id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-102276-0a8hup5y	Savage, R. S.	Development and validation of multivariable machine learning algorithms to predict risk of cancer in symptomatic patients referred urgently from primary care	2020-10-27		.txt	text/plain	3792	227	57	title: Development and validation of multivariable machine learning algorithms to predict risk of cancer in symptomatic patients referred urgently from primary care In use-case 1, the algorithms correctly identify 20% of patients who do not have cancer and may not need an urgent 2WW referral. 10 We report the development and validation of a set of machine learning algorithms to provide a calibrated risk probability of cancer (a score between zero and one, higher values indicating greater risk of cancer) for triaging symptomatic patients. Table 6 shows test performance characteristics for use-case 2 (triage), to identify patients at higher risk of cancer who would be considered for priority through the urgent referral pathway. This paper reports the development and validation of a set of statistical machine learning algorithms based on routine laboratory blood measurements that can predict cancer outcomes for symptomatic patients referred urgently from primary care for possible cancer diagnosis.	./cache/cord-102276-0a8hup5y.txt	./txt/cord-102276-0a8hup5y.txt