Shaukat Khanum Memorial Cancer Hospital and Research Centre

Primary spinal cord tumors (PSCTs) are rare in children, accounting for 2–4

Recently, histopathology vision-language foundation models (VLMs) have gained popularity due to their enhanced performance and generalizability across different downstream tasks. However, most existing histopathology benchmarks are either unimodal or limited in terms of diversity of clinical tasks, organs, and acquisition instruments, as well as their partial availability to the public due to patient data privacy. As a consequence, there is a lack of comprehensive evaluation of existing histopathology VLMs on a unified benchmark setting that better reflects a wide range of clinical scenarios. To address this gap, we introduce HistoVL, a fully open-source comprehensive benchmark comprising images acquired using up to 11 various acquisition tools that are paired with specifically crafted captions by incorporating class names and diverse pathology descriptions. Our Histo-VL includes 26 organs, 31 cancer types, and a wide variety of tissue obtained from 14 heterogeneous patient cohorts, totaling more than 5 million patches obtained from over 41K WSIs viewed under various magnification levels. We systematically evaluate existing histopathology VLMs on Histo-VL to simulate diverse tasks performed by experts in real-world clinical scenarios. Our analysis reveals interesting findings, including large sensitivity of most existing histopathology VLMs to textual changes with a drop in balanced accuracy of up to 25 Metastasis detection, low robustness to adversarial attacks, as well as improper calibration of models evident through high ECE values and low model prediction confidence, all of which can affect their clinical implementation.

Large Language Models (LLMs) hold the potential for clinical task-shifting by processing unstructured clinical text, enabling tasks such as clinical concept extraction and medical question answering from electronic health records. If implemented reliably, such approaches may benefit over-burdened healthcare systems, particularly in resource-limited settings and for traditionally overlooked populations, provided that local fine-tuning is supported by appropriate clinical and technical expertise. However, this powerful technology remains largely understudied in real-world contexts, particularly in the Global South. This study aims to assess whether openly available LLMs can be used reliably for processing medical notes in real-world settings in South Asia. We used publicly available LLMs to parse de-identified clinical notes from a large electronic health records (EHR) database in Pakistan, containing hospital records for 8.2 million patients. ChatGPT (GPT-3.5) as a general-purpose LLM, and GatorTron (base), BioMegatron, BioBert and ClinicalBERT as medical LLMs were evaluated when applied to these data, after fine-tuning them with (a) publicly available clinical datasets namely Informatics for Integrating Biology the Bedside (I2B2) and National NLP Clinical Challenges (N2C2) for medical concept extraction (MCE) and emrQA for medical question answering (MQA), and (b) the local Pakistani de-identified EHR dataset, which includes inpatient Discharge Summaries (DS) and Subjective, Objective, Assessment, and Plan (SOAP) notes, as detailed in this paper. MCE models were applied to these clinical notes using both 3-label and 9-label formats, while MQA models were applied to medical questions. Internal and external validation performance was measured for (a) and (b) using F1 score, precision, recall, and accuracy for MCE and BLEU and ROUGE-L, which measure lexical and sequence similarity, for MQA. When clinical LLMs were not fine-tuned on the local EHR dataset, their performance during external validation on local data was notably poorer compared to internal validation on the dataset used for fine-tuning, with reductions of at least 15

Awake craniotomy facilitates real-time assessment of neurological function and maximises the extent of tumour resection, reducing the risk of postoperative deficits. Awake craniotomy is uncommonly performed in young children. To our knowledge, we report the youngest case of awake craniotomy in medical literature, involving a 6-year-old child. He had a right frontoparietal tumour and a 4-year history of drug-resistant epilepsy. As the tumour was located in an eloquent brain area, an awake craniotomy was planned. Pre-operative preparation included psychological assessment, theatre environment simulation and interpreter-assisted counselling. An asleep-awake-asleep technique was employed. Maximum safe resection was achieved without haemodynamic instability. The patient remained neurologically intact postoperatively, with no speech or motor deficits. Postoperative magnetic resonance imaging demonstrated satisfactory resection. Psychological follow-up confirmed no distress or significant recall of the surgery. He was discharged seizure-free and without any deficit on postoperative day 4. This case shows that with thorough preparation and multidisciplinary teamwork, awake craniotomy is feasible and well tolerated even in very young paediatric patients.

We report an unusual manifestation of hydatid disease, presenting as a progressively enlarging, painless swelling in the right infraclavicular region. Imaging studies revealed a large necrotic mass extending into the superior mediastinum with the destruction of the adjacent right sternoclavicular joint; this was initially suspected to be thyroidal in origin. However, histopathological examination was consistent with a ruptured hydatid cyst, and Echinococcus serology was positive. Due to anatomical considerations, surgical intervention was not pursued, and the patient was managed with oral anthelmintic therapy, resulting in partial radiological response after 12 weeks of therapy. This case underscores the importance of considering hydatid disease as a differential diagnosis, even with atypical anatomical involvement. It also highlights the potential role of medical management alone as a viable alternative when surgery is not feasible.