Improving Skin cancer Management with ARTificial Intelligence (SMARTI): protocol for a preintervention/postintervention trial of an artificial intelligence system used as a diagnostic aid for skin cancer management in a specialist dermatology setting

IntroductionConvolutional neural networks (CNNs) can diagnose skin cancers with impressive accuracy in experimental settings, however, their performance in the real-world clinical setting, including comparison to teledermatology services, has not been validated in prospective clinical studies.Methods and analysisParticipants will be recruited from dermatology clinics at the Alfred Hospital and Skin Health Institute, Melbourne. Skin lesions will be imaged using a proprietary dermoscopic camera. The artificial intelligence (AI) algorithm, a CNN developed by MoleMap Ltd and Monash eResearch, classifies lesions as benign, malignant or uncertain. This is a preintervention/postintervention study. In the preintervention period, treating doctors are blinded to AI lesion assessment. In the postintervention period, treating doctors review the AI lesion assessment in real time, and have the opportunity to then change their diagnosis and management. Any skin lesions of concern and at least two benign lesions will be selected for imaging. Each participant’s lesions will be examined by a registrar, the treating consultant dermatologist and later by a teledermatologist. At the conclusion of the preintervention period, the safety of the AI algorithm will be evaluated in a primary analysis by measuring its sensitivity, specificity and agreement with histopathology where available, or the treating consultant dermatologists’ classification. At trial completion, AI classifications will be compared with those of the teledermatologist, registrar, treating dermatologist and histopathology. The impact of the AI algorithm on diagnostic and management decisions will be evaluated by: (1) comparing the initial management decision of the registrar with their AI-assisted decision and (2) comparing the benign to malignant ratio (for lesions biopsied) between the preintervention and postintervention periods.Ethics and disseminationHuman Research Ethics Committee (HREC) approval received from the Alfred Hospital Ethics Committee on 14 February 2019 (HREC/48865/Alfred-2018). Findings from this study will be disseminated through peer-reviewed publications, non-peer reviewed media and conferences.Trial registration numberNCT04040114.

Targeted muscle reinnervation in quadruple amputees: self-reported outcomes

Targeted muscle reinnervation (TMR) reduces pain and physical and psychological disabilities in amputees. We present the first two cases reported globally of quadruple amputees that underwent acute TMR. Each patient completed our novel ‘The Alfred Hospital Osteointegration Survey’ (TAHOS) for each limb at six, 12 and 24 months post amputation which evaluated aspects of prosthesis wear, neuroma-related residual limb pain (RLP), phantom limb pain (PLP) and overall function. Our findings that TMR reduced or eliminated RLP and PLP by 12 months and clinically improved prosthetic function in both quadruple amputees reflects the current literature for single and multiple limb amputees.

Dr Himson Tamur Mulas, the first national specialist anaesthetist in Papua New Guinea

Dr Himson Tamur Mulas was born on the Gazelle Peninsula of East New Britain, New Guinea, on 13 March 1934. After finishing his schooling, he was selected to go to Fiji to undertake a medical course at Fiji Central Medical School in 1953, returning to New Guinea in 1958. He successfully completed residency posts and after a period of training in anaesthesia in Port Moresby, was sent to the Alfred Hospital in Melbourne, Australia, in 1966–1967 to further his anaesthetic career. After returning to New Guinea he undertook several administrative posts as well as continuing his anaesthetic career before settling at Nonga Hospital in Rabaul, East New Britain Province. He was first registered as a specialist anaesthetist in 1972. He went on to complete a Diploma in Public Health in New Zealand in 1974, and in 1976 completed a Diploma in Tropical Health and Hygiene at the University of Sydney. He left public hospital anaesthetic practice in 1980. He is recognised as the first New Guinean to be a specialist anaesthetist. He died on 28 July 2000 aged 66 years.

Low volume ECMO results study

Objectives: To report extracorporeal membrane oxygenation (ECMO) experience at Princess Alexandra and Gold Coast University hospitals and compare mortality with benchmarks. Design: Case series of patients treated with ECMO. Setting: Two adult tertiary Australian intensive care units with low ECMO case volumes. Participants: Patients treated with ECMO, aged > 18 years. Main outcome measures: Patients were categorised into respiratory, cardiac, and extracorporeal cardiopulmonary resuscitation (eCPR) groups. Observed mortality was compared with mortality predicted using individual risk of death predictions from the Survival after Veno-arterial ECMO (SAVE) and Respiratory ECMO Survival Prediction (RESP) scores; mortality predicted when mortality predictions of the SAVE score were modified to be consistent with the validation cohort in the SAVE study (Alfred Hospital); and with mortality predicted when eCPR patients were all assigned a risk of death equal to Extracorporeal Life Support Organization (ELSO) Registry eCPR mortality. Results: Over 10 years, 86 patients were treated with ECMO. Eight deaths were observed in 49 patients with respiratory failure, below the 95% CI (13–24) for the deaths predicted by the RESP score (P < 0.001). Nine deaths were observed in 27 patients with cardiac failure, below the 95% CI (14–23) for the deaths predicted by the SAVE score (P < 0.001), but within the 95% CI (9–17) for the deaths predicted by the SAVE score modified to be consistent with the Alfred Hospital cohort (P > 0.05). Seven deaths were observed in the ten eCPR patients, within the 95% CI (4–10) predicted using the risk of death derived from the ELSO Registry. Conclusions: Mortality in two low volume ECMO centres was not inferior to benchmarks.

Malignant Clonal Cell Proliferation in Multiple Myeloma and the Hypercoagulable State

Introduction: The malignant clonal cell proliferation in multiple myeloma (MM) results in significant immune dysregulation through clonal specific T cell expansion, elevated levels of CD4+ CD25+FOXP3+ T regulator cells, downregulation of NK cells, high levels of IL-6 and activation of immunosuppressive tumour associated macrophages (TAM) . However, the mechanisms underlying the hypercoagulable state in MM and predisposing to venous thromboembolic (VTE) complications is unclear. Confounding disease factors is the use of immunomodulatory drugs (IMiDs) such as Lenalidomide, Thalidomide and Pomalidomide causing ubiquitination and degradation of the Ikaros Family Zinc Finger Protein (IKZF)1 and 3 by cereblon which also contributes to the prothrombotic effect despite thromboprophylaxis. Aims: The aim of this study was to analyse the changes in the coagulation profile and plasma cell disease burden with treatment, including Lenalidomide, in patients with MM to help define potential underlying mechanisms for hypercoagulability and thrombosis. Methods: Coagulation profiles and disease markers were retrospectively analysed in 16 MM patients receiving treatment with Daratumumab, Lenalidomide and Dexamethasone (DRd) at The Alfred Hospital, Melbourne from April 2019 to August 2020. Patients enrolled were transplant eligible with MM that was refractory to initial induction therapy with Velcade, Cyclophosphamide and Dexamethasone (VCD). This study was approved by The Alfred Hospital ethics committee. Statistical analysis was performed using descriptive statistics and the Wilcoxon Sign Rank Test to compare the median coagulation profiles and disease markers after 1-2 cycles of DRd and 3-4 cycles of DRd. Biomarkers included Prothrombin Time (PT), Partial Thromboplastin Time (PTT), Fibrinogen, Thrombin Clotting Time (TCT), serum paraprotein (SPEP) and serum free light chain (SFLC) with a p value of &lt;0.05 indicating statistical significance. Results: A total 7 patients had coagulation profiles at the two time points i) post 1-2 cycles and ii) post 3-4 cycles of DRd (Table 1). 9 patients had coagulation profiles only after 3-4 cycles of DRd. A separate analysis was performed using Wilcoxon Sign Rank with imputed median differences to allow the inclusion of the 9 additional patients subsequently increasing the sample size to a total of 16 (Table 2). All patients were on anticoagulation with aspirin (n=14), rivaroxaban (n=1) or clopidogrel (n=1) at the time of the analysis. The analysis showed a statistically significant reduction in PT from median 13.6s (11.9-16.6) to 12.7s (11.7-14.1) with 3-4 cycles DRd in both analysis (p=0.006 and p= 0.027). Fibrinogen levels reduced from median of 5.4 g/L (2.8-8) to 3.98 g/L (2.3- 5.1) after 3-4 cycles (p=0.001). TCT increased after 3-4 cycles of DRd (p=0.005). Serum paraprotein demonstrated statistically significant reduction from 10.8g/L (6 -13) to 7.6 g/L (2-13) after 3-4 cycles (p=0.007). Serum free light chain assay also demonstrated reduction in median values from 82.8mg/L (8.1 - 415.7) to 54.6mg/L (0.8 - 338.6) but was not statistically significant (p=0.084). Discussion: All the patients in this study either responded to treatment or had stable disease after treatment with DRd. The data demonstrate a coagulation response to treatment. The median fibrinogen level that was above the upper limit of normal declined on treatment, the TCT increased and the PT decreased, all coinciding with the statistically significant decline in paraprotein level. A larger study is required to confirm these findings. However, this study has demonstrated that the hypercoagulable state in MM improves with disease response. Disclosures Spencer: Roche: Consultancy, Honoraria; Pfizer: Consultancy, Honoraria; Pharmamar: Other; Secura Bio: Consultancy, Honoraria; Sanofi: Consultancy, Honoraria; Servier: Consultancy, Other: Grant/Research Support; Janssen: Consultancy, Honoraria, Other: Grant/Research Support, Speakers Bureau; Haemalogix: Consultancy, Honoraria, Other: Grant/Research Support; BMS: Honoraria, Other: Grant/Research Support, Research Funding, Speakers Bureau; TheraMyc: Consultancy, Honoraria; Amgen: Consultancy, Honoraria, Other: Grant/Research Support; Takeda: Honoraria, Other, Speakers Bureau; Antegene: Consultancy, Honoraria; Abbvie: Consultancy, Honoraria, Other: Grant/Research Support.