Article
Mathematical & Computational Biology
Richard D. Riley, Thomas P. A. Debray, Gary S. Collins, Lucinda Archer, Joie Ensor, Maarten van Smeden, Kym I. E. Snell
Summary: External validation is crucial in examining the performance of prediction models, but current studies often face issues with small sample sizes. To address this, determining the minimum sample size needed for a new external validation study with precise estimation calculations is proposed, taking into account calibration, discrimination, and clinical utility measures.
STATISTICS IN MEDICINE
(2021)
Article
Health Care Sciences & Services
Menelaos Pavlou, Chen Qu, Rumana Z. Omar, Shaun R. Seaman, Ewout W. Steyerberg, Ian R. White, Gareth Ambler
Summary: This paper investigates the sample size requirements for validation studies with binary outcomes to estimate measures of predictive performance, providing various estimators which perform well even when normality assumptions are violated. Our estimators show good performance, even when normality assumptions are violated.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2021)
Article
Mathematical & Computational Biology
Lucinda Archer, Kym I. E. Snell, Joie Ensor, Mohammed T. Hudda, Gary S. Collins, Richard D. Riley
Summary: Clinical prediction models offer personalized outcome predictions for patient counseling and decision making, with external validation crucial for assessing model performance. Proposed criteria aim to determine minimum sample size needed for external validation of a clinical prediction model, considering factors like proportion of variance explained and agreement between predicted and observed values. The recommendations provide a framework for estimating precision and ensuring adequate sample sizes in future validation studies.
STATISTICS IN MEDICINE
(2021)
Article
Health Care Sciences & Services
Toshihiko Takada, Steven Nijman, Spiros Denaxas, Kym I. E. Snell, Alicia Uijl, Tri-Long Nguyen, Folkert W. Asselbergs, Thomas P. A. Debray
Summary: This study aimed to evaluate the need for complex strategies in developing generalizable prediction models in large clustered datasets, using Cox regression models to estimate the risk of heart failure. The results showed that simple prediction models performed well in discrimination and calibration, with complex strategies not significantly improving the outcomes.
JOURNAL OF CLINICAL EPIDEMIOLOGY
(2021)
Article
Mathematical & Computational Biology
Richard D. Riley, Gary S. Collins, Joie Ensor, Lucinda Archer, Sarah Booth, Sarwar Mozumder, Mark J. Rutherford, Maarten van Smeden, Paul C. Lambert, Kym I. E. Snell
Summary: This article introduces how to calculate the sample size required for external validation of prediction models, extending guidelines from continuous and binary outcomes to time-to-event outcomes. A simulation-based framework is proposed to calculate the sample size needed for precise estimation of calibration, discrimination, and net-benefit in datasets containing censoring. Assumptions about the validation population and distribution of the model's linear predictor are essential for this process.
STATISTICS IN MEDICINE
(2022)
Article
Public, Environmental & Occupational Health
Ramy Mohamed Ghazy, Sally Waheed Elkhadry, Suzan Abdel-Rahman, Sarah Hamed N. Taha, Naglaa Youssef, Abdelhamid Elshabrawy, Sarah Assem Ibrahim, Salah Al Awaidy, Tareq Al-Ahdal, Bijaya Kumar Padhi, Noha Fadl
Summary: This study aims to externally validate the PACV scale and assess parents' attitude toward seasonal influenza vaccination in six different countries. The results show that the PACV has good predictive ability and accuracy among parents in these countries, making it a useful tool for assessing parental attitudes towards influenza vaccination.
FRONTIERS IN PUBLIC HEALTH
(2023)
Article
Anesthesiology
Shubhangi Singh, Daniela A. Carusi, Penny Wang, Elena Reitman-Ivashkov, Ruth Landau, Kara G. Fields, Carolyn F. Weiniger, Michaela K. Farber
Summary: The Weiniger model, which predicts placenta accreta spectrum (PAS), showed variable performance depending on the case-mix of the population with regard to PAS clinical risk factors and ultrasound features. The model was beneficial for predicting PAS in populations with substantial case-mix heterogeneity at a threshold probability of >25%.
ANESTHESIA AND ANALGESIA
(2023)
Article
Endocrinology & Metabolism
Hui Zhang, Dandan Chen, Jin Shao, Ping Zou, Nianqi Cui, Leiwen Tang, Xiyi Wang, Dan Wang, Zhihong Ye
Summary: The externally validated prediction model for metabolic syndrome risk in adults showed good discrimination and calibration, indicating its accuracy in predicting the risk. However, further validation in international and prospective cohorts is recommended for broader applicability.
DIABETES METABOLIC SYNDROME AND OBESITY-TARGETS AND THERAPY
(2021)
Article
Public, Environmental & Occupational Health
Chava L. Ramspek, Lucy Teece, Kym I. E. Snell, Marie Evans, Richard D. Riley, Maarten van Smeden, Nan van Geloven, Merel van Diepen
Summary: This article discusses how to account for competing events when validating prognostic models, using an example of kidney failure prediction. The results show that the 5-year prediction model overestimates the risk of kidney failure when competing events are considered.
INTERNATIONAL JOURNAL OF EPIDEMIOLOGY
(2022)
Review
Clinical Neurology
Femke Kremers, Esmee Venema, Martijne Duvekot, Lonneke Yo, Reinoud Bokkers, Geert Lycklama A. Nijeholt, Adriaan van Es, Aad van der Lugt, Charles Majoie, James Burke, Bob Roozenbeek, Hester Lingsma, Diederik Dippel
Summary: This study provides an overview and validation of prediction models for functional outcome after endovascular treatment in acute ischemic stroke patients. The results show that the THRIVE-c score and MR PREDICTS score have good performance in predicting functional outcome.
Article
Health Care Sciences & Services
Tsvetan R. Yordanov, Ricardo R. Lopes, Anita C. J. Ravelli, Marije Vis, Saskia Houterman, Henk Marquering, Ameen Abu-Hanna
Summary: This study aims to validate prediction models for 30-day mortality in transcatheter aortic valve implantation (TAVI) using multicenter data. The study found that the predictive performance varied among hospitals, with a range of AUCs and miscalibration in some hospitals. Case mix differences between hospitals were substantial, indicating low model transportability.
JOURNAL OF CLINICAL EPIDEMIOLOGY
(2023)
Article
Oncology
Timofei Biziaev, Michelle L. Aktary, Qinggang Wang, Thierry Chekouo, Parveen Bhatti, Lorraine Shack, Paula J. Robson, Karen A. Kopciuk
Summary: This study identified factors related to the stage of cancer diagnosis and developed risk prediction models for males and females. The models were validated and showed acceptable calibration but poor discrimination when applied to external data. Updating the models with additional predictors may improve their predictive performance.
Article
Geriatrics & Gerontology
William J. Doherty, Thomas A. Stubbs, Andrew Chaplin, Mike R. Reed, Avan A. Sayer, Miles D. Witham, Antony K. Sorial
Summary: The study assessed the Nottingham Hip Fracture Score (NHFS) for prediction of mortality, physical function, length of stay, and postoperative complications, finding that NHFS performed consistently well in predicting functional outcomes, moderately in predicting mortality, but less well in predicting length of stay and complications.
JOURNAL OF THE AMERICAN MEDICAL DIRECTORS ASSOCIATION
(2021)
Article
Chemistry, Analytical
An Li, Xinyu Zhang, Xianshuang Wang, Yage He, Yunsong Yin, Ruibin Liu
Summary: This study proposed a new algorithm for high-accuracy quantitative analysis of coal using small sample size machine learning, which improves prediction accuracy for small samples through specific data extraction and data resampling.
JOURNAL OF ANALYTICAL ATOMIC SPECTROMETRY
(2022)
Article
Cardiac & Cardiovascular Systems
Yanghui Xu, Yunjiao Meng, Xuan Qian, Honglei Wu, Yanmei Liu, Peipei Ji, Honglin Chen
Summary: The aim of this study was to construct a nomogram model for discriminating the risk of delirium in patients undergoing cardiovascular surgery. Logistic regression analysis identified CPB duration, postoperative serum sodium, age, and postoperative MV as independent risk factors for delirium. The established model showed good predictive performance and can assist medical staff in preventing postoperative delirium.
JOURNAL OF CARDIOTHORACIC SURGERY
(2022)
Article
Primary Health Care
Constantinos Koshiaris, Lucinda Archer, Sarah Lay-Flurrie, Kym I. E. Snell, Richard D. Riley, Richard Stevens, Amitava Banerjee, Juliet A. Usher-Smith, Andrew Clegg, Rupert A. Payne, Margaret Ogden, F. D. Richard Hobbs, Richard J. McManus, James P. Sheppard
Summary: This study developed a prediction model to estimate the risk of acute kidney injury (AKI) in people potentially indicated for antihypertensive treatment. The model showed good accuracy in identifying high-risk patients and provided reassurance for the majority of low-risk patients, indicating the safety and appropriateness of antihypertensive treatment.
BRITISH JOURNAL OF GENERAL PRACTICE
(2023)
Review
Clinical Neurology
Alan Nagington, Nadine E. Foster, Kym Snell, Kika Konstantinou, Siobhan Stynes
Summary: This systematic review aimed to identify prognostic factors associated with outcomes following epidural steroid injection (ESI) for patients with imaging confirmed disc-related sciatica. The review found limited evidence and low quality studies regarding prognostic factors for this treatment. Future well-designed prospective cohort studies are needed to determine these factors.
EUROPEAN SPINE JOURNAL
(2023)
Article
Multidisciplinary Sciences
Ruth Walker, Bob Phillips, Sofia Dias
Summary: Recruiting children for randomized clinical trials poses challenges, resulting in less certainty about the safety and effectiveness of treatments compared to adults. However, it is possible to use adult evidence to better understand the effectiveness of treatments in children, and there are various statistical methods available for conducting these analyses.
Review
Medicine, General & Internal
Kara G. Fields, Jie Ma, Tatjana Petrinic, Hassan Alhassan, Anthony Eze, Ankith Reddy, Mona Hedayat, Rui Providencia, Gregory Y. H. Lip, Jonathan P. Bedford, David A. Clifton, Oliver C. Redfern, Benjamin O'Brien, Peter J. Watkinson, Gary S. Collins, Jochen D. Muehlschlegel
Summary: This systematic review aims to critically appraise the methodology and risk of bias in the development and validation of multivariable prediction models for atrial fibrillation after cardiac surgery (AFACS). The findings will be disseminated to improve future studies and provide a clinically useful risk estimation tool.
Article
Medicine, General & Internal
Epaminondas Markos Valsamis, Gary S. Collins, Rafael Pinedo-Villanueva, Michael R. Whitehouse, Amar Rangan, Adrian Sayers, Jonathan L. Rees
Summary: This study aimed to investigate the association between surgeon volume and patient outcomes after elective shoulder replacement surgery. The results showed that surgeons with an average annual volume of more than 10.4 procedures had lower rates of revision surgery and reoperation, lower risk of serious adverse events, and shorter hospital stays.
BMJ-BRITISH MEDICAL JOURNAL
(2023)
Article
Pediatrics
Kenneth S. Gunasekera, Olivier Marcy, Johanna Munoz, Elisa Lopez-Varela, Moorine P. Sekadde, Molly F. Franke, Maryline Bonnet, Shakil Ahmed, Farhana Amanullah, Aliya Anwar, Orvalho Augusto, Rafaela Baroni Aurilio, Sayera Banu, Iraj Batool, Annemieke Brands, Kevin P. Cain, Lucia Carratala-Castro, Maxine Caws, Eleanor S. Click, Lisa M. Cranmer, Alberto L. Garcia-Basteiro, Anneke C. Hesseling, Julie Huynh, Senjuti Kabir, Leonid Lecca, Anna Mandalakas, Farai Mavhunga, AyeAye Myint, Kyaw Myo, Dorah Nampijja, Mark P. Nicol, Patrick Orikiriza, Megan Palmer, Clemax Couto Sant'Anna, Sara Ahmed Siddiqui, Jonathan P. Smith, Rinn Song, Nguyen Thuy Thuong Thuong, Vibol Ung, Marieke M. van der Zalm, Sabine Verkuijl, Kerri Viney, Elisabetta G. Walters, Joshua L. Warren, Heather J. Zar, Ben J. Marais, Stephen M. Graham, Thomas P. A. Debray, Ted Cohen, James A. Seddon
Summary: This study evaluated the performance of current diagnostic algorithms for pediatric tuberculosis and developed evidence-based algorithms using prediction modeling to assist in treatment decision-making. The existing treatment-decision algorithms had highly variable diagnostic performance. The scoring system derived from the prediction model that included clinical and chest x-ray features had higher sensitivity and lower specificity, while the scoring system derived from clinical features only also accurately diagnosed tuberculosis to some extent.
LANCET CHILD & ADOLESCENT HEALTH
(2023)
Article
Mathematical & Computational Biology
Richard D. Riley, Gary S. Collins
Summary: Clinical prediction models estimate an individual's risk of a particular health outcome. Many models are developed using small datasets, leading to instability in the model and its predictions. Researchers should examine instability at the model development stage and propose instability plots and measures to assess model reliability and inform critical appraisal, fairness, and validation requirements.
BIOMETRICAL JOURNAL
(2023)
Article
Mathematical & Computational Biology
J. Hoogland, T. P. A. Debray, M. J. Crowther, R. D. Riley, J. Inthout, J. B. Reitsma, A. H. Zwinderman
Summary: This study proposes a method that combines flexible parametric survival modeling and regularization to improve risk prediction models for time-to-event data. By introducing different penalty terms, the models can be regularized to enhance prediction accuracy and model performance.
BIOMETRICAL JOURNAL
(2023)
Review
Health Care Sciences & Services
Paula Dhiman, Jie Ma, Victoria N. Gibbs, Alexandros Rampotas, Hassan Kamal, Sahar S. Arshad, Shona Kirtley, Carolyn Doree, Michael F. Murphy, Gary S. Collins, Antony J. R. Palmer
Summary: This study conducted a systematic review and found that most blood transfusion prediction models have a high risk of bias and poor methodological quality, which need to be improved and enhanced in clinical practice.
JOURNAL OF CLINICAL EPIDEMIOLOGY
(2023)
Article
Health Care Sciences & Services
Francesco Cottone, Fabio Efficace, David Cella, Neil K. Aaronson, Johannes M. Giesinger, Jean-Baptiste Bachet, Christophe Louvet, Emilie Charton, Gary S. Collins, Amelie Anota
Summary: This study applied the estimand framework to analyze time to deterioration in patient-reported outcomes. The results showed significant differences in estimates depending on the statistical methods used, especially when considering death as a competing risk. Therefore, the Fine-Gray competing risks model should be considered to reflect the patient's experience of the disease and treatment burden.
JOURNAL OF CLINICAL EPIDEMIOLOGY
(2023)
Review
Psychiatry
Ita Fitzgerald, Laura J. Sahm, Amy Byrne, Jean O'Connell, Joie Ensor, Ciara Ni Dhubhlaing, Sarah O'Dwyer, Erin K. Crowley
Summary: This study systematically explored the impact of non-genetic prognostic factors on the variable prognosis of antipsychotic-induced weight gain (AIWG). The results showed that age, baseline BMI, and sex had nonsignificant effects on AIWG prognosis. However, the trend of early BMI increase was identified as the most clinically significant prognostic factor, which should be included in AIWG management guidance.
EUROPEAN PSYCHIATRY
(2023)
Article
Rheumatology
Manuela L. Ferreira, Katie de Luca, Lydia M. Haile, Jaimie Steinmetz, Garland Culbreth, Marita Cross, Jacek A. Kopec, Paulo H. Ferreira, Fiona M. Blyth, Rachelle Buchbinder, Jan Hartvigsen, Ai-Min Wu, Saeid Safiri, Anthony Woolf, Gary S. Collins, Kanyin Liane Ong, Stein Emil Vollset, Amanda E. Smith, Jessica A. Cruz, Kai Glenn Fukutaki, Semagn Mekonnen Abate, Mitra Abbasifard, Mohsen Abbasi-Kangevari, Zeinab Abbasi-Kangevari, Ahmed Abdelalim, Aidin Abedi, Hassan Abidi, Qorinah Estiningtyas Sakilah Adnani, Ali Ahmadi, Rufus Olusola Akinyemi, Abayneh Tadesse Alamer, Adugnaw Zeleke Alem, Yousef Alimohamadi, Mansour Abdullah Alshehri, Mohammed Mansour Alshehri, Hosam Alzahrani, Saeed Amini, Sohrab Amiri, Hubert Amu, Catalina Liliana Andrei, Tudorel Andrei, Benny Antony, Jalal Arabloo, Judie Arulappan, Ashokan Arumugam, Tahira Ashraf, Seyyed Shamsadin Athari, Nefsu Awoke, Sina Azadnajafabad, Till Winfried Baernighausen, Lope H. Barrero, Amadou Barrow, Akbar Barzegar, Lindsay M. Bearne, Isabela M. Bensenor, Alemshet Yirga Berhie, Bharti Bhandari Bhandari, Vijayalakshmi S. Bhojaraja, Ali Bijani, Belay Boda Abule Bodicha, Srinivasa Rao Bolla, Javier Brazo-Sayavera, Andrew M. Briggs, Chao Cao, Periklis Charalampous, Vijay Kumar Chattu, Flavia M. Cicuttini, Benjamin Clarsen, Sarah Cuschieri, Omid Dadras, Xiaochen Dai, Lalit Dandona, Rakhi Dandona, Azizallah Dehghan, Takele Gezahegn G. Demie, Edgar Denova-Gutierrez, Syed Masudur Rahman Dewan, Samath Dhamminda Dharmaratne, Mandira Lamichhane Dhimal, Meghnath Dhimal, Daniel Diaz, Mojtaba Didehdar, Lankamo Ena Digesa, Mengistie Diress, Hoa Thi Do, Linh Phuong Doan, Michael Ekholuenetale, Muhammed Elhadi, Sharareh Eskandarieh, Shahriar Faghani, Jawad Fares, Ali Fatehizadeh, Getahun Fetensa, Irina Filip, Florian Fischer, Richard Charles Franklin, Balasankar Ganesan, Belete Negese Belete Gemeda, Motuma Erena Getachew, Ahmad Ghashghaee, Tiffany K. Gill, Mahaveer Golechha, Pouya Goleij, Bhawna Gupta, Nima Hafezi-Nejad, Arvin Haj-Mirzaian, Pawan Kumar Hamal, Asif Hanif, Netanja Harlianto, Hamidreza Hasani, Simon Hay, Jeffrey J. Hebert, Golnaz Heidari, Mohammad Heidari, Reza Heidari-Soureshjani, Mbuzeleni Mbuzeleni Hlongwa, Mohammad-Salar Hosseini, Alexander Kevin Hsiao, Ivo Iavicoli, Segun Emmanuel Ibitoye, Irena M. Ilic, Milena Ilic, Sheikh Mohammed Shariful Islam, Manthan Dilipkumar Janodia, Ravi Prakash Jha, Har Ashish Jindal, Jost B. Jonas, Gebisa Guyasa Kabito, Himal Kandel, Rimple Jeet Kaur, Vikash Ranjan Keshri, Yousef Saleh Khader, Ejaz Ahmad Khan, Md Jobair Khan, Moien AB Khan, Hamid Reza Khayat Kashani, Jagdish Khubchandani, Yun Jin Kim, Adnan Kisa, Jitka Klugarova, Ali-Asghar Kolahi, Hamid Reza Koohestani, Ai Koyanagi, G. Anil Kumar, Narinder Kumar, Tea Lallukka, Savita Lasrado, Wei-Chen Lee, Yo Han Lee, Ata Mahmoodpoor, Jeadran N. Malagon-Rojas, Mohammad-Reza Malekpour, Reza Malekzadeh, Narges Malih, Man Mohan Mehndiratta, Entezar Mehrabi Nasab, Ritesh G. Menezes, Alexios-Fotios A. Mentis, Mohamed Kamal Mesregah, Ted R. Miller, Mohammad Mirza-Aghazadeh-Attari, Maryam Mobarakabadi, Yousef Mohammad, Esmaeil Mohammadi, Shafiu Mohammed, Ali H. Mokdad, Sara Momtazmanesh, Lorenzo Monasta, Mohammad Ali Moni, Ebrahim Mostafavi, Christopher J. L. Murray, Tapas Sadasivan Nair, Javad Nazari, Seyed Aria Nejadghaderi, Subas Neupane, Sandhya Neupane Kandel, Cuong Tat Nguyen, Ali Nowroozi, Hassan Okati-Aliabad, Emad Omer, Abderrahim Oulhaj, Mayowa Owolabi, Songhomitra Panda-Jonas, Anamika Pandey, Eun-Kee Park, Shrikant Pawar, Paolo Pedersini, Jeevan Pereira, Mario F. P. Peres, Ionela-Roxana Petcu, Mohammadreza Pourahmadi, Amir Radfar, Shahram Rahimi-Dehgolan, Vafa Rahimi-Movaghar, Mosiur Rahman, Amir Masoud Rahmani, Nazanin Rajai, Chythra R. Rao, Vahid Rashedi, Mohammad-Mahdi Rashidi, Zubair Ahmed Ratan, David Laith Rawaf, Salman Rawaf, Andre M. N. Renzaho, Negar Rezaei, Zahed Rezaei, Leonardo Roever, Guilherme de Andrade Ruela, Basema Saddik, Amirhossein Sahebkar, Sana Salehi, Francesco Sanmarchi, Sadaf G. Sepanlou, Saeed Shahabi, Shayan Shahrokhi, Elaheh Shaker, Mohammadbagher Shamsi, Mohammed Shannawaz, Saurab Sharma, Maryam Shaygan, Rahim Ali Sheikhi, Jeevan K. Shetty, Rahman Shiri, Siddharudha Shivalli, Parnian Shobeiri, Migbar Mekonnen Sibhat, Ambrish Singh, Jasvinder A. Singh, Helen Slater, Marco Solmi, Ranjani Somayaji, Ker-Kan Tan, Rekha Thapar, Seyed Abolfazl Tohidast, Sahel Valadan Tahbaz, Rohollah Valizadeh, Tommi Juhani Vasankari, Narayanaswamy Venketasubramanian, Vasily Vlassov, Bay Vo, Yuan-Pang Wang, Taweewat Wiangkham, Lalit Yadav, Ali Yadollahpour, Seyed Hossein Yahyazadeh Jabbari, Lin Yang, Fereshteh Yazdanpanah, Naohiro Yonemoto, Mustafa Z. Younis, Iman Zare, Armin Zarrintan, Mohammad Zoladl, Theo Vos, Lyn M. March
Summary: This study provides the most up-to-date global, regional, and national data on the prevalence and years lived with disability (YLDs) for low back pain. It reveals that low back pain is the leading cause of YLDs globally and projects that there will be over 800 million cases of low back pain worldwide by 2050. Challenges persist in obtaining primary country-level data on low back pain, highlighting the need for more high-quality data to improve accuracy and monitoring of the condition.
LANCET RHEUMATOLOGY
(2023)
Article
Medical Informatics
Ash Kieran Clift, Gary S. Collins, Simon Lord, Stavros Petrou, David Dodwell, Michael Brady, Julia Hippisley-Cox
Summary: This study aims to develop a prognostic model that accurately predicts the 10-year risk of breast cancer mortality in female individuals without breast cancer at baseline.
LANCET DIGITAL HEALTH
(2023)
Article
Primary Health Care
Constantinos Koshiaris, Lucinda Archer, Sarah Lay-Flurrie, Kym I. E. Snell, Richard D. Riley, Richard Stevens, Amitava Banerjee, Juliet A. Usher-Smith, Andrew Clegg, Rupert A. Payne, Margaret Ogden, F. D. Richard Hobbs, Richard J. McManus, James P. Sheppard
Summary: A prediction model has been developed in this study to aid treatment decisions by identifying high-risk AKI patients.
BRITISH JOURNAL OF GENERAL PRACTICE
(2023)