Artificial Intelligence - Perception of Clinical Laboratories' Technical Staff a Nationwide Multicentre Survey in Pakistan.

Introduction: As Artificial Intelligence (AI) technology continues to assimilate into various industries, there is a huge scope in the healthcare industry specifically in clinical laboratories. The perspective of the laboratory professionals can give valuable insight on the ideal path to take for AI implementation. Methods: The study utilized a cross-sectional survey design and was conducted at the section of Chemical Pathology, Department of Pathology and Laboratory Medicine, the Aga Khan University (AKU), Karachi, Pakistan in collaboration with Consultant Pathologists of 9 clinical laboratories associated with teaching hospitals across Pakistan from October-November 2023. The survey was for a duration of 2 weeks and was circulated to all working laboratory technical staff after informed consent. Results: A total of 351 responses were received, of which 342 (male=146, female=196) responses were recorded after exclusion. Respondents ranged from technologists, faculty, residents, and coordinators, and were from different sections (chemical pathology, microbiology, haematology, histopathology, POCT). Out of the total 312 (91.2%) of respondents stated that they were at least somewhat familiar with AI technology. Experts in AI were only 2.0% (n=7) of all respondents, but 90% (n=6) of these were < 30 years old. 76.3% (n=261) of the respondents felt the need to implement more AI technology in the laboratories, with time saving (26.1%) and improving performances of tests (17.7%) cited to be the greatest benefits of AI. Security concerns (n=144) and a fear of decreasing personal touch (n=143) were the main concerns of the respondents while the younger employees had an increased fear of losing their jobs. 76.3% were in favour of an increase in AI usage in the laboratories. Conclusion: This study highlights a favourable perspective among laboratory professionals, acknowledging the potential of AI to enhance both the efficiency and quality of laboratory practices. However, it underscores the importance of addressing their concerns in the thoughtful implementation of this emerging technology.

Spectrum of Diagnoses in Female Patients With Proctologic Symptoms Presenting to the Surgery Unit of a Tertiary Care Center.

Introduction Anorectal diseases are prevalent in the general population and may vary from benign disorders to malignant lesions that can metastasize. There is a variety of proctologic symptoms associated with each disease. The incidence of proctologic disease varies in different cultures due to dietary habits and variations in lifestyle. The present study was conducted to determine the spectrum of different proctologic diseases in female patients presenting with proctologic symptoms. Methods This cross-sectional study was conducted in the Surgery Department of Mardan Medical Complex, Mardan, and Khyber Teaching Hospital, Peshawar, from January 2022 to January 2023. Female patients with proctologic symptoms were included, while non-consenting patients were excluded. After obtaining a detailed history and examination by the experienced surgeon, digital rectal examination and proctoscopy/sigmoidoscopy were performed where necessary. Diagnoses were made, and the data regarding proctologic symptoms and their corresponding diagnoses was analyzed using Statistical Package for the Social Sciences (SPSS) version 20.0 (IBM SPSS Statistics, Armonk, NY) using mean and standard deviation for quantitative variables and frequency and percentage for qualitative variables. Results The mean age of 500 female study participants was 38.35±16.305 (range: 7-108) years. Bleeding per rectum, constipation, and pain per rectum were the commonest proctologic symptoms seen in 341 (68.2%), 287 (57.4%), and 272 (54.4%) cases, respectively. Anal fissures and hemorrhoids were the commonest proctologic diseases seen in 264 (52.8%) and 60 (12%) cases, respectively. Conclusion Bleeding per rectum is the commonest proctologic symptom in patients. Anal fissures and hemorrhoids are the commonest proctologic diseases in our setup. Bleeding per rectum and hemorrhoids in the female population cause loss of blood, which in turn will aggravate the clinical picture of underlying anemia, if any.

Full-Thickness Macular Hole: An Exceptional Case Presentation in Behçet's Disease.

Behçet's disease (BD) is a vascular disorder affecting a variety of organ systems. It is an auto-immune disease with inflammatory vasculitis that is systemic in nature, the exact etiology of which is unknown. Obliterative vasculitis, recurrent aphthous ulcers, mucocutaneous manifestations, recurrent genital ulcerations, and intraocular inflammation, especially chronic relapsing uveitis, are the characteristic features of BD. The case report presents a unique manifestation of BD in a 20-year-old Pakistani male who presents with a one-year-old history of viral encephalitis, after which he developed a blurring of vision. On examination, he had recurrent aphthous ulcers, recurrent ulcerations of genitalia, and a history of lesions of the skin. After making the patient undergo a cascade of investigations for evaluating and assessing the various signs and symptoms, a diagnosis of BD with bilateral panuveitis and a full-thickness macular hole (FTMH) in the right eye was established. Immuno-suppressants, steroids, and azathioprine were used as treatment options, following which the state of remission was attained.

Chinese stock market integration with developed world: A portfolio diversification analysis.

This study investigates integration dynamics between the Chinese stock market and major developed counterparts-Australia, Germany, Japan, the UK, and the US-focusing on portfolio diversification. Using a comprehensive analytical approach from 2012 to 2022, encompassing events like the Belt and Road Initiative, the Shanghai market crash, US-China trade tensions, and the COVID-19 pandemic, the research employs descriptive statistics, unit root tests, cointegration analysis, and VECM-based Granger Causality Tests. Findings indicate modest integration, endorsing diversified portfolios for developed country investors due to higher returns in China with acceptable risk. Unit root analysis confirms cointegration with developed indices, indicating relatively low integration. Granger Causality Tests reveal bidirectional causality, emphasizing mutual influence. Notably, no causal link exists between the US and China, possibly due to regulatory disparities and the trade war. The study enhances understanding of Chinese stock market dynamics, supporting global economic intertwining and urging further openness of China's domestic shares for economic growth.

Development and characterisation of buccal dispersible film, syrup and effervescent granules of extemporaneous antigout remedy.

Homemade medicinal remedies used to treat both acute and chronic ailments for centuries need to be transformed into modern evidence-based dosage forms. Therefore, the present study aimed to develop buccal dispersible film, syrup and effervescent granules of an extemporaneous antigout homemade remedy. The dosage forms were prepared using holistic remedy (HR) as an active entity and excipients masking disagreeable features. The dosage forms and HR were subjected to physicochemical evaluation, and standardised by a reversed-phase HPLC method using chlorogenic acid, caffeic acid, vanillin, and ferulic acid as analytical standards. The standardised dosage forms were investigated for antigout activity using an appropriate model. The dosage forms were found to be physically elegant and phytochemically aligned with HR. The developed dosage forms contained the selected markers and possessed antigout activity. Hence, these standardised and evidence-based dosage forms may have wider acceptance in the market compared to HR.

Developing a simple and efficient modeling solution for predicting key phenological stages of table grapes in a non-traditional viticulture zone in south Asia.

Phenological shifts are one of the most visible signs of climatic variability and change in the biosphere. However, modeling plant phenological responses has always been a key challenge due to climatic variability and plant adaptation. Grapevine is a phenologically sensitive crop and, thus, its developmental stages are affected by the increase in temperature. The goal of this study was to develop a temperature-based grapevine phenology model (GPM) for predicting key developmental stages for different table grape cultivars for a non-traditional viticulture zone in south Asia. Experiments were conducted in two vineyards at two locations (Chakwal and Islamabad) in the Pothawar region of Pakistan during the 2019 and 2020 growing seasons for four cultivars including Perlette, King's Ruby, Sugraone and NARC Black. Detailed phenological observations were obtained starting in January until harvest of the grapes. The Mitscherlich monomolecular equation was used to develop the phenology model for table grapes. There was a strong non-linear correlation between the Eichhorn and Lorenz phenological (ELP) scale and growing degree days (GDD) for all cultivars with coefficient of determinations (R2) ranging from 0.90 to 0.94. The results for model development indicated that GPM was able to predict phenological stages with high skill scores, i.e., a root mean square (RMSE) of 2.14 to 2.78 and mean absolute error (MAE) of 1.86 to 2.26 days. The prediction variability of the model for the onset timings of phenological stages was up to 3 days. The results also reveal that the phenology model based on GDD approach provides an efficient planning tool for viticulture industry in different grape growing regions. The proposed methodology, being a simpler one, can be easily applied to other regions and cultivars as a predictor for grapevine phenology.

Comet Assay and Micronucleus Test in Circulating Erythrocytes of Ctenopharyngodon idella Exposed to Nickel Oxide Nanoparticles.

The number of pollutants released into freshwater and marine environments has increased due to the widespread use of nanoparticles. Nickel oxide nanoparticles (NiO-NPs) were tested for genotoxicity in fish fingerlings of the species Ctenopharyngodon idella. For 7, 14, and 21 days, fingerlings were exposed to NiO-NPs with each increasing concentrations of 2.25 mg/L, 4.50 mg/L, and 6.75 mg/L, respectively. The micronuclei assay and comet assay were used to evaluate the DNA damage. The experiment revealed that with the increase in nanoparticle concentration and exposure duration, the level of DNA damage also increased. The experiment resulted to be time and dose dependent, and the damage was found as follows: 6.75 mg/L > 4.50 mg/L > 2.25 mg/L against each exposure period. In terms of comet assay, the results showed that after 7 days, the level of DNA damage in all the concentrations was highly significant (P < 0.001). Increased DNA damage was calculated at the higher administered dose of 6.75 mg/L for 21 days of exposition, followed by 14 and 7 days, respectively. The second high toxic effect was observed in the fish blood at the exposure concentration of 4.50 mg/L for 21 days, followed by 14 and 7 days, respectively. The micronuclei induction in the nanoparticle's administered blood could be detected only for a 7-day exposition period. Whereas for the exposed duration of 14 and 21 days, the entire red blood cells of the grass carp were completely destroyed demonstrating the ability of the nanoparticles to cause anomalies in aquatic life.

Factors influencing pregnancy rate and loss after laparoscopic artificial insemination with frozen-thawed semen in Lohi sheep under sub-tropical conditions.

This study evaluates factors influencing pregnancy rates per artificial insemination (P/AI) and pregnancy loss in Lohi ewes undergoing laparoscopic AI with frozen-thawed semen under sub-tropical conditions. Data from three experiments comprising ewes (n = 358) of mixed parity (nulliparous; NP and parous; P), various body condition score (BCS) and assigned to long-term (LTP, 11 days) and short-term (STP, 5 days) oestrus synchronization regimen across high breeding season (HBS) and low breeding season (LBS) were analysed. Laparoscopic insemination was conducted 54 h post-sponge removal. Pregnancy diagnosis and loss were evaluated on days 35 and 90 post-insemination via ultrasonography. Results showed parity significantly influenced P/AI, with nulliparous ewes achieving higher pregnancy ratios than parous ewes (p = .001). BCS significantly influenced P/AI (p < .05), with a quadratic relationship observed between BCS and season (BCS*BCS*Season; p = .07). Progestin treatment did not significantly influence the ratio of pregnant ewes (p = .07). Pregnancy losses were significantly higher during LBS than HBS (p < .05), irrespective of progestin treatment. In conclusion, parity and BCS significantly influenced P/AI, with BCS demonstrating a quadratic association with season. Ewes bred during LBS experienced higher pregnancy losses than HBS, irrespective of progestin treatment.

A Cautionary Note on Pembrolizumab use in Patients with Ascending Aortic Aneurysms.

Case description: We describe a case of a patient treated with pembrolizumab (an immune checkpoint inhibitor) for metastatic scalp melanoma. He had a previous history of colorectal cancer, prostatic cancer and chronic polymyalgia rheumatica. The patient was known to have a stable ascending aortic aneurysm of 4.5 cm. However, he developed a rapid expansion of the ascending aortic aneurysm with the size crossing the threshold for surgery. The patient was referred to the cardiothoracic surgery service for intervention and he subsequently underwent surgery. The patient was electively admitted one week later for resection of aortic aneurysm, aortoplasty and external graft fixation. Pathologically, gross evidence of dissection was not identified; however, the histological analysis of the media showed laminar medial necrosis, multifocal in nature, with occasional clusters of histiocytic cells appreciated at their edge reminiscent of that seen in an inflammatory aortitis (granulomatous/giant cell type). Discussion: Immune checkpoint inhibitor-induced aortitis is becoming increasingly evident, and its presentation can vary. It has been discovered incidentally on surveillance imaging with the use of nivolumab. In other cases, patients have been symptomatic to severely symptomatic. Atezolizumab with carboplatin and etoposide has been reported to cause abdominal aortitis which was responsive to corticosteroids and subsequent discontinuation of atezolizumab. Pembrolizumab has been linked to a case of transverse aortic arch aortitis. In our case, the inflammatory aortitis due to pembrolizumab was the cause of the rapid expansion of the ascending aortic aneurysm. Conclusion: Patients with known aortic aneurysms should undergo careful surveillance when commencing immune-checkpoint inhibitor therapy. LEARNING POINTS: Immune checkpoint inhibitors are being increasingly used in the treatment of metastatic malignancy. However, they are a relatively new group of medications, and the side effect profile of each is yet to be fully recognised. Aortitis has occurred with several different immune checkpoint inhibitors.Patients with known aortic aneurysms should undergo careful surveillance when commencing immune checkpoint inhibitors.All interventional therapeutic options should be considered early in these patients on the development of aneurysmal expansion.

Rutin prevents EqHV-8 induced infection and oxidative stress via Nrf2/HO-1 signaling pathway.

Introduction: The Nuclear factor erythroid 2-related factor 2 (Nrf2)/heme oxygenase-1 (HO-1) signaling pathway has been extensively studied for its role in regulating antioxidant and antiviral responses. The Equid herpesvirus type 8 (EqHV-8) poses a significant threat to the equine industry, primarily manifesting as respiratory disease, abortions, and neurological disorders in horses and donkeys. Oxidative stress is considered a key factor associated with pathogenesis of EqHV-8 infection. Unfortunately, there is currently a dearth of therapeutic interventions available for the effective control of EqHV-8. Rutin has been well documented for its antioxidant and antiviral potential. In current study we focused on the evaluation of Rutin as a potential therapeutic agent against EqHV-8 infection. Methods: For this purpose, we encompassed both in-vitro and in-vivo investigations to assess the effectiveness of Rutin in combatting EqHV-8 infection. Results and Discussion: The results obtained from in vitro experiments demonstrated that Rutin exerted a pronounced inhibitory effect on EqHV-8 at multiple stages of the viral life cycle. Through meticulous experimentation, we elucidated that Rutin's antiviral action against EqHV-8 is intricately linked to the Nrf2/HO-1 signaling pathway-mediated antioxidant response. Activation of this pathway by Rutin was found to significantly impede EqHV-8 replication, thereby diminishing the viral load. This mechanistic insight not only enhances our understanding of the antiviral potential of Rutin but also highlights the significance of antioxidant stress responses in combating EqHV-8 infection. To complement our in vitro findings, we conducted in vivo studies employing a mouse model. These experiments revealed that Rutin administration resulted in a substantial reduction in EqHV-8 infection within the lungs of the mice, underscoring the compound's therapeutic promise in vivo. Conclusion: In summation, our finding showed that Rutin holds promise as a novel and effective therapeutic agent for the prevention and control of EqHV-8 infections.

Prediction of Alzheimer's disease stages based on ResNet-Self-attention architecture with Bayesian optimization and best features selection.

Alzheimer's disease (AD) is a neurodegenerative illness that impairs cognition, function, and behavior by causing irreversible damage to multiple brain areas, including the hippocampus. The suffering of the patients and their family members will be lessened with an early diagnosis of AD. The automatic diagnosis technique is widely required due to the shortage of medical experts and eases the burden of medical staff. The automatic artificial intelligence (AI)-based computerized method can help experts achieve better diagnosis accuracy and precision rates. This study proposes a new automated framework for AD stage prediction based on the ResNet-Self architecture and Fuzzy Entropy-controlled Path-Finding Algorithm (FEcPFA). A data augmentation technique has been utilized to resolve the dataset imbalance issue. In the next step, we proposed a new deep-learning model based on the self-attention module. A ResNet-50 architecture is modified and connected with a self-attention block for important information extraction. The hyperparameters were optimized using Bayesian optimization (BO) and then utilized to train the model, which was subsequently employed for feature extraction. The self-attention extracted features were optimized using the proposed FEcPFA. The best features were selected using FEcPFA and passed to the machine learning classifiers for the final classification. The experimental process utilized a publicly available MRI dataset and achieved an improved accuracy of 99.9%. The results were compared with state-of-the-art (SOTA) techniques, demonstrating the improvement of the proposed framework in terms of accuracy and time efficiency.

SEM and LM insights: Spore morphology and its taxonomic significance in Sino Himalayan, Malesian, and European elements of Pteridaceae.

The Pteridaceae family, known for its taxonomic complexity, presents challenges in identification due to high variability among its species. This study investigates the spore morphology employing both SEM and LM techniques in 10 Pteridaceae taxa phytogeographicaly Sino-Himalayan, Malesian, and European elements in Pakistan. The taxa include Adiantum capillus-veneris, A. incisum, A. venustum, Aleuritopteris bicolor, Oeosporangium nitidulum, O. pteridioides, Onychium cryptogrammoides, O. vermae, Pteris cretica, and P. vittata. The objective is to assess their taxonomic relevance and develop a spore-based taxonomic key. Findings indicate differences in spore shape, sizes, exospore thickness, and in surface ornamentation highlighting the potential for taxonomic differentiation. Spores are trilete, and notable differences are observed in the dimension of spores in both distal and proximal sides. Equatorial dimensions vary between 35 and 50 µm, while the polar diameter ranges from 29 to 50 µm. SEM revealed different spore ornamentation types that show several useful characteristics establishing valuable taxonomic variations. The studied Adiantum taxa feature a perispore with tubercules and a micro-granulose surface. The spores of examined Oeosporangium and Aleuritopteris taxa shows cristate sculptures with variable ornamentations. Both species of Onychium have tuberculate-pleated tubercles with sinuous folds on both distal and proximal sides. The surface ornamentation among examined Pteris taxa show variability. PCA analysis indicated that spore quantitative data identified distinct groups, underscoring taxonomic significance. Nevertheless, there was variation observed in surface ornamentation and spore shape, indicating the potential for discrimination among taxa. RESEARCH HIGHLIGHTS: Spore morphology of 10 Pteridaceae taxa has been investigated through LM and SEM. Investigated species shows differences in spore shape, sizes, exospore thickness, and in surface ornamentation. Ornamentation on the perispore provides several valuable characteristics, establishing useful taxonomic distinctions. Spore morphological analysis is effective at the generic level, with minor distinctions discernible at the species level.

Association of county-level provider density and social vulnerability with colorectal cancer-related mortality.

BACKGROUND: Health care providers play a crucial role in increasing overall awareness, screening, and treatment of cancer, leading to reduced cancer mortality. We sought to characterize the impact of provider density on colorectal cancer population-level mortality. METHODS: County-level provider data, obtained from the Area Health Resource File between 2016 and 2018, were used to calculate provider density per county. These data were merged with county-level colorectal cancer mortality 2016-2020 data from the Centers for Disease Control and Prevention. Multivariable regression was performed to define the association between provider density and colorectal cancer mortality. RESULTS: Among 2,863 counties included in the analytic cohort, 1,132 (39.5%) and 1,731 (60.5%) counties were categorized as urban and rural, respectively. The colorectal cancer-related crude mortality rate was higher in counties with low provider density versus counties with moderate or high provider density (low = 22.9, moderate = 21.6, high = 19.3 per 100,000 individuals; P < .001). On multivariable analysis, the odds of colorectal cancer mortality were lower in counties with moderate and high provider density versus counties with low provider density (moderate odds ratio 0.97, 95% confidence interval 0.94-0.99; high odds ratio 0.88, 95% confidence interval 0.86-0.91). High provider density remained associated with a lower likelihood of colorectal cancer mortality independent of social vulnerability index (low social vulnerability index and high provider density: odds ratio 0.85, 95% confidence interval 0.81-0.89; high social vulnerability index and high provider density: odds ratio 0.93, 95% confidence interval 0.89-0.98). CONCLUSION: Regardless of social vulnerability index, high county-level provider density was associated with lower colorectal cancer-related mortality. Efforts to increase access to health care providers may improve health care equity, as well as long-term cancer outcomes.

Unlocking the Hidden Pathway: A Rare Encounter With Right Coronary Artery Fistula to Coronary Sinus and Right Ventricle.

Coronary artery fistulas (CAFs) are rare vascular anomalies characterized by abnormal connections between coronary arteries and cardiac chambers or adjacent structures. Advances in cardiac interventions have led to an increasing recognition of acquired CAFs, which are typically congenital. We present a case of a 62-year-old male with a complex medical history, including hypertension, atrial fibrillation, and heart failure, who presented with exertional chest pain and palpitations. Diagnostic evaluation revealed a significant CAF originating from the right coronary artery (RCA) and terminating into the coronary sinus and right ventricle. Despite the absence of significant coronary artery occlusions, the fistula was deemed clinically significant due to its potential to cause myocardial ischemia. Management involved guideline-directed medical therapy and lifestyle modifications. This case underscores the importance of early recognition and appropriate management of CAFs to optimize patient outcomes. Further research is needed to better understand the natural history and optimal management strategies of CAFs.

Angiogenic protein profiling, phytochemical screening and in silico anti-cancer targets validation of stem, leaves, fruit, and seeds of Calotropis procera in human liver and breast cancer cell lines.

The main focus of anticancer drug discovery is on developing medications that are gentle on normal cells and should have the ability to target multiple anti-cancer pathways. Liver cancer is becoming a worldwide epidemic due to the highest occurring and reoccurring rate in some countries. Calotropis procera is a xerophytic herbal plant growing wildly in Saudi Arabia. Due to its anti-angiogenic and anticancer capabilities, "C. procera " is a viable option for developing innovative anticancer medicines. However, no study has been done previously, to discover angiogenic and anti-cancer targets which are regulated by C. procera in liver cancer. In this study, leaves, stems, flowers, and seeds of C. procera were used to prepare crude extracts and were fractionated into four solvents of diverse polarities. These bioactivity-guided solvent fractions helped to identify useful compounds with minimal side effects. The phytoconstituents present in the leaves and stem were identified by GC-MS. In silico studies were done to predict the anti-cancer targets by major bioactive constituents present in leaves and stem extracts. A human angiogenesis antibody array was performed to profile novel angiogenic targets. The results from this study showed that C. procera extracts are an ideal anti-cancer remedy with minimum toxicity to normal cells as revealed by zebrafish in vivo toxicity screening assays. The novel antiangiogenic and anticancer targets identified in this study could be explored to design medication against liver cancer.

Assessment and classification of COVID-19 DNA sequence using pairwise features concatenation from Multi-Transformer and deep features with Machine Learning models.

The 2019 novel coronavirus (renamed SARS-CoV-2, and generally referred to as the COVID-19 virus) has spread to 184 countries with over 1.5 million confirmed cases. Such a major viral outbreak demands early elucidation of taxonomic classification and origin of the virus genomic sequence, for strategic planning, containment, and treatment. The emerging global infectious COVID-19 disease by novel Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) presents critical threats to global public health and the economy since it was identified in late December 2019 in China. The virus has gone through various pathways of evolution. Due to the continued evolution of the SARS-CoV-2 pandemic, researchers worldwide are working to mitigate, suppress its spread, and better understand it by deploying deep learning and machine learning approaches. In a general computational context for biomedical data analysis, DNA sequence classification is a crucial challenge. Several machine and deep learning techniques have been used in recent years to complete this task with some success. The classification of DNA sequences is a key research area in bioinformatics as it enables researchers to conduct genomic analysis and detect possible diseases. In this paper, three state-of-the-art deep learning-based models are proposed using two DNA sequence conversion methods. We also proposed a novel multi-transformer deep learning model and pairwise features fusion technique for DNA sequence classification. Furthermore, deep features are extracted from the last layer of the multi-transformer and used in machine-learning models for DNA sequence classification. The k-mer and one-hot encoding sequence conversion techniques have been presented. The proposed multi-transformer achieved the highest performance in COVID DNA sequence classification. Automatic identification and classification of viruses are essential to avoid an outbreak like COVID-19. It also helps in detecting the effect of viruses and drug design.

Machine-Learning Models for Diagnosis of Rotator Cuff Tears in Osteoporosis Patients Based on Anteroposterior X-rays of the Shoulder Joint.

OBJECTIVE: This study aims to diagnose Rotator Cuff Tears (RCT) and classify the severity of RCT in patients with Osteoporosis (OP) through the analysis of shoulder joint anteroposterior (AP) X-ray-based localized proximal humeral bone mineral density (BMD) measurements and clinical information based on machine learning (ML) models. METHODS: A retrospective cohort of 89 patients was analyzed, including 63 with both OP and RCT (OPRCT) and 26 with OP only. The study analyzed a series of shoulder radiographs from April 2021 to April 2023. Grayscale values were measured after plotting ROIs based on AP X-rays of shoulder joint. Five kinds of ML models were developed and compared based on their performance in predicting the occurrence and severity of RCT from ROIs' greyscale values and clinical information (age, gender, advantage side, lumbar BMD, and acromion morphology (AM)). Further analysis using SHAP values illustrated the significant impact of selected features on model predictions. RESULTS: R1-6 had a positive correlation with BMD respectively. The nine variables, including greyscale R1-6, age, BMD, and AM, were used in the prediction models. The RF model was determined to be superior in effectively diagnosing RCT in OP patients, with high AUC scores of 0.998, 0.889, and 0.95 in the training, validation, and testing sets, respectively. SHAP values revealed that the most influential factors on the diagnostic outcomes were the grayscale values of all cancellous bones in ROIs. A column-line graph prediction model based on nine variables was constructed, and DCA curves indicated that RCT prediction in OP patients was favored based on this model. Furthermore, the RF model was also the most superior in predicting the types of RCT within the OPRCT group, with an accuracy of 86.364% and 73.684% in the training and test sets, respectively. SHAP values indicated that the most significant factor affecting the predictive outcomes was the AM, followed by the grayscale values of the greater tubercle, among others. CONCLUSIONS: ML models, particularly the RF algorithm, show significant promise in diagnosing RCT occurrence and severity in OP patients using conventional shoulder X-rays based on the nine variables. This method presents a cost-effective, accessible, and non-invasive diagnostic strategy that has the potential to substantially enhance the early detection and management of RCT in OP patient population.

Impact of an artificial intelligence based model to predict non-transplantable recurrence among patients with hepatocellular carcinoma.

OBJECTIVE: We sought to develop Artificial Intelligence (AI) based models to predict non-transplantable recurrence (NTR) of hepatocellular carcinoma (HCC) following hepatic resection (HR). METHODS: HCC patients who underwent HR between 2000-2020 were identified from a multi-institutional database. NTR was defined as recurrence beyond Milan Criteria. Different machine learning (ML) and deep learning (DL) techniques were used to develop and validate two prediction models for NTR, one using only preoperative factors and a second using both preoperative and postoperative factors. RESULTS: Overall, 1763 HCC patients were included. Among 877 patients with recurrence, 364 (41.5%) patients developed NTR. An ensemble AI model demonstrated the highest area under ROC curves (AUC) of 0.751 (95% CI: 0.719-0.782) and 0.717 (95% CI:0.653-0.782) in the training and testing cohorts, respectively which improved to 0.858 (95% CI: 0.835-0.884) and 0.764 (95% CI: 0.704-0.826), respectively after incorporation of postoperative pathologic factors. Radiologic tumor burden score and pathological microvascular invasion were the most important preoperative and postoperative factors, respectively to predict NTR. Patients predicted to develop NTR had overall 1- and 5-year survival of 75.6% and 28.2%, versus 93.4% and 55.9%, respectively, among patients predicted to not develop NTR (p < 0.0001). CONCLUSION: The AI preoperative model may help inform decision of HR versus LT for HCC, while the combined AI model can frame individualized postoperative care (https://altaf-pawlik-hcc-ntr-calculator.streamlit.app/).

Impact of early primary care physician follow-up on hospital readmission following gastrointestinal cancer surgery.

BACKGROUND: We sought to examine the association between primary care physician (PCP) follow-up on readmission following gastrointestinal (GI) cancer surgery. METHODS: Patients who underwent surgery for GI cancer were identified using the Surveillance, Epidemiology and End Results (SEER) database. Multivariable regression was performed to examine the association between early PCP follow-up and hospital readmission. RESULTS: Among 60 957 patients who underwent GI cancer surgery, 19 661 (32.7%) visited a PCP within 30-days after discharge. Of note, patients who visited PCP were less likely to be readmitted within 90 days (PCP visit: 17.4% vs. no PCP visit: 28.2%; p < 0.001). Median postsurgical expenditures were lower among patients who visited a PCP (PCP visit: $4116 [IQR: $670-$13 860] vs. no PCP visit: $6700 [IQR: $870-$21 301]; p < 0.001). On multivariable analysis, PCP follow-up was associated with lower odds of 90-day readmission (OR: 0.52, 95% CI: 0.50-0.55) (both p < 0.001). Moreover, patients who followed up with a PCP had lower risk of death at 90-days (HR: 0.50, 95% CI: 0.40-0.51; p < 0.001). CONCLUSION: PCP follow-up was associated with a reduced risk of readmission and mortality following GI cancer surgery. Care coordination across in-hospital and community-based health platforms is critical to achieve optimal outcomes for patients.