically reliable and could play a certain auxiliary role in clinical Poincare plots based diagnosis classification.

© 2018, European Society of Sports Traumatology, Knee Surgery, Arthroscopy (ESSKA). Purpose: To develop a statement on the diagnosis, classification, treatment, and rehabilitation concepts of posterolateral corner (PLC) injuries of the knee using a modified Delphi technique. Methods: A working group of three individuals generated a list of statements relating to the diagnosis, classification, treatment, and rehabilitation of PLC injuries to form the basis of an initial survey for rating by an international group of experts. The PLC expert group (composed of 27 experts throughout the world) was surveyed on three occasions to establish consensus on the inclusion/exclusion of each item. In addition to rating agreement, experts were invited to propose further items for inclusion or to suggest modifications of existing items at each round. Pre-defined criteria were used to refine item lists after each survey. Statements reaching consensus in round three were included within the final consensus document. Results: Twenty-seven experts (100% response rate) completed three rounds of surveys. After three rounds, 29 items achieved consensus with over 75% agreement and less than 5% disagreement. Consensus was reached in 92% of the statements relating to diagnosis of PLC injuries, 100% relating to classification, 70% relating to treatment and in 88% of items relating to rehabilitation statements, with an overall consensus of 81%. Conclusions: This study has established a consensus statement relating to the diagnosis, classification, treatment, and rehabilitation of PLC injuries. Further research is needed to develop updated classification systems, and better understand the role of non-invasive and minimally invasive approaches along with standardized rehabilitation protocols. Level of evidence: Consensus of expert opinion, Level V.