Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

Clinical applications and limitations of large language models in nephrology: a systematic review

Z. Unger, S. Soffer, O. Efros, L. Chan, E. Klang, GN. Nadkarni

. 2025 ; 18 (9) : sfaf243. [pub] 20250918

Status neindexováno Jazyk angličtina Země Anglie, Velká Británie

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc25020370

BACKGROUND: Large language models (LLMs) have emerged as potential tools in healthcare. This systematic review evaluates the applications of text-generative conversational LLMs in nephrology, with particular attention to their reported advantages and limitations. METHODS: A systematic search was performed in PubMed, Web of Science, Embase and the Cochrane Library in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Eligible studies assessed LLM applications in nephrology. PROSPERO registration number CRD42024550169. RESULTS: Of 1070 records screened, 23 studies met inclusion criteria, addressing four clinical applications in nephrology. In patient education (n = 13), GPT-4 improved the readability of kidney donation information from a 10th to a 4th grade level (9.6 ± 1.9 to 4.30 ± 1.71) and Gemini provided the most accurate answers to chronic kidney disease questions (Global Quality Score 3.46 ± 0.55). Regarding workflow optimization (n = 7), GPT-4 achieved high accuracy (90-94%) in managing continuous renal replacement therapy alarms and improved diagnosis of diabetes insipidus using chain-of-thought and retrieval-augmented prompting. In renal dietary guidance (n = 2), Bard AI led in classifying phosphorus and oxalate content of foods (100% and 84%), while GPT-4 and Bing Chat were most accurate for potassium classification (81%). For laboratory data interpretation (n = 1), Copilot significantly outperformed ChatGPT and Gemini in simulated nephrology datasets (median scores 5/5 compared with 4/5 and 4/5; P < .01). TRIPOD-LLM assessment revealed frequent omissions in data handling, prompting strategies and transparency. CONCLUSIONS: While LLMs may enhance various aspects of nephrology practice, their widespread adoption remains premature. Input-quality dependence and limited external validation restrict generalizability. Further research is needed to confirm their real-world feasibility and ensure safe clinical integration.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc25020370
003      
CZ-PrNML
005      
20251014150326.0
007      
ta
008      
251007s2025 enk f 000 0|eng||
009      
AR
024    7_
$a 10.1093/ckj/sfaf243 $2 doi
035    __
$a (PubMed)41018275
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a enk
100    1_
$a Unger, Zoe $u First Faculty of Medicine, Charles University, Prague, Czech Republic $1 https://orcid.org/0009000486409479
245    10
$a Clinical applications and limitations of large language models in nephrology: a systematic review / $c Z. Unger, S. Soffer, O. Efros, L. Chan, E. Klang, GN. Nadkarni
520    9_
$a BACKGROUND: Large language models (LLMs) have emerged as potential tools in healthcare. This systematic review evaluates the applications of text-generative conversational LLMs in nephrology, with particular attention to their reported advantages and limitations. METHODS: A systematic search was performed in PubMed, Web of Science, Embase and the Cochrane Library in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Eligible studies assessed LLM applications in nephrology. PROSPERO registration number CRD42024550169. RESULTS: Of 1070 records screened, 23 studies met inclusion criteria, addressing four clinical applications in nephrology. In patient education (n = 13), GPT-4 improved the readability of kidney donation information from a 10th to a 4th grade level (9.6 ± 1.9 to 4.30 ± 1.71) and Gemini provided the most accurate answers to chronic kidney disease questions (Global Quality Score 3.46 ± 0.55). Regarding workflow optimization (n = 7), GPT-4 achieved high accuracy (90-94%) in managing continuous renal replacement therapy alarms and improved diagnosis of diabetes insipidus using chain-of-thought and retrieval-augmented prompting. In renal dietary guidance (n = 2), Bard AI led in classifying phosphorus and oxalate content of foods (100% and 84%), while GPT-4 and Bing Chat were most accurate for potassium classification (81%). For laboratory data interpretation (n = 1), Copilot significantly outperformed ChatGPT and Gemini in simulated nephrology datasets (median scores 5/5 compared with 4/5 and 4/5; P < .01). TRIPOD-LLM assessment revealed frequent omissions in data handling, prompting strategies and transparency. CONCLUSIONS: While LLMs may enhance various aspects of nephrology practice, their widespread adoption remains premature. Input-quality dependence and limited external validation restrict generalizability. Further research is needed to confirm their real-world feasibility and ensure safe clinical integration.
590    __
$a NEINDEXOVÁNO
655    _2
$a časopisecké články $7 D016428
700    1_
$a Soffer, Shelly $u Institute of Hematology, Davidoff Cancer Center, Rabin Medical Center, Petah-Tikva, Israel $u School of Medicine, Tel Aviv University, Tel Aviv, Israel $1 https://orcid.org/0000000278532029
700    1_
$a Efros, Orly $u School of Medicine, Tel Aviv University, Tel Aviv, Israel $u National Hemophilia Center and Thrombosis Institute, Sheba Medical Center, Ramat Gan, Israel $1 https://orcid.org/0000000260249110
700    1_
$a Chan, Lili $u Division of Data-Driven and Digital Medicine (D3M), Icahn School of Medicine at Mount Sinai, New York, NY, USA $u Charles Bronfman Institute of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA $u Barbara T. Murphy Division of Nephrology, Icahn School of Medicine at Mount Sinai, New York, NY, USA
700    1_
$a Klang, Eyal $u Division of Data-Driven and Digital Medicine (D3M), Icahn School of Medicine at Mount Sinai, New York, NY, USA $u Charles Bronfman Institute of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
700    1_
$a Nadkarni, Girish N $u Division of Data-Driven and Digital Medicine (D3M), Icahn School of Medicine at Mount Sinai, New York, NY, USA $u Charles Bronfman Institute of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA $u Barbara T. Murphy Division of Nephrology, Icahn School of Medicine at Mount Sinai, New York, NY, USA
773    0_
$w MED00178639 $t Clinical kidney journal $x 2048-8505 $g Roč. 18, č. 9 (2025), s. sfaf243
856    41
$u https://pubmed.ncbi.nlm.nih.gov/41018275 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20251007 $b ABA008
991    __
$a 20251014150332 $b ABA008
999    __
$a ok $b bmc $g 2410799 $s 1258526
BAS    __
$a 3
BAS    __
$a PreBMC-PubMed-not-MEDLINE
BMC    __
$a 2025 $b 18 $c 9 $d sfaf243 $e 20250918 $i 2048-8505 $m Clinical kidney journal $n Clin Kidney J $x MED00178639
LZP    __
$a Pubmed-20251007

Najít záznam

Citační ukazatele

Pouze přihlášení uživatelé

Možnosti archivace