Development and external validation of machine learning-based models to predict patients with cellulitis developing sepsis during hospitalisation.

OBJECTIVE: Cellulitis is the most common cause of skin-related hospitalisations, and the mortality of patients with sepsis remains high. Some stratification models have been developed, but their performance in external validation has been unsatisfactory. This study was designed to develop and compare different models for predicting patients with cellulitis developing sepsis during hospitalisation. DESIGN: This is a retrospective cohort study. SETTING: This study included both the development and the external-validation phases from two independent large cohorts internationally. PARTICIPANTS AND METHODS: A total of 6695 patients with cellulitis in the Medical Information Mart for Intensive care (MIMIC)-IV database were used to develop models with different machine-learning algorithms. The best models were selected and then externally validated in 2506 patients with cellulitis from the YiduCloud database of our university. The performances and robustness of selected models were further compared in the external-validation group by area under the curve (AUC), diagnostic accuracy, sensitivity, specificity and diagnostic OR. PRIMARY OUTCOME MEASURES: The primary outcome of interest in this study was the development based on the Sepsis-3.0 criteria during hospitalisation. RESULTS: Patient characteristics were significantly different between the two groups. In internal validation, XGBoost was the best model, with an AUC of 0.780, and AdaBoost was the worst model, with an AUC of 0.585. In external validation, the AUC of the artificial neural network (ANN) model was the highest, 0.830, while the AUC of the logistic regression (LR) model was the lowest, 0.792. The AUC values changed less in the boosting and ANN models than in the LR model when variables were deleted. CONCLUSIONS: Boosting and neural network models performed slightly better than the LR model and were more robust in complex clinical situations. The results could provide a tool for clinicians to detect hospitalised patients with cellulitis developing sepsis early.

Common Skin Conditions in Children and Adolescents: Bacterial Infections.

Bacterial skin infections represent a significant health care burden. Cellulitis and erysipelas are rapidly spreading, painful, superficial skin infections, usually caused by streptococci or Staphylococcus aureus. Folliculitis is an infection of hair follicles mostly caused by S aureus. Simple folliculitis typically is self-limited. Topical benzoyl peroxide is a first-line nonantibiotic treatment. Mupirocin and clindamycin are topical antibiotic options. For treatment-resistant cases, oral cephalexin or dicloxacillin is an appropriate option. Impetigo is a common, self-limited infection in children. Bullous impetigo is caused by S aureus, and nonbullous impetigo is caused by beta-hemolytic streptococci, S aureus, or both. In most cases, topical mupirocin or retapamulin (Altabax) is effective. Oral antibiotics should be considered for household outbreaks or patients with multiple lesions. Abscesses are red, painful collections of purulence in the dermis and deeper tissues caused by S aureus or polymicrobial infections. Furuncles are abscesses of a hair follicle, whereas carbuncles involve several hair follicles. In recurrent cases of these lesions, culture of the exudate is recommended. Abscess, furuncle, and carbuncle management consists of incision and drainage. Oral antibiotics are not necessary in most cases but should be prescribed for patients with severe immunocompromise or systemic signs of infection. In bacterial skin infections, methicillin-resistant S aureus coverage should be considered for patients with infections that have not improved with treatment.

Periorbital cellulitis as the initial presentation of acute lymphoblastic leukaemia.

A girl in early childhood with no significant medical history developed left eye periorbital oedema and erythema. She was treated with intravenous antibiotics for suspected severe periorbital cellulitis. Despite treatment, the patient's cellulitis progressed into necrotising fasciitis, and she was transferred for ophthalmology review and imaging. A CT scan and eye swab culture-confirmed Staphylococcus aureus periorbital cellulitis. Incidentally, pathology revealed significant pancytopenia suspicious of leukaemia. The patient underwent bone marrow biopsy and was diagnosed with B-cell acute lymphoblastic leukaemia (ALL). A multidisciplinary specialist assessment revealed no ocular evidence of leukaemia and no intraocular concerns. In medical literature, it is consistently found that cases of ALL initially manifesting as proptosis or eyelid oedema are invariably due to neoplastic infiltration. This case represents unique documentation where periorbital cellulitis is the initial presentation of B-cell ALL, underscoring the necessity to consider periorbital cellulitis as a possible differential diagnosis in ophthalmic manifestations of ALL.

What you need to know about common skin problems in older adults.

Skin ageing is a multifaceted process impacted by both intrinsic and extrinsic factors. Drier and less elastic skin with declining sebum levels in older age makes ageing skin more vulnerable to various skin conditions, including infections, inflammatory dermatoses, and cancers. Skin problems are common among older adults due to the effects of ageing, polypharmacy and multimorbidity impacting not only physical health but wellbeing and quality of life. In the UK, older adults in geriatric medicine wards may present with various skin conditions. Hospitalised older individuals may have undiagnosed skin problems unrelated to their admission, making hospitalisation an opportunity to manage unmet needs. Asteatotic eczema, incontinence associated dermatitis, seborrhoeic dermatitis, chronic venous insufficiency, and cellulitis are common disorders clinicians encounter in the geriatric medicine wards. This article outlines the importance of performing comprehensive skin assessments to help diagnose and commence management for these common conditions.

"Demodicosis" Mimicking PreSeptal Cellulitis: Severe Periocular and Facial Inflammation Caused by "Normal" Skin Flora.

Due to their relatively high prevalence and commensalism, the pathogenicity of Demodex mites has been debated. Recent data, however, show Demodex to be associated with skin and ocular surface diseases such as rosacea, blepharitis, and keratitis. Here the authors report the first known case, to the best of the their knowledge, of Demodex infestation mimicking preseptal cellulitis in an adult human. A 29-year-old male bilaterally blind from advanced retinopathy of prematurity presented with a 2-month history of right-greater-than-left upper eyelid and periocular/cheek swelling, redness, and ocular discharge that did not resolve with oral antibiotics or oral steroids. Based on MRI findings, biopsies of the right lacrimal gland, right orbital fat, and right upper eyelid preseptal skin were obtained which revealed marked intrafollicular Demodex mite density and budding yeasts in the upper eyelid skin. This case serves to alert clinicians to this entity that may not otherwise be usually considered in ophthalmic clinical practice.

Eosinophilic cellulitis (Wells' syndrome) in a female pediatric patient. / Celulitis eosinofílica (síndrome de Wells) en una paciente en edad pediátrica.

Wells' syndrome, or eosinophilic cellulitis, is an inflammatory disease of unknown origin, uncommon in the pediatric age. It usually appears clinically as erythematous and edematous plaques, nodules, papules, blisters, among other symptoms. Here we describe the case of a female pediatric patient with generalized, asymptomatic subcutaneous nodules associated with severe eosinophilia. The histopathological examination of the lesions was compatible with Wells' syndrome. An interdisciplinary evaluation was performed to establish the cause and look for associated eosinophilic disorders; the results were negative. Systemic corticosteroids were indicated and the patient had a good response; however, in view of the recurrence of the lesions after treatment discontinuation, dapsone was indicated as a second-line treatment, with subsequent improvement of the lesions and eosinophilia. The aim of this report was to describe the case of a female patient with an atypical manifestation of Wells' syndrome and the resulting therapeutic challenge.

El síndrome de Wells o celulitis eosinofílica es una enfermedad inflamatoria de origen desconocido, de aparición infrecuente en la edad pediátrica. Suele manifestarse clínicamente como placas eritematoedematosas, nódulos, pápulas, ampollas, entre otros. Se presenta una paciente en edad pediátrica con nódulos subcutáneos asintomáticos generalizados asociados a eosinofilia grave. El estudio histopatológico de las lesiones fue compatible con celulitis de Wells. Se realizó una evaluación interdisciplinaria en busca de la causa y trastornos eosinofílicos asociados, sin resultados positivos. Se indicó tratamiento sistémico con corticoides y presentó buena respuesta, pero, ante la recidiva de las lesiones tras su suspensión, se indicó dapsona como tratamiento de segunda línea, con mejoría posterior de las lesiones y de la eosinofilia. El objetivo del reporte es presentar una paciente con una manifestación atípica de síndrome de Wells y su desafío terapéutico.

Validation of Thermal Imaging and the ALT-70 Prediction Model to Differentiate Cellulitis From Pseudocellulitis.

Importance: Cellulitis is misdiagnosed in up to 30% of cases due to mimic conditions termed pseudocellulitis. The resulting overuse of antibiotics is a threat to patient safety and public health. Surface thermal imaging and the ALT-70 (asymmetry, leukocytosis, tachycardia, and age ≥70 years) prediction model have been proposed as tools to help differentiate cellulitis from pseudocellulitis. Objectives: To validate differences in skin surface temperatures between patients with cellulitis and patients with pseudocellulitis, assess the optimal temperature measure and cut point for differentiating cellulitis from pseudocellulitis, and compare the performance of skin surface temperature and the ALT-70 prediction model in differentiating cellulitis from pseudocellulitis. Design, Setting, and Participants: This prospective diagnostic validation study was conducted among patients who presented to the emergency department with acute dermatologic lower extremity symptoms from October 11, 2018, through March 11, 2020. Statistical analysis was performed from July 2020 to March 2021 with additional work conducted in September 2023. Main Outcomes and Measures: Temperature measures for affected and unaffected skin were obtained. Cellulitis vs pseudocellulitis was assessed by a 6-physician, independent consensus review. Differences in temperature measures were compared using the t test. Logistic regression was used to identify the temperature measure and associated cut point with the optimal performance for discriminating between cellulitis and pseudocellulitis. Diagnostic performance characteristics for the ALT-70 prediction model, surface skin temperature, and both combined were also assessed. Results: The final sample included 204 participants (mean [SD] age, 56.6 [16.5] years; 121 men [59.3%]), 92 (45.1%) of whom had a consensus diagnosis of cellulitis. There were statistically significant differences in all skin surface temperature measures (mean temperature, maximum temperature, and gradients) between cellulitis and pseudocellulitis. The maximum temperature of the affected limb for patients with cellulitis was 33.2 °C compared with 31.2 °C for those with pseudocellulitis (difference, 2.0 °C [95% CI, 1.3-2.7 °C]; P < .001). The maximum temperature was the optimal temperature measure with a cut point of 31.2 °C in the affected skin, yielding a mean (SD) negative predictive value of 93.5% (4.7%) and a sensitivity of 96.8% (2.3%). The sensitivity of all 3 measures remained above 90%, while specificity varied considerably (ALT-70, 22.0% [95% CI, 15.8%-28.1%]; maximum temperature of the affected limb, 38.4% [95% CI, 31.7%-45.1%]; combination measure, 53.9% [95% CI, 46.5%-61.2%]). Conclusions and Relevance: In this large diagnostic validation study, significant differences in skin surface temperature measures were observed between cases of cellulitis and cases of pseudocellulitis. Thermal imaging and the ALT-70 both demonstrated high sensitivity, but specificity was improved by combining the 2 measures. These findings support the potential of thermal imaging, alone or in combination with the ALT-70 prediction model, as a diagnostic adjunct that may reduce overdiagnosis of cellulitis.

Necrotising cellulitis of the breast associated with a fungating mucinous adenocarcinoma.

Breast necrotising soft tissue infections (NSTIs) are rare surgical emergencies with limited cases described in the literature. Here, we discuss a unique case of a woman in her 70s who presented with newly diagnosed diabetes and a neglected right breast cancer associated with breast erythema, skin necrosis, crepitus on examination and breast soft tissue gas seen on CT requiring emergent total mastectomy with partial pectoralis muscle excision. Pathology revealed a 15 cm invasive mucinous adenocarcinoma and necrotising polymicrobial cellulitis with a large abscess cavity. She recovered from her surgery with strict glycaemic control and a 10-day course of antibiotics. Multidisciplinary tumour board recommended adjuvant anastrozole, abemaciclib and postmastectomy radiation to complete her oncological treatment. Although exceedingly rare, it is important that clinicians be aware of, promptly recognise and properly treat NSTIs of the breast, as correct care can be life-saving from both infection and malignancy.

Incomplete Kawasaki disease presenting with a cellulitis-like plaque: Lessons from an unusual presentation.

Kawasaki disease (KD) is an acute small to medium-vessel vasculitis that primarily affects children under the age of 5 years. The cause of KD is unknown, but it is hypothesized to be a systemic inflammatory illness triggered by infections in genetically predisposed individuals. Diagnosis of incomplete KD is made in patients with prolonged fever without a source who do not meet diagnostic criteria but have some findings consistent with KD such as elevated inflammatory markers, transaminitis, and echocardiographic findings. We present a 7-year-old boy who developed 10 days of fevers and rash that began 3 days after his first dose of hepatitis A vaccination and had notable features of a peculiar cellulitis-like plaque and peripheral eosinophilia.

Cellulitis and bacteremia caused by the fish pathogen,Streptococcus iniae, in an immunocompromised patient: Case report and mini-review of zoonotic disease, lab identification, and antimicrobial susceptibility.

Streptococcus iniae is a fish pathogen that can also infect mammals including dolphins and humans. Its prevalence in farmed fish, particularly tilapia, provides potential for zoonotic infections, as documented by multiple case reports. Systematic clinical data beyond cellulitis for S. iniae infection in humans, including antimicrobial susceptibility data, are unfortunately rare. Here, we present a case of cellulitis progressing to bacteremia caused by Streptococcus iniae in a functionally immunocompromised patient based on CDK4/CDK6 inhibitor and endocrine therapy, and we discuss risk factors, identification, and antimicrobial susceptibility of this rare pathogen.

Diagnosing, assessing and managing cellulitis.

Cellulitis is an acute bacterial infection that affects the deep dermis and surrounding subcutaneous tissue. Although it is a common condition, it is often misdiagnosed because it can mimic a range of conditions that also cause inflamed, red, irritated and painful skin. Such misdiagnoses may lead to unnecessary hospital admissions and antibiotic overuse, with most alternative diagnoses being non-infectious. Undertaking a holistic patient assessment, skin assessment and thorough clinical history is important in the diagnosis of cellulitis, and it is vital to use a collaborative multidisciplinary approach in its acute management and to prevent recurrence. This article defines the term cellulitis and explores its presenting features. The author also discusses the associated risk factors, clinical assessment techniques and effective management strategies, as well as outlining the actions that nurses can take to prevent recurrence.

Role of Acute Rhinosinusitis in Periorbital Infections in Children.

OBJECTIVE: Periorbital cellulitis in children are commonly caused by acute rhinosinusitis (ARS). This study investigated the association of ARS and the severity of periorbital cellulitis in children. STUDY DESIGN: Retrospective case-control study of children with periorbital cellulitis with ARS versus periorbital cellulitis without ARS. SETTING: Patients were seen at West Virginia University Children's Hospitals between August 2011 to August 2022. METHODS: Patients were divided into cases and controls based on presence or absence of ARS. ARS was defined based on clinical symptoms with objective presence of disease on CT scan. Patients' characteristics, treatment, hospital length of stay, and readmission were collected. RESULTS: The sample consisted of 118 pediatric patients with orbital cellulitis. Patients with ARS were younger than patients without ARS (6.3 vs 8.5, p = 0.025), however there were no sex differences between two groups (p = 0.540). The ARS group had higher incidence of postseptal cellulitis (51.5% vs 9.6%, p < 0.001). As compared to patients without ARS, patients with ARS were more likely to be admitted (p < 0.001), have a longer length of stay (median of 3.5 days vs 0.5 days, p < 0.001), require IV antibiotics (95.3% vs 54.9%, p < 0.001), and require surgical intervention (23.1% vs 5.8%, p < 0.001). Readmission rate was similar between the two groups. CONCLUSION: Children presenting with acute periorbital cellulitis who have ARS tend to have more severe infection requiring higher level of care. ARS should be assessed and incorporated into the plan of care of pediatric patients with periorbital infections.

The critical role of phlebolymphedema in cellulitis associated with lymphedema: Its incidence and economic impact in a large real-world population.

OBJECTIVE: The aims of this study were: to define the incidence of cellulitis in patients with lymphedema (LED) overall and relate this to the etiology of LED; to determine how this rate might be affected by recurrence of cellulitis; and to quantify the contemporary economic burden of treatment. Understanding these factors is essential in developing targeted cellulitis prevention strategies and reducing health care costs. METHODS: The IBM MarketScan Research Database was examined from April 2013 to March 2019 for patients with a new diagnosis of LED (n = 85,601). Based on International Classification of Diseases (ICD)-9/ICD-10 diagnosis codes, the incidence and cost of cellulitis were ascertained during the 3-year follow-up period. Incidence rates (per 100 patient-years [PYs]) and cost (per patient per year) of cellulitis were evaluated among all patients with LED and within subgroups of LED etiologies. RESULTS: Among the three most common morbidities associated with LED (breast cancer-related lymphedema [BCRL], n = 17,954 [20.97%]; gynecological cancer-related LED [GCRL], n = 1256 [1.47%]; and phlebolymphedema [PLED], n = 8406 [9.82%]), rates of cellulitis were markedly lower for BCRL (8.9; 95% confidence interval [CI], 8.7-9.2) and GCRL (14.8; 95% CI, 13.4-16.4) vs PLED (47.7; 95% CI, 46.7-48.8). Patients with a history of cellulitis had markedly higher cellulitis rates during follow-up than those without-overall, 74.0% vs 16.4%; BCRL, 42.9%; 95% CI, 39.7%-46.3% vs 7.6%; 95% CI, 7.3%-7.9%; GCRL, 67.5%; 95% CI, 56.4%-80.8% vs 11.0%; 95% CI, 9.8%-12.4%; and PLED, 81.7%; 95% CI, 79.4%-84.1% vs 30.4%; 95% CI, 29.4%-31.4%, respectively. The mean $/patient/year of cellulitis-related costs for a patient with PLED ($2836; 95% CI, $2395-$3471) was significantly greater than that for BCRL ($503; 95% CI, $212-$1387) and GCRL ($609; 95% CI, $244-$1314). CONCLUSIONS: The incidence of cellulitis associated with LED varies by the etiology of LED. PLED has the highest rates of both an initial cellulitis episode and recurrent cellulitis events. Additionally, PLED has one of the largest cellulitis-related total costs per patient per year. Prevention, as well as early identification and treatment of PLED-associated cellulitis, could significantly decrease health care costs and improve patient quality of life.

Clinical diagnosis and outcome of cervicofacial cellulitis in pyrexic rabbits: six cases (2014-2021).

OBJECTIVES: To assess the signalment, history, exam findings, diagnostics, treatment and outcome of rabbits diagnosed with pyrexia and concurrent cervicofacial cellulitis. MATERIALS AND METHODS: Retrospective evaluation of medical records of rabbits diagnosed with cervicofacial cellulitis and pyrexia based on physical exam, contrast-enhanced CT, clinicopathology and microbiology findings. RESULTS: Six out of 1588 rabbits met the study inclusion criteria. Rabbits presented with a median age of 6 years (range, 8 months to 8 years) with a presenting complaint of anorexia or hyporexia. All rabbits had a rectal temperature >40.2°C (104.4°F). Physical exam and contrast-enhanced CT revealed unilateral submandibular and ipsilateral cervical diffuse soft tissue swelling in five of six rabbits. No antemortem evidence of periodontal or dental disease was found on physical exam or CT. Leucopenia was present in five of six rabbits. A left shift with marked toxic changes was present in all four rabbits, for which blood smears were reviewed. Bacterial cultures of the aspirated subcutaneous soft tissue swelling cultured Escherichia coli, Pasteurella multocida, Granulicatella adiacens, Streptococcus species, Haemophilus species and Bacteroides species. Treatment was pursued in five rabbits, where all rabbits received supportive care and four of five rabbits received systemic antibiotics. One rabbit was euthanased following a diagnosis of cervicofacial cellulitis. Three out of five rabbits continued to decline clinically despite medical management, and thus, euthanasia was pursued within 24 hours of starting treatment. Two rabbits responded to initial treatment and developed subsequent multi-focal abscessation. One rabbit was euthanased due to client cost constraints, and one rabbit died shortly after achieving clinical resolution of cervicofacial cellulitis. CLINICAL SIGNIFICANCE: Cervicofacial cellulitis should be considered a differential diagnosis in pyrexic rabbits with facial or cervical swelling with medical and surgical management pursued for therapy.