A machine learning model for colorectal liver metastasis post-hepatectomy prognostications.

Background: Currently, surgical resection is the mainstay for colorectal liver metastases (CRLM) management and the only potentially curative treatment modality. Prognostication tools can support patient selection for surgical resection to maximize therapeutic benefit. This study aimed to develop a survival prediction model using machine learning based on a multicenter patient sample in Hong Kong. Methods: Patients who underwent hepatectomy for CRLM between 1 January 2009 and 31 December 2018 in four hospitals in Hong Kong were included in the study. Survival analysis was performed using Cox proportional hazards (CPH). A stepwise selection on Cox multivariable models with Least Absolute Shrinkage and Selection Operator (LASSO) regression was applied to a multiply-imputed dataset to build a prediction model. The model was validated in the validation set, and its performance was compared with that of Fong Clinical Risk Score (CRS) using concordance index. Results: A total of 572 patients were included with a median follow-up of 3.6 years. The full models for overall survival (OS) and recurrence-free survival (RFS) consist of the same 8 established and novel variables, namely colorectal cancer nodal stage, CRLM neoadjuvant treatment, Charlson Comorbidity Score, pre-hepatectomy bilirubin and carcinoembryonic antigen (CEA) levels, CRLM largest tumor diameter, extrahepatic metastasis detected on positron emission-tomography (PET)-scan as well as KRAS status. Our CRLM Machine-learning Algorithm Prognostication model (CMAP) demonstrated better ability to predict OS (C-index =0.651), compared with the Fong CRS for 1-year (C-index =0.571) and 5-year OS (C-index =0.574). It also achieved a C-index of 0.651 for RFS. Conclusions: We present a promising machine learning algorithm to individualize prognostications for patients following resection of CRLM with good discriminative ability.

Operative management of midshaft clavicle fractures demonstrates better long-term outcomes: A systematic review and meta-analysis of randomised controlled trials.

INTRODUCTION: Midshaft clavicular fractures are common amongst young adults. Conservative or surgical treatment for definitive fracture management has been widely debate, both with their pros and cons. Previous meta-analyses compared the clinical outcomes between conservative and surgical treatment options of midshaft clavicular fractures but failed to elucidate any difference in functional improvement. We postulate that functional improvement after fracture union plateaus and the clinical outcome after treatment varies at different time points. This meta-analysis will focus on the synthesis comparison of outcomes at early, short-term results (3 months), intermediate-term (6 to 12 months) and long-term (>24 months) clinical outcomes. METHODS: A systematic search was done on databases (Pubmed, Embase, Medline, Cochrane) in June 2021. Search keywords were: midshaft clavicular fractures and clinical trials. Clinical trials fulfilling the inclusion criteria were selected for comparison and the clinical outcomes of midshaft clavicular fractures using surgical and non-surgical interventions in terms of improvement in the Disabilities of the Arm, Shoulder and Hand (DASH) score, Constant-Murley Score (CMS), time to union and risk ratio of treatment related complications were analysed in correlation with post-treatment timeframe. RESULTS: Of the 3094 patients of mean age 36.7 years in the 31 selected studies, surgical intervention was associated with improved DASH score (standard-mean difference SMD -0.22, 95% CI -0.36 to -0.07, p = 0.003; mean difference MD -1.72, 95% CI -2.93 to -0.51, p = 0.005), CMS (SMD 0.44, 95% CI 0.17-0.72, p = 0.001; MD 3.64, 95% CI 1.09 to 6.19, p = 0.005), time to union (non-adjusted SMD -2.83, 95% CI -4.59 to -1.07, p = 0.002; adjusted SMD -0.69, 95% CI -0.97 to -0.41, p<0.001) and risk ratio of bone-related complications including bone non-union, malunion and implant failure (0.21, 95% CI 0.1 to 0.42; p<0.001). Subgroup analysis based on time period after treatment showed that surgical intervention was far superior in terms of improved DASH score at the intermediate-term results (6-12 months later, SMD -0.16, 95% CI -0.30 to -0.02, p = 0.02; and long term results (>24 months SMD -4.24, 95% CI -7.03 to -1.45, p = 0.003) and CMS (>24 months, SMD 1.03, 95% CI 0.39 to 1.68, p = 0.002; MD 5.77, 95% CI 1.63 to 9.91, p = 0.006). Surgical outcome is independent of fixation with plates or intra-medullary nails. CONCLUSION: Surgical intervention was associated with better clinical outcomes compared with non-surgical approach for midshaft clavicular fractures in terms of improvement in functional scores DASH, CMS, time to union and fracture related complications, although not to the minimal clinically significant difference. Benefits in the long-term functional improvements are more pronounced.

A cross-sectional study on the attitudes and perceptions of outpatients towards palliative care at the Hong Kong Queen Mary Hospital Hospice Centre.

BACKGROUND: Palliative care aims to improve the quality of life for patients and their families, by helping them to cope with problems associated with illness. It targets four aspects of health: physical, psychological, social, and spiritual. Most of the current literature on palliative care is limited to the perspectives of health professionals. This study aims to investigate the views of outpatients receiving palliative care at the Hong Kong Queen Mary Hospital Hospice Centre (HKQMHHC), which offers palliative care services to cancer patients. METHODS: This observational cross-sectional study was performed with the completion of a single paper- based original questionnaire over 18 afternoon clinic sessions on Thursdays and Fridays from December 2017 to February 2018 at the HKQMHHC. The questionnaire was designed to examine patients' perspectives; in particular, the Edmonton Symptom Assessment Scale (ESAS) was used to assess their symptoms. Descriptive and univariate analyses were performed. RESULTS: One hundred patients attending HKQMHHC were included in the study. The study revealed that all the mean scores for aspects of care offered at the centre were above 8, on a scale of 0-10 with 0 being extremely inadequate and 10 being extremely adequate. Each respondent was able to identify an average of 1.82 of the 4 aspects of palliative care. Eighty-seven percent of respondents perceived the physical aspect of this care to be of the highest priority. A negative correlation (P<0.05) was found between the extent of symptoms experienced by the patient and their satisfaction towards the services offered. CONCLUSIONS: Patients generally held very positive attitudes, reflecting that the services sufficiently met their needs. However, owing to their rather limited knowledge, this may have restricted their perspectives to a largely superficial level, as many discerned palliative care to be simply targeting physical health with medical consultations. Considering the implications of the results, the addition of accessibility and education components to Hong Kong's current system of palliative care is crucial in the betterment of such services for patients. There should also be increased local coverage of palliative care services to facilitate convenience of access. With reference to the World Health Organisation (WHO) palliative care model, the inclusion of a continued spectrum of services, such as physical and mental health activities and psychosocial counselling, should be reinforced throughout the progression of disease so as to better help patients to cope with illness. The discovery of the relationship between extent of symptoms experienced and patients' satisfaction towards services provided is a new direction for further study.